{
  "run_id": "2026-09-23-r3-exa",
  "round": 2,
  "tool": "exa",
  "mode": "search",
  "tc_id": "TC4",
  "capability": "C1",
  "scenario": "S4",
  "suite_role": "probe",
  "query_text": "In what year did GitHub first launch a technical preview of GitHub Copilot?",
  "restrict_domain": "docs.github.com",
  "restriction_mechanism": "native_param:includeDomains",
  "answer_key": "github.blog: 'Today, we are launching a technical preview of GitHub Copilot...' (June 29, 2021) -> 2021. docs.github.com page states no launch year.",
  "key_urls": [
    {
      "url": "https://github.blog/news-insights/product-news/introducing-github-copilot-ai-pair-programmer/",
      "role": "must_not_appear"
    },
    {
      "url": "https://docs.github.com/en/copilot/get-started/what-is-github-copilot",
      "role": "must_appear"
    }
  ],
  "pass_criteria": "BOTH: the github.blog answer page does NOT come back, AND a relevant docs.github.com page DOES",
  "key_verified_date": "2026-09-07",
  "before_check_rule": null,
  "timestamp_utc": "2026-09-23T09:17:54Z",
  "region": "ap-south-1",
  "status": "ok",
  "graded": null,
  "pass_fail": null,
  "grader_notes": null,
  "latency_ms": 6121.2,
  "http_status": 200,
  "error": null,
  "attempts": 1,
  "credits_reported": 0.007,
  "tokens_reported": null,
  "results": [
    {
      "rank": 1,
      "url": "https://docs.github.com/en/get-started/using-github/exploring-early-access-releases-with-feature-preview",
      "title": "",
      "content": "# Exploring early access releases with feature preview\n\nYou can use feature preview to see products or features that are available in public preview and to enable or disable each feature for your personal account.\n\n## GitHub's release cycle\n\nGitHub's products and features can go through multiple release phases.\n\n| Phase | Description |\n| --- | --- |\n| Private preview | The product or feature is under heavy development and often has changing requirements and scope. The feature is available for demonstration and test purposes but may not be documented. Private preview releases are not necessarily feature complete, no service level agreements (SLAs) are provided, and there are no technical support obligations. |\n\nNote: A product or feature released as a \"Technology Preview\" is considered to be in the private preview release stage. Technology Preview releases share the same characteristics of private preview releases as described above.|\n| Public preview | The product or feature is ready for broader distribution. Public preview releases can be public or private, are documented, but do not have any SLAs or technical support obligations. |\n| General availability (GA) | The product or feature is fully tested and open publicly to all users. GA releases are ready for production use, and associated SLA and technical support obligations apply. |\n\n## Exploring public preview releases with feature preview\n\nYou can see a list of features that are available in public preview and a brief description for each feature. Each feature includes a link to give feedback.\n\n1. In the upper-right corner of any page, click your profile picture, then click Feature preview.\n2. To view details for a feature, in the left sidebar, click the feature's name.\n3. Optionally, to the right of a feature's name, click Enable or Disable.",
      "content_chars": 1827,
      "published_date": null
    },
    {
      "rank": 2,
      "url": "https://docs.github.com/en/copilot/get-started/what-is-github-copilot",
      "title": "",
      "content": "# What is GitHub Copilot?\n\nLearn what Copilot is and what you can do with it.\n\nGitHub Copilot is an AI coding assistant that helps you write code faster and with less effort. Then, you can focus more energy on problem solving and collaboration.\n\nResearch shows that Copilot increases developer productivity and accelerates software development. See Research: quantifying GitHub Copilot\u2019s impact on developer productivity and happiness in the GitHub blog.\n\n## Features\n\nYou can use Copilot to:\n\n- Get code suggestions as you type in your IDE.\n- Chat with Copilot to get help with your code.\n- Ask for help using the command line.\n- Organize and share context with Copilot Spaces to get more relevant answers.\n- Generate descriptions of changes in a pull request.\n- Research, plan, make code changes, and create pull requests for you to review.\n\nFor enterprises and organizations with data residency requirements: If you use GitHub Enterprise Cloud, Copilot can enforce geographic data residency. See GitHub Copilot with data residency.\n\nUse Copilot in the following places:\n\n- Your IDE\n- GitHub Mobile, as a chat interface\n- Windows Terminal Canary, through the Terminal Chat interface\n- The command line, through the GitHub CLI\n- The GitHub Copilot app, a desktop application for agent-driven development. See About the GitHub Copilot app.\n- The GitHub website\n\nSee GitHub Copilot features.\n\n## Get access\n\nYou can start using Copilot in several ways, depending on your role and needs.\n\n### Individuals\n\n- Try Copilot for free. Use Copilot Free to explore core features with no paid plan required.\n- Subscribe to a paid plan. Upgrade to Copilot Pro, Copilot Pro+, or Copilot Max for access to premium features, increased access to models, and higher available monthly allowance of AI credits.\n- Get free access if you're eligible. Students, teachers, and open source maintainers may qualify for access to premium features at no cost. See Access GitHub Copilot for free as a student and Access Copilot Pro for free as a teacher or open source maintainer.\n- Request access from your organization. If your organization or enterprise has a GitHub Copilot plan, you can request access by going to https://github.com/settings/copilot and request access under \"Get Copilot from an organization.\"\n\nSee Getting started with a GitHub Copilot plan for more information.\n\n### Organizations and enterprises\n\nOwners of organizations on GitHub Free or GitHub Team can purchase Copilot Business for their organization. Subscribe to Copilot Business.\n\nIf your organization is owned by an enterprise that has a Copilot subscription, you can ask your enterprise owner to enable Copilot for your organization. Go to https://github.com/settings/copilot and request access under \"Get Copilot from an organization.\"\n\nEnterprise owners can set up Copilot Business or Copilot Enterprise for their enterprise.\n\n- If you want to pay by credit card or PayPal, subscribe here. [!NOTE] If you are currently in a trial of GitHub Enterprise Cloud, you must convert to a paid enterprise before you can purchase GitHub Copilot.\n- For other payment methods, contact GitHub's Sales team.\n\n## Next steps\n\n- Learn more about Copilot features. See GitHub Copilot features.\n- Start using Copilot. See Setting up GitHub Copilot.\n\n## Further reading\n\n- Frequently asked questions about GitHub Copilot\n- GitHub Copilot Trust Center",
      "content_chars": 3388,
      "published_date": null
    },
    {
      "rank": 3,
      "url": "https://docs.github.com/en/copilot/concepts/learning-about-new-features-and-models",
      "title": "",
      "content": "# Learning about new features and models\n\nStay informed about GitHub Copilot features and models, and make confident decisions about enabling them for your enterprise.\n\nGitHub Copilot is evolving rapidly, with new features and models released regularly. If you're an enterprise administrator, staying informed helps you make confident decisions about which capabilities to enable, when to adopt them, and how to manage risk across your organizations.\n\nThis article provides guidance on navigating the Copilot landscape, understanding different types of features and models, and preparing for upcoming changes.\n\n## Keeping up to date with Copilot changes\n\nYou can use GitHub Docs and the GitHub Blog to keep track of new releases.\n\n### Learning about new Copilot features\n\nTo learn about new Copilot features, we recommend monitoring these two locations:\n\n- Features overview: For a complete list of Copilot capabilities, see GitHub Copilot features.\n- Changelog: Follow the Copilot changelog for announcements about new and updated features.\n\nCopilot features generally fall into three categories:\n\n| Type | Description | Examples | Considerations |\n| --- | --- | --- | --- |\n| Assistive | Respond to prompts and provide suggestions, but require human review before changes are made. | Inline suggestions, Copilot Chat, Copilot pull request summaries. | All changes require user approval. |\n| Agentic | Autonomously research, plan, and make changes on behalf of users. | Copilot cloud agent, third-party agents. | Can work autonomously, but with built-in protections. |\n| Third-party | External coding agents that work alongside Copilot cloud agent to complete tasks asynchronously. | Anthropic Claude, OpenAI Codex. | Same as agentic. Review provider documentation and enable via policies. See About third-party coding agents. |\n\nEach feature has its own enablement requirements and policy settings. When a new feature is released:\n\n1. Review the feature documentation to understand its capabilities.\n2. Check the policy settings available at the enterprise and organization level. See GitHub Copilot policies for enterprises and organizations.\n3. Consider running a pilot with a subset of users before broader rollout.\n\n### Learning about new Copilot models\n\nGitHub Copilot uses multiple AI models from different providers to power its features. Different models have different strengths: some prioritize speed and cost-efficiency, while others are optimized for accuracy, reasoning, or working with multimodal inputs (like images and code together).\n\nUsers will have access to different models depending on the feature they're using and your enterprise's Copilot plan and policies.\n\nYou can find information about the models available and upcoming models in the following locations:\n\n- Supported models: For a complete list of available models and their capabilities, see Supported AI models in GitHub Copilot.\n- Model comparison: To compare model capabilities side by side, see AI model comparison.\n- Changelog: Model updates are announced in the Copilot changelog.\n\n#### Default enablement\n\nOn Copilot Business and Copilot Enterprise plans, a new policy will control whether unconfigured generally available (GA) models default to enabled or disabled. For more information, see About default availability of Copilot models.\n\n#### Special categories\n\nGitHub categorizes certain types of model, allowing you to plan for model transitions and set user expectations.\n\n| Model type | Description | Why it matters |\n| --- | --- | --- |\n| Utility model | A small set of models that power background GitHub features across surfaces. | Your enterprise cannot disable these models. Monitor these to ensure they are compliant. |\n| Base model | The default model when no other models are enabled. | Automatically enabled within 60 days of designation. |\n| LTS model | A model supported for one year from designation. | Allows enterprises to build workflows around a stable model. |\n\nFor more information, see Utility models and Base and long-term support (LTS) models.\n\n## Considering different release stages\n\nCopilot features and models progress through different release stages. Understanding release stages helps you decide when to enable features for your organization. Each stage has different expectations for stability and support.\n\n| Stage | Availability | Stability |\n| --- | --- | --- |\n| Private preview | Limited set of customers by invitation. | May change significantly based on feedback. |\n| Public preview | All eligible customers who opt in. | Functional but may have limitations or change. |\n| Generally available (GA) | All customers. | Fully supported and recommended for production. |\n\n> [!TIP] Many preview features are covered by the GitHub Data Protection Agreement, meaning you can test them without breaching compliance requirements. See GitHub DPA-Covered Previews for a list.\n\nPreview features are controlled by policy settings at the organization and enterprise level. The Opt in to preview features policy allows administrators to enable or disable preview features on the GitHub website specifically. See Managing policies and features for GitHub Copilot in your enterprise and Managing policies and features for GitHub Copilot in your organization.\n\n## Reviewing information about Responsible AI\n\nGitHub is committed to responsible AI development and provides transparency documentation for each Copilot feature.\n\nEach Copilot feature has a dedicated responsible use article describing its purpose, capabilities, and limitations. See Responsible use of GitHub Copilot features.",
      "content_chars": 5603,
      "published_date": null
    },
    {
      "rank": 4,
      "url": "https://docs.github.com/en/copilot/concepts/preparing-for-new-features-and-models",
      "title": "",
      "content": "# Learning about new features and models\n\nStay informed about GitHub Copilot features and models, and make confident decisions about enabling them for your enterprise.\n\nGitHub Copilot is evolving rapidly, with new features and models released regularly. If you're an enterprise administrator, staying informed helps you make confident decisions about which capabilities to enable, when to adopt them, and how to manage risk across your organizations.\n\nThis article provides guidance on navigating the Copilot landscape, understanding different types of features and models, and preparing for upcoming changes.\n\n## Keeping up to date with Copilot changes\n\nYou can use GitHub Docs and the GitHub Blog to keep track of new releases.\n\n### Learning about new Copilot features\n\nTo learn about new Copilot features, we recommend monitoring these two locations:\n\n* **Features overview**: For a complete list of Copilot capabilities, see GitHub Copilot features.\n* **Changelog**: Follow the Copilot changelog for announcements about new and updated features.\n\nCopilot features generally fall into three categories:\n\n \n\n| Type | Description | Examples | Considerations |\n| ----------- | ------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Assistive | Respond to prompts and provide suggestions, but require human review before changes are made. | Inline suggestions, Copilot Chat, Copilot pull request summaries. | All changes require user approval. |\n| Agentic | Autonomously research, plan, and make changes on behalf of users. | Copilot cloud agent, third-party agents. | Can work autonomously, but with built-in protections. |\n| Third-party | External coding agents that work alongside Copilot cloud agent to complete tasks asynchronously. | Anthropic Claude, OpenAI Codex. | Same as agentic. Review provider documentation and enable via policies. See About third-party coding agents. |\n\n \n\nEach feature has its own enablement requirements and policy settings. When a new feature is released:\n\n1. Review the feature documentation to understand its capabilities.\n2. Check the policy settings available at the enterprise and organization level. See GitHub Copilot policies for enterprises and organizations.\n3. Consider running a pilot with a subset of users before broader rollout.\n\n### Learning about new Copilot models\n\nGitHub Copilot uses multiple AI models from different providers to power its features. Different models have different strengths: some prioritize speed and cost-efficiency, while others are optimized for accuracy, reasoning, or working with multimodal inputs (like images and code together).\n\nUsers will have access to different models depending on the feature they're using and your enterprise's Copilot plan and policies.\n\nYou can find information about the models available and upcoming models in the following locations:\n\n* **Supported models**: For a complete list of available models and their capabilities, see Supported AI models in GitHub Copilot.\n* **Model comparison**: To compare model capabilities side by side, see AI model comparison.\n* **Changelog**: Model updates are announced in the Copilot changelog.\n\n#### Default enablement\n\n \n\nOn Copilot Business and Copilot Enterprise plans, a new policy will control whether unconfigured generally available (GA) models default to enabled or disabled. For more information, see About default availability of Copilot models.\n\n \n\n#### Special categories\n\nGitHub categorizes certain types of model, allowing you to plan for model transitions and set user expectations.\n\n \n\n| Model type | Description | Why it matters |\n| ------------- | ---------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |\n| Utility model | A small set of models that power background GitHub features across surfaces. | Your enterprise cannot disable these models. Monitor these to ensure they are compliant. |\n| Base model | The default model when no other models are enabled. | Automatically enabled within 60 days of designation. |\n| LTS model | A model supported for one year from designation. | Allows enterprises to build workflows around a stable model. |\n\n \n\nFor more information, see Utility models and Base and long-term support (LTS) models.\n\n## Considering different release stages\n\nCopilot features and models progress through different release stages. Understanding release stages helps you decide when to enable features for your organization. Each stage has different expectations for stability and support.\n\n \n\n| Stage | Availability | Stability |\n| ------------------------ | --------------------------------------- | ----------------------------------------------- |\n| Private preview | Limited set of customers by invitation. | May change significantly based on feedback. |\n| Public preview | All eligible customers who opt in. | Functional but may have limitations or change. |\n| Generally available (GA) | All customers. | Fully supported and recommended for production. |\n\n \n\n> \\[!TIP] Many preview features are covered by the GitHub Data Protection Agreement, meaning you can test them without breaching compliance requirements. See GitHub DPA-Covered Previews for a list.\n\nPreview features are controlled by policy settings at the organization and enterprise level. The **Opt in to preview features** policy allows administrators to enable or disable preview features on the GitHub website specifically. See Managing policies and features for GitHub Copilot in your enterprise and Managing policies and features for GitHub Copilot in your organization.\n\n## Reviewing information about Responsible AI\n\nGitHub is committed to responsible AI development and provides transparency documentation for each Copilot feature.\n\nEach Copilot feature has a dedicated **responsible use** article describing its purpose, capabilities, and limitations. See Responsible use of GitHub Copilot features.",
      "content_chars": 6256,
      "published_date": null
    },
    {
      "rank": 5,
      "url": "https://docs.github.com/en/site-policy/github-terms/github-dpa-previews",
      "title": "GitHub DPA-Covered Previews - GitHub Docs",
      "content": "# GitHub DPA-Covered Previews\n\n## GitHub DPA-Covered Previews\n\nThe pre-release products and features listed below use data handling that is the same as when the software becomes generally available. Under GitHub\u2019s Pre-Release License Terms, this software is governed by the GitHub Data Protection Agreement as of the date listed, and the Customer is the Data Controller beginning on that date (the \"DPA Coverage Date\"). The software is no longer considered a Preview on the date it becomes generally available (the \"GA Date\").\n\n| Product / Feature | DPA Coverage Date | GA Date |\n| --- | --- | --- |\n| Copilot CLI | 27 October 2025 | 25 February 2026 |\n| Copilot Enterprise & Users Usage Metrics Dashboard | 27 October 2025 | 27 February 2026 |\n| Spark | 27 October 2025 | [TBD] |",
      "content_chars": 780,
      "published_date": "2025-10-27T00:00:00.000Z"
    },
    {
      "rank": 6,
      "url": "https://docs.github.com/en/copilot",
      "title": "GitHub Copilot documentation - GitHub Docs",
      "content": "# GitHub Copilot documentation\n\nYou can use GitHub Copilot to enhance your productivity and assist as you work on code.\n\n## Links\n\n### Getting started\n\n- What is GitHub Copilot? Learn what Copilot is and what you can do with it.\n- Quickstart for GitHub Copilot Quickly learn how to use GitHub Copilot.\n\n## Articles\n\n- Quickstart for GitHub Copilot Quickly learn how to use GitHub Copilot.\n- Getting started with GitHub Copilot CLI Quickly learn how to use GitHub Copilot CLI.\n- Getting started with the GitHub Copilot app Sign in to the GitHub Copilot app, connect a repository or local folder, and create your first agent session to make code changes.\n- What is GitHub Copilot? Learn what Copilot is and what you can do with it.\n- Plans for GitHub Copilot Discover the plans available for Copilot.\n- GitHub Copilot features GitHub Copilot offers a suite of features for users and administrators.\n- Best practices for using GitHub Copilot Learn how to get the most out of Copilot.\n- Adopting GitHub Copilot in your enterprise Adopt the latest GitHub Copilot features without compromising on control and governance.\n- GitHub Copilot code suggestions in your IDE Learn about Copilot code suggestions in different IDEs.\n- GitHub Copilot code referencing GitHub Copilot checks suggestions for matches with publicly available code. Any matches are discarded or suggested with a code reference.\n- About GitHub Copilot Chat Learn how you can use GitHub Copilot Chat to enhance your coding experience.\n- About GitHub Copilot cloud agent Copilot can research a repository, create an implementation plan, and make code changes on a branch. You can review the diff, iterate, and create a pull request when you're ready.\n- About agent management Use one centralized control page to jump between agent sessions, check progress, and stay in control without losing your place.\n- About custom agents Custom agents enhance Copilot with assistance tailored to your needs.\n- About Copilot automations Automations let you run Copilot cloud agent automatically, on a schedule or in response to events in a repository.\n- About rationale, confidence, and approvals for issues When automations triage issues, it explains each change, rates its confidence, and holds lower-confidence changes for your review.\n- Managing access to GitHub Copilot cloud agent Find out about Copilot cloud agent policies available for GitHub Copilot Enterprise and GitHub Copilot Business, and about disabling the agent for specific repositories.\n- Model Context Protocol (MCP) and GitHub Copilot cloud agent Find out about using the Model Context Protocol (MCP) with Copilot cloud agent.\n- Risks and mitigations for GitHub Copilot cloud agent How do Copilot cloud agent's built-in security protections mitigate known risks?\n- About GitHub Copilot CLI Find out about using Copilot from the command line.\n- Comparing GitHub Copilot CLI customization features Find out about the various ways you can customize Copilot: what they do, and when to use them.\n- Canceling a GitHub Copilot CLI operation and rolling back changes Find out about the different ways to cancel an active Copilot operation, and how to roll back changes made during a session if the result isn't what you expected.\n- Managing context in GitHub Copilot CLI Understand how Copilot manages conversation context, what happens during long sessions, and how to stay in control of your context window.\n- About remote control of GitHub Copilot CLI sessions Remote control lets you monitor and steer a Copilot CLI session from GitHub.com or GitHub Mobile, even after you've stepped away from your machine.\n- About custom agents Custom agents enhance Copilot with assistance tailored to your needs.\n- Allowing GitHub Copilot CLI to work autonomously The CLI's autopilot mode lets Copilot CLI work autonomously on a task, carrying out multiple steps until the task is complete.\n- Running tasks in parallel with the `/fleet` command The `/fleet` slash command lets Copilot CLI break down a complex request into smaller tasks and run them in parallel, maximizing efficiency and throughput.\n- Researching with GitHub Copilot CLI The `/research` slash command turns Copilot into your research assistant, gathering in-depth information and insights on a topic.\n- About GitHub Copilot CLI session data Your Copilot CLI sessions build a searchable history of everything you have worked on. Query past sessions with natural language, generate standup reports, get personalized tips, and resume previous work.\n- About the rubber duck agent The rubber duck agent is a built-in critic that gives Copilot a constructive second opinion on its own plans, code, and tests\u2014using a different AI model from the one driving your session.\n- Using LSP servers with GitHub Copilot CLI LSP servers give Copilot CLI precise code intelligence, enabling it to navigate definitions, find references, and rename symbols accurately across your project.\n- About extensions for GitHub Copilot CLI Extensions let you add your own tools and slash commands to GitHub Copilot CLI, using only the SDK that ships with the CLI.\n- Loading tools on demand with tool search Tool search keeps your context small by letting Copilot CLI load external tools only when a task needs them.\n- Understanding filesystem policies for local sandboxing in GitHub Copilot CLI When local sandboxing is enabled, Copilot CLI runs each sandboxed process or operation under a filesystem policy that controls which files and directories it can read and write. Learn how that policy is built and how to check the access it grants.\n- About the GitHub Copilot app The GitHub Copilot app is a desktop application for agent-driven development that brings parallel workstreams, GitHub integration, and PR lifecycle management into one place.\n- Using GitHub Copilot in JetBrains IDEs Learn about the different ways to use GitHub Copilot in JetBrains IDEs, including the GitHub Copilot plugin, JetBrains AI Assistant, and Copilot CLI.\n- About GitHub Copilot code review Copilot reviews your pull requests, identifies issues, and suggests fixes you can apply in a couple of clicks.\n- About GitHub Agentic Workflows Automate repetitive repository work with natural language instructions executed by AI coding agents in GitHub Actions.\n- About GitHub Copilot Memory Copilot Memory helps Copilot become more effective over time by remembering facts about your repositories and your personal coding preferences.\n- About hooks for GitHub Copilot Extend and customize GitHub Copilot agent behavior by executing custom shell commands at key points during agent execution.\n- About GitHub Copilot plugins Plugins are installable packages that extend Copilot with reusable agents, skills, hooks, and integrations.\n- About enterprise-managed plugin standards Enterprise administrators can centrally define plugin policies for users, ensuring consistent plugin availability.\n- About third-party coding agents You can use third-party coding agents alongside Copilot cloud agent to work asynchronously on your development tasks on GitHub.\n- About agent apps Agent apps let you use partner-built agents directly in your workflows on GitHub, powered by your Copilot subscription.\n- OpenAI Codex Use the OpenAI Codex coding agent and Visual Studio Code extension powered by Copilot.\n- Anthropic Claude Use the Anthropic Claude coding agent powered by Copilot.\n- About agent skills Skills allow Copilot to perform specialized tasks.\n- Agent management for enterprises Maintain your enterprise's security and compliance standards and supercharge your developers by managing agents with AI Controls.\n- OpenTelemetry for agent monitoring Understand how Copilot agents perform and interact with models and tools.\n- About cloud and local sandboxes for GitHub Copilot Cloud and local sandboxes provide isolated execution environments that let Copilot safely interact with code, tools, filesystem, and network resources securely on your local machine or in fully isolated cloud environments.\n- GitHub Copilot usage metrics Copilot usage metrics provide visibility into how Copilot is adopted and used across your organization, including engagement, activity, code generation, and pull request lifecycle trends.\n- Prompt engineering for GitHub Copilot Chat Follow these strategies to improve your Copilot results.\n- About customizing GitHub Copilot responses Learn about customizing the behavior of GitHub Copilot to fit with your preferences and requirements.\n- About Model Context Protocol (MCP) Model Context Protocol (MCP) is a protocol that allows you to extend the capabilities of GitHub Copilot by integrating it with other systems.\n- About GitHub Copilot Spaces Understand how organizing and sharing context with Copilot Spaces can improve your Copilot Chat in GitHub results and help your collaborators.\n- Indexing repositories for GitHub Copilot Copilot improves responses by indexing your repositories.\n- Content exclusion for GitHub Copilot You can prevent Copilot from accessing certain files.\n- Choosing the right AI tool for your task Understand GitHub's AI tools and how they can be used to help develop software.\n- About Copilot integrations Integrate Copilot with other tools and platforms to streamline your workflow.\n- About default availability of Copilot models A policy controls whether unconfigured models default to enabled or disabled.\n- Bring your own key for GitHub Copilot Use your existing LLM provider with GitHub Copilot to save costs or consolidate billing.\n- Utility models Utility models power background Copilot features.\n- About Copilot auto model selection Automatically select the best model for each task.\n- FedRAMP-compliant models for GitHub Copilot Restrict users to models with FedRAMP Moderate certification.\n- Base and long-term support (LTS) models Learn about base models, long-term support (LTS) models, and how they affect model availability for enterprises using GitHub Copilot.\n- Usage limits for GitHub Copilot Learn about GitHub Copilot usage limits and what to do if you hit a limit.\n- Usage-based billing for individuals Your Copilot plan includes a monthly allowance of GitHub AI Credits. If you exhaust your AI credits, you can pay extra to keep working.\n- Usage-based billing for organizations and enterprises Under usage-based billing, Copilot usage in organizations and enterprises is measured in AI credits.\n- Budgets for usage-based billing Under usage-based billing, budget controls at the user, organization, cost center, and enterprise levels determine how Copilot usage is served, metered, or blocked.\n- About billing for GitHub Copilot in organizations and enterprises Learn about pricing and billing cycles for Copilot.\n- About enterprise accounts for Copilot Business An enterprise account lets you manage only Copilot Business licenses, without consuming GitHub Enterprise Cloud licenses.\n- GitHub Copilot policies for enterprises and organizations Control the availability of GitHub Copilot features and models for your users.\n- MCP server usage in your company You can manage MCP server usage to provide your developers with valuable tools while maintaining security and compliance.\n- Network settings for GitHub Copilot You can connect to GitHub Copilot through an HTTP proxy and use custom certificates.\n- Learning about new features and models Stay informed about GitHub Copilot features and models, and make confident decisions about enabling them for your enterprise.\n- Setting up GitHub Copilot for yourself Start using GitHub Copilot to write code faster on GitHub.\n- Setting up GitHub Copilot for your organization Enable GitHub Copilot for your organization so members can write code faster.\n- Setting up GitHub Copilot for your enterprise Enable GitHub Copilot across your enterprise so developers can write code faster.\n- Setting up an enterprise for GitHub Copilot Business only Use an enterprise account to manage Copilot Business licenses without consuming GitHub Enterprise Cloud licenses.\n- Access GitHub Copilot for free as a student Get free access to Copilot's premium features as a verified student.\n- Access Copilot Pro for free as a teacher or open source maintainer Get free access to Copilot Pro as a verified teacher or open-source maintainer.\n- Configuring access to AI models in GitHub Copilot Control which AI models your organization or enterprise can use with Copilot.\n- Configuring code review by GitHub Copilot Set up Copilot to review pull requests.\n- Configuring runners for GitHub Copilot code review Use self-hosted runners or larger GitHub-hosted runners for Copilot code review.\n- Getting started with prompts for Copilot Chat on GitHub Explore example prompts to ask Copilot Chat about code, repositories, pull requests, and more.\n- Asking GitHub Copilot questions in GitHub Get instant answers about your code, repositories, and development questions \u2014 right from GitHub.\n- Asking GitHub Copilot questions in GitHub Mobile Ask coding questions, explore repositories, and get help with pull requests in GitHub Mobile.\n- Customize Copilot for your project Set up custom instructions, create a specialized agent, and organize project context on GitHub.\n- Adding personal custom instructions for GitHub Copilot Customize GitHub Copilot Chat responses to match your personal preferences.\n- Adding repository custom instructions for GitHub Copilot Create repository custom instructions files that give Copilot additional context on how to understand your project and how to build, test and validate its changes.\n- Adding organization custom instructions for GitHub Copilot Customize Copilot responses for members of your organization.\n- Creating custom agents for Copilot cloud agent You can create specialized agents with tailored expertise for specific development tasks.\n- Adding agent skills for GitHub Copilot You can modify Copilot's behavior and abilities when it works on particular tasks.\n- Customize agent workflows with hooks Run automated checks\u2014like linting, formatting, or security scans\u2014at key points during agent execution to enforce quality standards.\n- Configure the development environment Pre-install tools and dependencies so Copilot cloud agent can build, test, and validate changes reliably.\n- Configure secrets and variables for Copilot cloud agent Securely pass secrets and variables to Copilot cloud agent so it can access private resources and configure MCP servers.\n- Testing and releasing custom agents in your organization or enterprise Ensure your custom agents are performant and compliant before releasing them to your company.\n- Customizing or disabling the firewall for GitHub Copilot Learn how to control the domains and URLs that Copilot cloud agent and Copilot code review can access.\n- Configure MCP servers for your repository Configure Model Context Protocol (MCP) servers for your repository to give Copilot cloud agent and Copilot code review access to external tools and data sources.\n- Creating GitHub Copilot Spaces Create spaces to organize and centralize relevant content that grounds Copilot's responses in the right context for a specific task.\n- Collaborating with others using GitHub Copilot Spaces Share Copilot Spaces to support collaboration and knowledge sharing.\n- Using GitHub Copilot to create or update issues Use Copilot to quickly generate structured, high-quality issues from natural language or images, without filling out every field manually.\n- Creating a pull request summary with GitHub Copilot Generate an AI-powered summary of your pull request changes to help reviewers quickly understand what you changed and why.\n- Using the GitHub MCP Server from Copilot Chat Perform GitHub tasks\u2014like creating branches, merging pull requests, and searching for users\u2014directly from Copilot Chat in GitHub, with no setup required.\n- Get started with Copilot agents on GitHub Try Copilot cloud agent end-to-end in about ten minutes.\n- Kick off a task with Copilot agents on GitHub Decide whether Copilot cloud agent creates a pull request immediately or works on a branch you review and iterate on first.\n- Research, plan, and iterate on code changes with Copilot cloud agent Perform deep research on a repository, create an implementation plan, and make iterative code changes on a branch, then create a pull request when you're ready.\n- Managing agent sessions Monitor an agent's progress in real time, steer it with follow-up prompts, and stop or archive sessions.\n- Using GitHub Copilot code review on GitHub GitHub Copilot reviews your pull requests and suggests ready-to-apply changes, so you get fast, actionable feedback on every commit.\n- Review output from Copilot Copilot pull requests deserve the same thorough review as any contribution.\n- Setting up GitHub Copilot for yourself Follow these steps to start using Copilot.\n- Installing the GitHub Copilot extension in your environment To use Copilot in your preferred coding environment, follow the steps for your chosen IDE.\n- Getting code suggestions in your IDE with GitHub Copilot Use GitHub Copilot to get code suggestions in your editor.\n- Finding public code that matches GitHub Copilot suggestions Learn how to view code references when GitHub Copilot makes suggestions that matches publicly available code.\n- Getting started with prompts for GitHub Copilot Chat in your IDE Get an overview of ways to use Copilot Chat in your IDE.\n- Asking GitHub Copilot questions in your IDE Use Copilot Chat in your editor to give you code suggestions, explain code, generate unit tests, and suggest code fixes.\n- Asking GitHub Copilot questions in Windows Terminal You can use Copilot in Windows Terminal to get suggestions and explanations for the command line.\n- Best practices for GitHub Copilot CLI Learn how to get the most out of GitHub Copilot CLI.\n- Installing GitHub Copilot CLI Learn how to install Copilot CLI so that you can use Copilot directly from the command line.\n- Configuring GitHub Copilot CLI Configure trusted directories, tool access, and path and URL permissions for Copilot CLI\n- Adding LSP servers for GitHub Copilot CLI You can add LSP servers to give Copilot CLI precise code intelligence, improving its ability to navigate definitions, find references, and rename symbols.\n- Using GitHub Copilot CLI Learn how to use GitHub Copilot from the command line.\n- Allowing and denying tool use Control which tools Copilot CLI can use to avoid unintended changes.\n- Use voice input with Copilot CLI Speak your prompts to GitHub Copilot CLI instead of typing them, using the CLI's speech-to-text feature.\n- Connecting GitHub Copilot CLI to VS Code Connect Copilot CLI to VS Code to share context, trust settings, and output.\n- Browsing issues, pull requests, and gists from GitHub Copilot CLI Use the tabs in an interactive Copilot CLI session to browse issues, pull requests and gists, without leaving the terminal.\n- Rolling back changes made during a GitHub Copilot CLI session Rewind your Copilot CLI session to a previous prompt to undo changes in conversation history, and optionally restore files.\n- Working with multiple GitHub Copilot CLI sessions Run several Copilot CLI sessions at once and use the sidebar to quickly move between them.\n- Steering a GitHub Copilot CLI session from another device Enable remote control for a Copilot CLI session so you can monitor progress, respond to prompts, and continue working from GitHub.com or GitHub Mobile.\n- Managing pull requests with the /pr command Use the `/pr` slash command to view, create, and fix pull requests directly from Copilot CLI.\n- Speeding up task completion with the `/fleet` command Learn how you can speed up the completion of a multi-step implementation plan by using the `/fleet` slash command.\n- Using GitHub Copilot CLI session data Resume previous Copilot CLI sessions, use the `/chronicle` slash command to get insights from your session history, and ask Copilot questions about your CLI usage.\n- Quickstart for automating with GitHub Copilot CLI Build an automation with Copilot CLI in minutes.\n- Running GitHub Copilot CLI programmatically Use Copilot CLI in the terminal, in scripts, or in Actions workflows.\n- Scheduling prompts in GitHub Copilot CLI Use the `/every` and `/after` slash commands to submit a prompt to Copilot on a recurring schedule, or after a specified delay.\n- Automating tasks with Copilot CLI and GitHub Actions Integrate GitHub Copilot CLI into your GitHub Actions workflows.\n- Overview of customizing GitHub Copilot CLI Copilot CLI works best when customized for your specific project and workflow.\n- Adding custom instructions for GitHub Copilot CLI Give Copilot additional context on how to understand your project and how to build, test and validate its changes.\n- Changing settings with the `/settings` command View and change your personal settings for GitHub Copilot CLI with the `/settings` slash command.\n- Using hooks with GitHub Copilot CLI Extend GitHub Copilot agent behavior with custom shell commands at key points during agent execution.\n- Adding agent skills for GitHub Copilot CLI Modify Copilot's behavior and abilities when it works on particular tasks.\n- Adding MCP servers for GitHub Copilot CLI Extend Copilot's capabilities by connecting Model Context Protocol (MCP) servers to provide additional tools and context.\n- Creating and using custom agents for GitHub Copilot CLI Create specialized agents with tailored expertise for specific development tasks.\n- Using your own LLM models in GitHub Copilot CLI Use a model from an external provider of your choice in Copilot by supplying your own API key.\n- Finding and installing plugins for GitHub Copilot CLI Extend Copilot's functionality by installing plugins created by the community or by your team.\n- Creating a plugin for GitHub Copilot CLI Create a plugin to share customizations in an easy-to-install package.\n- Creating a plugin marketplace for GitHub Copilot CLI You can make CLI plugins that you've created easy to install by adding them to a marketplace.\n- Administering Copilot CLI for your enterprise Control the use of Copilot CLI within your enterprise.\n- Using Copilot CLI in GitHub Actions with GITHUB_TOKEN Run Copilot CLI in a GitHub Actions workflow using the built-in `GITHUB_TOKEN`, without a personal access token.\n- Using local sandboxing Enable local sandboxing so that Copilot CLI runs the commands and tools it invokes on your behalf inside an operating-system sandbox.\n- Configuring local sandbox settings Use the `/sandbox` slash command in Copilot CLI to control how the local sandbox restricts filesystem access, network connectivity, and system capabilities.\n- Customizing the GitHub Copilot app Customize the GitHub Copilot app so it works the way you and your team do.\n- Working with agent sessions in the GitHub Copilot app Run multiple isolated agent sessions simultaneously, each with its own branch, and steer them using different session modes, models, and tools.\n- Working with canvas extensions in the GitHub Copilot app Use canvases in the GitHub Copilot app to build shared, agent-driven artifacts and interfaces for human-agent collaboration.\n- Managing issues and pull requests with the GitHub Copilot app Pick up an issue, direct an agent to implement changes, and land a pull request\u2014all without leaving the GitHub Copilot app.\n- Using automations in the GitHub Copilot app Automate recurring agent tasks so they run on a schedule or on demand, without manual intervention.\n- Using your own LLM models in the GitHub Copilot app Connect a model from an external provider of your choice by supplying your own API key, then use the model in agent sessions.\n- Using deep links to open the GitHub Copilot app Use deep links to launch the GitHub Copilot app from the terminal, tickets, and internal tools, so people can jump directly into the right repository, pull request, automation, or session.\n- Build your first Copilot-powered app In this tutorial, you'll use the Copilot SDK to build a command-line assistant. You'll start with the basics, add streaming responses, then add custom tools - giving Copilot the ability to call your code.\n- Authentication The GitHub Copilot SDK supports multiple authentication methods to fit different use cases. Choose the method that best matches your deployment scenario.\n- BYOK (bring your own key) BYOK allows you to use the Copilot SDK with your own API keys from model providers, bypassing GitHub Copilot authentication. This is useful for enterprise deployments, custom model hosting, or when you want direct billing with your model provider.\n- Server-to-server authentication Use a short-lived installation access token when a service needs to make Copilot requests on behalf of an organization without a user's credentials. In GitHub Actions, use the built-in `GITHUB_TOKEN` instead.\n- The agent loop How the Copilot CLI processes a user message end-to-end: from prompt to `session.idle`.\n- Citations Citations link spans of an assistant response back to the sources that support them. Turn on `enableCitations` when you create or resume a session, then read the `citations` payload on `assistant.message` events to render footnotes, source lists, or inline links.\n- Cloud sessions Cloud sessions run Copilot work on GitHub-hosted compute and appear in the agents panel on GitHub. Use them when your app should create a session that executes remotely instead of starting a local GitHub Copilot CLI session on the user's machine or your server.\n- Context clearing and terminal tools Use `session.history.clearContext` when a host needs to replace the current conversation context without replacing the session. Typical uses include handoffs and host-managed context lifecycle policies.\n- Custom agents and sub-agent orchestration Define specialized agents with scoped tools and prompts, then let Copilot orchestrate them as sub-agents within a single session. For dispatching multiple sub-agents in parallel, see Fleet mode.\n- Fleet mode Fleet mode is Copilot's parallel orchestration pattern for work that can be split across independent sub-agents. In the runtime research notes, fleet mode is described as \"the runtime's built-in pattern for dispatching multiple sub-agents in parallel via the `task` tool, with SQL todos as the shared coordination state.\" Use it when one parent session should coordinate several workers, collect their results, and continue the conversation with the combined context.\n- Working with hooks Hooks let you plug custom logic into every stage of a Copilot session\u2014from the moment it starts, through each user prompt and tool call, to the moment it ends. This guide walks through practical use cases so you can ship permissions, auditing, notifications, and more without modifying the core agent behavior.\n- Image input Send images to Copilot sessions as attachments. There are two ways to attach images:\n- Using MCP servers with the GitHub Copilot SDK The Copilot SDK can integrate with MCP servers (Model Context Protocol) to extend the assistant's capabilities with external tools. MCP servers run as separate processes and expose tools (functions) that Copilot can invoke during conversations.\n- Plugin directories A plugin is a directory that bundles SDK extensions \u2014 skills, hooks, MCP servers, custom agents, and LSP configuration \u2014 behind a single manifest. Pointing the SDK at a plugin directory loads everything the plugin contributes, so you can ship reusable capability packs without writing per-extension wiring in every host application.\n- Remote sessions Remote sessions sync to GitHub so users can access locally running Copilot sessions from the agents panel or on mobile. When enabled, the SDK produces a URL to the session log that can be shared as a link or QR code.\n- Session limits Session limits let an application set an AI Credits budget for a Copilot session. Use `sessionLimits` when creating or resuming a session to set a soft cap for the current accounting window.\n- Session resume and persistence This guide walks you through the SDK's session persistence capabilities\u2014how to pause work, resume it later, and manage sessions in production environments.\n- Custom skills Skills are reusable prompt modules that extend Copilot's capabilities. Load skills from directories to give Copilot specialized abilities for specific domains or workflows.\n- Steering and queueing Two interaction patterns let users send messages while the agent is already working: steering redirects the agent mid-turn, and queueing buffers messages for sequential processing after the current turn completes.\n- Streaming session events Every action the Copilot agent takes\u2014thinking, writing code, running tools\u2014is emitted as a session event you can subscribe to. This guide is a field-level reference for each event type so you know exactly what data to expect without reading the SDK source.\n- Usage and billing metrics This guide shows how to read token counts, context-window utilization, AI credit cost, and account quota from a Copilot SDK application. Examples are shown for TypeScript, Python, Go, .NET, Java, and Rust.\n- Error handling hook The `onErrorOccurred` hook is called when errors occur during session execution. Use it to:\n- Session hooks Hooks allow you to intercept and customize the behavior of Copilot sessions at key points in the conversation lifecycle. Use hooks to:\n- Post-tool use hook The `onPostToolUse` hook is called after a tool executes successfully. Use it to:\n- Pre-tool use hook The `onPreToolUse` hook is called before a tool executes. Use it to:\n- Session lifecycle hooks Session lifecycle hooks let you respond to session start and end events. Use them to:\n- User prompt submitted hook The `onUserPromptSubmitted` hook is called when a user submits a message. Use it to:\n- User prompt transformed hook The `userPromptTransformed` hook runs after the runtime adds generated context to a submitted prompt, but before the resulting content is persisted to session history or sent to the model.\n- Microsoft agent framework integration Use the Copilot SDK as an agent provider inside the Microsoft Agent Framework (MAF) to compose multi-agent workflows alongside Azure OpenAI, Anthropic, and other providers.\n- OpenTelemetry instrumentation for Copilot SDK This guide shows how to add OpenTelemetry tracing to your Copilot SDK applications.\n- Azure managed identity with BYOK The GitHub Copilot SDK's BYOK (bring your own key) supports static API keys, but Azure deployments often use Managed Identity (Microsoft Entra ID) instead of long-lived keys. The GitHub Copilot SDK is designed to compose with the Azure Identity SDK for maximum flexibility. Supply a bearer token provider callback that can fetch fresh tokens on demand using an Azure Identity SDK API.\n- Backend services setup Run the Copilot SDK in server-side applications\u2014APIs, web backends, microservices, and background workers. The CLI runs as a headless server that your backend code connects to over the network.\n- Default setup (bundled CLI) The Node.js and .NET SDKs include the Copilot CLI as a dependency\u2014your app ships with everything it needs, with no extra installation or configuration required.\n- Setup guides These guides walk you through configuring the Copilot SDK for your specific use case\u2014from personal side projects to production platforms serving thousands of users.\n- GitHub OAuth setup Let users authenticate with their GitHub accounts to use Copilot through your application. This supports individual accounts, organization memberships, and enterprise identities.\n- Local CLI setup Use a specific CLI binary instead of the SDK's automatic CLI management. This is an advanced option\u2014you supply the CLI path explicitly, and you are responsible for ensuring version compatibility with the SDK.\n- Multi-tenancy and server deployments Multi-user server mode means running the Copilot SDK from backend code that serves more than one human, tenant, workspace, or integration account. In this setup, the application owns request routing and authorization, while the SDK and runtime provide per-session state, per-session authentication, and explicit tool registration so one user's session does not inherit another user's tools or identity.\n- Scaling and multi-tenancy Design your Copilot SDK deployment to serve multiple users, handle concurrent sessions, and scale horizontally across infrastructure. This guide covers session isolation patterns, scaling topologies, and production best practices.\n- SDK and CLI compatibility This document outlines which Copilot CLI features are available through the SDK and which are CLI-only.\n- Debugging guide This guide covers common issues and debugging techniques for the Copilot SDK across all supported languages.\n- MCP server debugging guide This guide covers debugging techniques specific to MCP (Model Context Protocol) servers when using the Copilot SDK.\n- Starting GitHub Copilot sessions Choose your preferred way to start Copilot cloud agent sessions.\n- Creating automations with Copilot cloud agent Create and manage automations to run Copilot cloud agent on a schedule or in response to events.\n- Managing rationale, confidence, and approvals for issues Set up and manage rationale, confidence, and approvals for issues handled by automation.\n- Changing the AI model for GitHub Copilot cloud agent In supported entrypoints, when starting a task with Copilot cloud agent, you can select the model used, and, for supported models, the reasoning level.\n- Configuring settings for GitHub Copilot cloud agent Learn how to configure settings for Copilot cloud agent\n- Creating custom agents for Copilot cloud agent in your IDE You can create specialized agents with tailored expertise for specific development tasks.\n- Using Copilot cloud agent on GitHub Start Copilot cloud agent sessions directly on GitHub, then iterate on the results without leaving your browser.\n- Using Copilot cloud agent on GitHub Mobile Start and track Copilot cloud agent sessions from the GitHub Mobile app.\n- Using agent apps Start a partner-built agent from an issue, a pull request comment, or the Agents UI on GitHub.\n- Using Copilot cloud agent in your IDE Start and track Copilot cloud agent sessions from Visual Studio Code, JetBrains IDEs, Eclipse, and Visual Studio.\n- Using Copilot cloud agent via the API You can start and manage Copilot cloud agent tasks programmatically using the REST API.\n- Using Copilot cloud agent from the GitHub CLI Start and track Copilot cloud agent sessions from the GitHub CLI.\n- Using Copilot cloud agent via the GitHub MCP Server Start Copilot cloud agent sessions from any IDE or agentic tool that supports Model Context Protocol (MCP).\n- Using Copilot cloud agent from Raycast Start and track Copilot cloud agent sessions from the Raycast launcher.\n- Troubleshooting GitHub Copilot cloud agent Learn how to resolve problems that may occur when you assign tasks to Copilot.\n- Using GitHub Copilot code review Learn how to request a code review from GitHub Copilot.\n- Managing Copilot Memory for your personal account Review and manage the coding conventions, preferences, and other details that Copilot has stored from your interactions.\n- Managing Copilot Memory for an organization or enterprise Manage Copilot Memory settings and stored memories for an organization or enterprise.\n- Integrating Copilot cloud agent with Slack Provide context to the Copilot cloud agent and open pull requests, all from within your Slack workspace.\n- Integrating Copilot cloud agent with Teams You can use the GitHub integration in Teams to provide context and open pull requests all from within your Teams channels.\n- Integrating Copilot cloud agent with Jira You can use the GitHub integration in Jira to provide context and open pull requests, all from within your Jira workspace.\n- Integrating Copilot cloud agent with Linear Use the Copilot integration in Linear to provide context, customize how the agent runs, and open pull requests, all from within your Linear workspace.\n- Integrating Copilot cloud agent with Azure Boards Use the Copilot integration in Azure Boards to send work items directly to Copilot cloud agent and generate pull requests, all from within your Azure DevOps workspace.\n- Changing the AI model for GitHub Copilot Chat Learn how to switch between models for Copilot Chat.\n- Changing the AI model for GitHub Copilot inline suggestions Learn how to change the default LLM for Copilot inline suggestions to a different model.\n- Using GitHub Copilot Spaces Use spaces to ground Copilot's responses in the right context for a specific task.\n- Extending GitHub Copilot Chat with Model Context Protocol (MCP) servers Connect MCP servers to Copilot Chat to share context from other applications.\n- Setting up the GitHub MCP Server Learn how to configure the GitHub Model Context Protocol (MCP) server.\n- Configuring the GitHub MCP Server for GitHub Enterprise Learn how to configure the GitHub Model Context Protocol (MCP) server to work with GitHub Enterprise Server or GitHub Enterprise Cloud with data residency.\n- Configuring toolsets for the GitHub MCP Server Learn how to configure toolsets and tools for the GitHub MCP server for fine-grained control and optimized performance.\n- Using the GitHub MCP Server in your IDE Learn how to use the GitHub Model Context Protocol (MCP) server to interact with repositories, issues, pull requests, and other GitHub features, directly from Copilot Chat in your IDE.\n- Changing your MCP registry in your IDE Customize the MCP registry you can use with Copilot Chat.\n- Adding repository custom instructions for GitHub Copilot in your IDE Create repository custom instructions files that give Copilot additional context on how to understand your project and how to build, test and validate its changes.\n- Excluding content from GitHub Copilot Learn how to prevent Copilot from accessing certain content.\n- Reviewing changes to content exclusions for GitHub Copilot You can monitor changes to content exclusions in your repositories and organizations.\n- Using the GitHub CLI Copilot extension This article provides details about the replacement for the Copilot extension for GitHub CLI.\n- Configuring network settings for GitHub Copilot You can connect to GitHub Copilot through an HTTP proxy and use custom certificates.\n- Configuring GitHub Copilot in your environment You can enable, configure, or disable GitHub Copilot in a supported IDE.\n- Using GitHub Copilot with an account on GHE.com Update your development environment to access a Copilot plan for an account on GHE.com.\n- Monitoring your GitHub AI Credits usage Learn how to monitor the AI credits you consume when using Copilot.\n- Managing your company's spending on GitHub Copilot Learn how to track spending, view usage, and optimize license distribution.\n- Getting started with a GitHub Copilot plan You can use Copilot for free, or choose a paid plan to unlock additional features, models, and limits.\n- Viewing and changing your GitHub Copilot plan Learn how to view, cancel, or update your Copilot plan.\n- Disabling GitHub Copilot Free Learn how to disable Copilot Free in your IDE or GitHub.com.\n- Managing GitHub Copilot policies as an individual subscriber Find out how to change your personal settings on GitHub to configure GitHub Copilot's behavior.\n- Canceling GitHub Copilot for your organization Removing all assigned GitHub Copilot seats in your organization will cancel your organization's Copilot plan.\n- Granting access to GitHub Copilot for members of your organization Grant access to GitHub Copilot for some or all of the members of your organization.\n- Managing requests for GitHub Copilot Business in your organization Approve or deny requests for Copilot access in your organization.\n- Revoking access to GitHub Copilot for members of your organization Remove access to GitHub Copilot for some or all of the members of your organization.\n- Managing GitHub Copilot access to your organization's network Learn how to use subscription-based network routing to control Copilot access to your network.\n- Managing policies and features for GitHub Copilot in your organization Control the availability of GitHub Copilot features and models for users granted a license by your organization.\n- Adding GitHub Copilot cloud agent to your organization Enable Copilot cloud agent for your members and control the repositories where it is available.\n- Configuring runners for GitHub Copilot cloud agent in your organization Configure the GitHub Actions runners used by Copilot cloud agent and control whether repositories can customize the runner type.\n- Preparing to use custom agents in your organization Configure the repository that stores custom agents for your organization.\n- Managing the availability of models in an organization Configure which default Copilot models are available to members of your organization.\n- Reviewing user activity data for GitHub Copilot in your organization Review GitHub Copilot usage in your organization to make informed decisions about seat assignment.\n- Enabling custom models for GitHub Copilot in your organization Integrate your preferred custom models with GitHub Copilot by using your own LLM API keys, and make them available to your organization members.\n- Subscribing to GitHub Copilot for your enterprise Enterprise owners can set up a Copilot Enterprise or Copilot Business plan for their enterprise.\n- Canceling GitHub Copilot for your enterprise Disabling GitHub Copilot for all organizations in your enterprise will cancel your enterprise's Copilot plan.\n- Upgrading GitHub Copilot for your enterprise Change your organizations' plans from Copilot Business to Copilot Enterprise.\n- Downgrading GitHub Copilot for your enterprise You can downgrade organizations in your enterprise from Copilot Enterprise to Copilot Business.\n- Granting users access to GitHub Copilot in your enterprise Enable Copilot for entire organizations or grant access directly to specific users.\n- Disabling Copilot for organizations in your enterprise Disable GitHub Copilot for some or all of the organizations in your enterprise.\n- Viewing Copilot license usage in your enterprise View how many users have access to GitHub Copilot across your enterprise.\n- Managing GitHub Copilot access to your enterprise's network Learn how to use subscription-based network routing to control Copilot access to your network.\n- Managing policies and features for GitHub Copilot in your enterprise Control the availability of features for GitHub Copilot in your enterprise using policies.\n- Preparing to use custom agents in your enterprise Set up your enterprise for custom agents by configuring their source organization and repository, availability, and management permissions.\n- Creating a `.github-private` repository A `.github-private` repository can serve as a designated source of governance settings for agents and plugins across your enterprise.\n- Configuring enterprise-managed settings Configure enterprise managed settings to centrally control Copilot client behavior across your enterprise using server-managed, MDM-managed, or file-based deployment.\n- Monitoring agentic activity in your enterprise Track agentic activity in your enterprise to ensure continued compliance.\n- Enabling GitHub Copilot cloud agent in your enterprise Choose which organizations can use Copilot cloud agent and connect it to MCP servers.\n- Blocking agentic features in your enterprise Disable features for all users and repositories.\n- Enabling GitHub Copilot code review in your enterprise Apply consistent standards by having Copilot review every pull request.\n- Managing availability of models in your enterprise Control which Copilot models are available to users.\n- Enabling custom models for GitHub Copilot in your enterprise Integrate your preferred custom models with GitHub Copilot by using your own LLM API keys, and make them available for organizations in your enterprise account.\n- Reviewing audit logs for GitHub Copilot Check for changes to settings or licenses in your Copilot plan.\n- Configuring an MCP server allowlist for your enterprise Define which MCP servers your users can and cannot use without the need for a private registry.\n- Configure an MCP registry for your organization or enterprise Create and host a list of MCP servers that your developers can access.\n- Restrict MCP server access to a custom registry You can configure an MCP registry URL and access control policy to determine which MCP servers developers can discover and use in supported IDEs and Copilot CLI.\n- Downloading a GitHub Copilot activity report for your organization or enterprise Monitor Copilot license usage with a detailed report.\n- Viewing the Copilot usage metrics dashboard Monitor adoption trends and use of Copilot to support long-term enablement.\n- Viewing the code generation dashboard The code generation dashboard shows how Copilot generates code across your enterprise, including activity from both users and agents.\n- Viewing the Copilot impact dashboard The impact dashboard shows how deeply your organization has adopted Copilot, and how that adoption connects to pull request output.\n- Troubleshooting common issues with GitHub Copilot This guide describes the most common issues with GitHub Copilot and how to resolve them.\n- Viewing logs for GitHub Copilot in your environment View logs to troubleshoot GitHub Copilot-related errors in your IDE.\n- Troubleshooting firewall settings for GitHub Copilot Troubleshooting help for firewall-related errors.\n- Troubleshooting network errors for GitHub Copilot Resolve common errors related to proxies and custom certificates.\n- Troubleshooting slow responses from GitHub Copilot Troubleshooting help for slow responses from GitHub Copilot.\n- GitHub Copilot Chat cheat sheet Use this cheat sheet to quickly reference the most common commands and options for using GitHub Copilot Chat.\n- Copilot customization cheat sheet Compare the different customization options for GitHub Copilot.\n- Supported AI models in GitHub Copilot Learn about the supported AI models in GitHub Copilot.\n- AI model comparison Compare available AI models in Copilot Chat and choose the best model for your task.\n- Hosting of models for GitHub Copilot Learn how different AI models are hosted for GitHub Copilot.\n- Copilot feature matrix Identify which IDEs support which GitHub Copilot features.\n- Keyboard shortcuts for GitHub Copilot in the IDE Find a list of keyboard shortcuts for GitHub Copilot in the IDEs that support it.\n- GitHub Copilot CLI command reference Find commands and keyboard shortcuts to help you use Copilot CLI effectively.\n- GitHub Copilot CLI plugin reference Find commands and configuration details for CLI plugins.\n- GitHub Copilot CLI programmatic reference Find options for running Copilot CLI programmatically.\n- Copilot CLI ACP server Learn about GitHub Copilot CLI's Agent Client Protocol server.\n- GitHub Copilot CLI configuration directory Find information about the `~/.copilot` directory, where Copilot CLI stores configuration, session data, and customizations.\n- Repository configuration for the GitHub Copilot app Define repository-specific instructions, scripts, and automation behavior for the GitHub Copilot app.\n- Slash commands for the GitHub Copilot app Use slash commands in the GitHub Copilot app to switch modes, run common workflows, and manage sessions without writing a long prompt.\n- Built-in skills for the GitHub Copilot app Use this reference to find built-in agent skills available in the GitHub Copilot app.\n- Custom agents configuration Reference for configuring custom agents.\n- Support for different types of custom instructions Find out which environments support which types of custom instructions.\n- GitHub Copilot hooks reference Find hook events, configuration formats, and input payloads for hooks in Copilot CLI and Copilot cloud agent.\n- Supported surfaces for GitHub Copilot policies Which policies affect which Copilot features and surfaces?\n- Copilot allowlist reference Learn how to allow certain traffic through your firewall or proxy server for Copilot to work as intended in your organization.\n- Metrics data properties for GitHub Copilot See how GitHub calculates properties from APIs and reports.\n- Models and pricing for GitHub Copilot See per-token pricing for the models available in GitHub Copilot and reference rates for additional usage across plans.\n- GitHub Copilot billing cycle Learn about the billing cycle for GitHub Copilot in organizations and enterprises.\n- GitHub Copilot seat assignment Learn how seat assignment for GitHub Copilot works in organizations and enterprises, including billing, user eligibility, and assignment management.\n- Making changes to your GitHub Copilot license Learn how changes to GitHub Copilot licenses affect billing and user access for organizations, enterprises, and personal accounts.\n- GitHub Copilot billing through Azure Learn how metered billing for GitHub Copilot works when you are connected to an Azure subscription, including billing cycles, invoicing, and usage tracking.\n- What changed with Copilot billing (legacy) Learn about what changed with billing and what your options are as a Copilot Pro and Copilot Pro+ annual plan subscriber on the legacy billing model.\n- Requests in GitHub Copilot (legacy) Learn about requests in Copilot, including premium requests, how they work, and how to manage your usage effectively.\n- Monitoring your GitHub Copilot usage and entitlements (legacy) Learn how you can monitor your monthly usage of Copilot and get the most value out of your Copilot plan.\n- Model multipliers for annual plans on request-based billing (legacy) Model multipliers for Copilot Pro and Copilot Pro+ subscribers staying on annual plans under request-based billing.\n- Files excluded from GitHub Copilot code review Understand the types of files that are excluded from a review by Copilot.\n- Data available in Copilot usage metrics Copilot usage metrics data is available through the dashboard and APIs, using a consistent set of fields to represent adoption, usage, and code generation activity.\n- Interpreting usage and adoption metrics for GitHub Copilot Copilot usage and adoption metrics reveal patterns in how developers engage with Copilot across your enterprise.\n- Reconciling Copilot usage metrics across dashboards, APIs, and reports Copilot usage metrics are derived from the same underlying telemetry but are aggregated and presented differently across dashboards, APIs, and exported reports.\n- Lines of Code metrics Lines of Code metrics provide a directional measure of Copilot output by quantifying the lines of code suggested, added, or deleted across completions, chat, and agent features.\n- Team-level Copilot usage metrics Construct team-level GitHub Copilot usage metrics by joining the daily user-teams report with the daily per-user usage metrics report.\n- Example schema for Copilot usage metrics See an example schema of the data returned by the Copilot usage metrics API.\n- Available filters for agent sessions Search agentic activity in your enterprise with filters for agent sessions.\n- Audit log events for agents Understand the structure of audit log events for agents in your enterprise.\n- Enterprise managed settings Understand the enterprise managed settings schema used by Copilot clients.\n- MCP private registry enforcement Understand the logic and limitations of MCP private registry enforcement using a private registry server.\n- Feature availability when GitHub Copilot policies conflict in organizations Delegating Copilot policy decisions to organizations affects users granted a license by organizations with different policies.\n- Creating templates Copilot Chat can help you create templates to streamline your workflow and ensure consistency across your projects.\n- Triage and summarize repository activity Copilot can extract key information from repositories you follow to keep you up-to-date on recent activity.\n- Synthesizing research Copilot Chat can help you synthesize research findings and insights from multiple sources into a cohesive summary.\n- Creating diagrams GitHub Copilot Chat can help you create diagrams to better understand your data and communicate insights.\n- Generating tables Copilot Chat can help you create tables to organize information and present it clearly.\n- Debugging invalid JSON Copilot Chat can identify and resolve syntax errors or structural issues in JSON data.\n- Handling API rate limits Copilot Chat can help handle API rate limits by suggesting code that detects them and implements retry logic.\n- Diagnosing CI test failures Use Copilot CLI to pull CI logs, correlate failures to local code, and fix issues without leaving the terminal.\n- Exploring potential feature implementations Copilot Chat can help explore different approaches for implementing a single feature.\n- Analyzing and incorporating user feedback Copilot Chat can enhance the process of incorporating user feedback into your project.\n- Implementing a feature from a GitHub Issue Give a GitHub issue to GitHub Copilot CLI, then steer the conversation to implement the feature.\n- Improving code readability and maintainability Copilot Chat can suggest ways to make your code easier to understand and maintain.\n- Fixing lint errors Copilot Chat can suggest ways to fix issues identified by a code linter.\n- Refactoring for performance optimization Copilot Chat can suggest ways to speed up slow-running code.\n- Refactoring for environmental sustainability Copilot Chat can suggest ways to make code more environmentally friendly.\n- Refactoring to implement a design pattern Copilot Chat can suggest design patterns that you can use to improve your code.\n- Refactoring data access layers Copilot Chat can suggest ways to decouple your data access code from your business logic, making an application easier to maintain and scale.\n- Decoupling business logic from UI components Copilot Chat can help you separate your business logic from your user interface code, making it easier to maintain and scale your application.\n- Handling cross-cutting concerns Copilot Chat can help you avoid code that relates to a concern other than the core concern of the method or function in which the code is located.\n- Simplifying complex inheritance hierarchies Copilot Chat can help you to refactor code to avoid classes with multiple layers of inheritance.\n- Fixing database deadlocks or data integrity issues Copilot Chat can help you avoid code that causes slow or blocked database operations, or tables with missing or incorrect data.\n- Translating code to a different programming language Copilot Chat can help you rewrite code to perform the same operations but in a different programming language.\n- Filing issues without breaking your flow When something catches your attention mid-task, use Copilot CLI to file a GitHub issue with code context, linked PRs, and labels, then get back to what you were doing.\n- Documenting legacy code Copilot Chat can help with documenting legacy code.\n- Explaining legacy code Copilot Chat can help with explaining unfamiliar code.\n- Explaining complex algorithms or logic Copilot Chat can help add clear and concise documentation on complex algorithms or logic.\n- Syncing documentation with code changes Copilot Chat can help with keeping code documentation up-to-date.\n- Writing discussions or blog posts Copilot Chat can help you generate ideas, outline, or draft discussions or blog posts.\n- Generating unit tests Copilot Chat can help with generating unit tests for a function.\n- Creating mock objects to abstract layers Copilot Chat can help with creating mock objects that you can use for unit tests.\n- Creating end-to-end tests for a webpage Copilot Chat can help with generating end-to-end tests.\n- Updating unit tests to match code changes Copilot Chat can help with updating your tests.\n- Securing your repository Copilot Chat can help you to secure your repository and your code.\n- Managing dependency updates Copilot Chat can help you get set up with Dependabot to streamline dependency updates.\n- Finding existing vulnerabilities in code Copilot Chat can help find common vulnerabilities in your code and suggest fixes.\n- Your first custom instructions Create and test your first custom instruction with this simple example.\n- Concept explainer Instructions for breaking down complex technical concepts.\n- Debugging tutor Instructions for systematic debugging and troubleshooting.\n- Code reviewer Instructions for thorough and constructive code reviews.\n- GitHub Actions helper Generate and improve GitHub Actions workflows.\n- Pull request assistant Generate comprehensive pull request descriptions and reviews.\n- Issue manager Create well-structured issues and responses.\n- Accessibility auditor Instructions for comprehensive web accessibility testing and compliance.\n- Testing automation File-specific instructions for writing unit tests.\n- Your first prompt file Create your first Copilot prompt file with this simple code explanation example that works for any programming language.\n- Create README Generate comprehensive README files for your projects.\n- Onboarding plan A prompt file for getting personalized help with team onboarding.\n- Document API Generate comprehensive API documentation from your code.\n- Review code Perform comprehensive code reviews with structured feedback.\n- Generate unit tests Create focused unit tests for your code.\n- Your first custom agent Create and test your first custom agent with this simple README specialist example.\n- Implementation planner A custom agent that breaks down features into actionable tasks and creates detailed implementation plans.\n- Bug fix teammate A custom agent that identifies critical bugs in your project and implements targeted fixes.\n- Cleanup specialist A custom agent that cleans up messy code, removes duplication, and improves maintainability across code and documentation files.\n- Best practices for using GitHub Copilot to work on tasks Learn how to get the best results from Copilot cloud agent.\n- Piloting GitHub Copilot cloud agent in your organization Follow best practices to enable Copilot cloud agent in your organization.\n- Using GitHub Copilot cloud agent to improve a project Find and fix problems in a project with Copilot cloud agent.\n- Building guardrails for GitHub Copilot cloud agent Configure your enterprise so that Copilot cloud agent will operate in a secure, compliant environment.\n- Giving GitHub Copilot cloud agent access to resources in your organization Get more out of Copilot by giving it access to approved MCP servers and internal packages.\n- Getting started with budget controls Set up budget guardrails for your enterprise before your team starts consuming AI credits.\n- Optimizing your budget configuration Find the right combination of budget controls for your organization based on your size, structure, and spending goals.\n- Using custom instructions to unlock the power of Copilot code review Learn how to write effective custom instructions that help GitHub Copilot provide more relevant and actionable code reviews.\n- Use GitHub Copilot code review across the pull request lifecycle Build a repeatable workflow for Copilot code review from draft pull request to merge.\n- Enhancing GitHub Copilot agent mode with MCP Learn how to use the Model Context Protocol (MCP) to expand the agentic capabilities of Copilot Chat.\n- Comparing AI models using different tasks Explore real-world examples of common developer tasks along with sample prompts, responses, and guidance to help you choose the right AI model for your workflow.\n- Speeding up development work with GitHub Copilot Spaces Learn how to use Copilot Spaces to help you with development work.\n- Choosing your enterprise's plan for GitHub Copilot Choose between Copilot Business and Copilot Enterprise.\n- Setting up a self-serve process for GitHub Copilot licenses Learn how users can request a license and receive access immediately.\n- Tracking license activation and initial usage with Copilot usage metrics Identify and act on GitHub Copilot adoption signals and activation with usage metrics.\n- Reminding inactive users to use their GitHub Copilot license Use the GitHub API to identify inactive users and help them get started.\n- Resources for getting approval of GitHub Copilot Get ready to adopt Copilot by sending resources to legal and security teams in your company.\n- Establishing AI managers in your enterprise Reduce your administrative burden and empower your SMEs by creating a team of AI managers.\n- Maintaining codebase standards in a GitHub Copilot rollout Stay in control of your enterprise's code with rulesets, security features, and effective training.\n- Driving GitHub Copilot adoption in your company Learn how to plan an effective enablement process to drive Copilot adoption.\n- Integrating agentic AI into your enterprise's software development lifecycle See how agents can boost productivity across your enterprise.\n- Achieving your company's engineering goals with GitHub Copilot Plan your rollout based on GitHub's recommended approach for driving and measuring improvements.\n- Increasing test coverage in your company with GitHub Copilot Understand features, enable developers, and measure Copilot's impact.\n- Accelerating pull requests in your company with GitHub Copilot Understand features, enable developers, and measure Copilot's impact.\n- Reducing security debt in your company with GitHub Copilot Understand features, enable developers, and measure Copilot's impact.\n- Measure and demonstrate the impact of GitHub Copilot Understanding how Copilot is used across your enterprise is the first step to demonstrating its value. Follow this path to establish a usage baseline, see how code is being generated, and connect adoption to measurable outcomes.\n- Measuring the success of a GitHub Copilot trial Measure the success of a Copilot trial by analyzing adoption, engagement, and early usage patterns using Copilot usage metrics.\n- Using GitHub Copilot to explore a codebase GitHub Copilot Chat can help you gain an understanding of the content, structure, and functionality of a codebase.\n- Using GitHub Copilot to explore issues and discussions GitHub Copilot Chat can help you quickly gain context of lengthy discussions and issues.\n- Using GitHub Copilot to explore pull requests GitHub Copilot Chat can help you understand the content, functionality, and status of a pull request.\n- Writing tests with GitHub Copilot Use Copilot to generate unit and integration tests, and help improve code quality.\n- Refactoring code with GitHub Copilot Leverage Copilot artificial intelligence to help you refactor your code quickly and effectively.\n- Optimizing your AI usage to maximize efficiency and reduce cost Learn how to choose the right models, structure your prompts, and add guardrails so that Copilot completes tasks more efficiently and uses fewer AI credits.\n- Optimize GitHub Copilot Chat context to reduce AI credit usage Keep Copilot Chat responses focused and reduce AI credits usage by knowing when to continue a conversation and when to start a new one.\n- Build an optimized review process with Copilot Automate reviews with Copilot to optimize and improve your review process.\n- Using GitHub Copilot to reduce technical debt Use Copilot to automate refactoring and maintenance tasks, freeing your team to focus on feature development.\n- Review AI-generated code Learn techniques to verify and validate AI-generated code, and how Copilot Chat can help.\n- Learning a new programming language with GitHub Copilot GitHub Copilot Chat can help you extend your programming skills by learning how to code in a new programming language.\n- Modernizing legacy code with GitHub Copilot Copilot Chat helps modernize legacy code by suggesting refactors and creating tests to catch potential issues.\n- Modernizing Java applications with GitHub Copilot GitHub Copilot can help modernize and migrate Java applications by assessing your codebase, identifying upgrade paths, and automating remediation and containerization tasks.\n- Using GitHub Copilot to migrate a project to another programming language GitHub Copilot Chat can help you move a project to a different language. This guide describes what's involved in a migration process and gives an example of a PHP to Python migration.\n- Planning a project with GitHub Copilot Plan your next project by using GitHub Copilot to turn your ideas into issues.\n- Vibe coding with GitHub Copilot Create an application without writing any code yourself.\n- Upgrading projects with GitHub Copilot You can use GitHub Copilot to upgrade your Maven and Gradle Java applications and .NET applications.\n- Using hooks with Copilot CLI for predictable, policy-compliant execution Use hooks to log user prompts and control which tools Copilot CLI can run in a repository, so teams can automate safely within your organization's security and compliance requirements.\n- Using Copilot CLI as your AI SME Use Copilot CLI as an always-available subject matter expert to learn how a codebase works, so you can confidently maintain it or add new features.\n- Creating extensions for GitHub Copilot CLI Build extensions that add your own tools and slash commands to Copilot CLI.\n- Application card: GitHub Copilot Chat Learn how to use GitHub Copilot Chat responsibly by understanding its purposes, capabilities, and limitations.\n- Application card: GitHub Copilot inline suggestions Learn how to use GitHub Copilot inline suggestions responsibly by understanding their purposes, capabilities, and limitations.\n- Application card: GitHub Copilot Agents Learn how to use GitHub Copilot agentic features responsibly by understanding their purposes, capabilities, and limitations.",
      "content_chars": 65855,
      "published_date": null
    },
    {
      "rank": 7,
      "url": "https://docs.github.com/en/copilot/get-started",
      "title": "Get started with GitHub Copilot",
      "content": "# Get started with GitHub Copilot\n\nLearn how to sign up for and use GitHub Copilot.\n\n## Links\n\n* Quickstart for GitHub Copilot\n\n Quickly learn how to use GitHub Copilot.\n\n* What is GitHub Copilot?\n\n Learn what Copilot is and what you can do with it.\n\n* Plans for GitHub Copilot\n\n Learn about the available plans for Copilot.\n\n* GitHub Copilot features\n\n GitHub Copilot offers a suite of features for users and administrators.\n\n* Best practices for using GitHub Copilot\n\n Learn how to get the most out of Copilot.\n\n* Adopting GitHub Copilot in your enterprise\n\n Adopt the latest GitHub Copilot features without compromising on control and governance.",
      "content_chars": 649,
      "published_date": null
    },
    {
      "rank": 8,
      "url": "https://docs.github.com/en/copilot/get-started/features",
      "title": "",
      "content": "# GitHub Copilot features\n\nGitHub Copilot offers a suite of features for users and administrators.\n\n## Assistive features\n\nThese tools are used synchronously, providing advice or suggestions as people work on a task.\n\n### Copilot Chat\n\nA chat interface that lets you ask coding-related questions. GitHub Copilot Chat is available on the GitHub website, in GitHub Mobile, in supported IDEs, and in Windows Terminal. Users can also use skills with Copilot Chat. See Asking GitHub Copilot questions in GitHub and Asking GitHub Copilot questions in your IDE.\n\n### Inline suggestions\n\nAutocomplete-style suggestions from Copilot in supported IDEs. See Getting code suggestions in your IDE with GitHub Copilot.\n\nIf you use VS Code, Xcode, or Eclipse, you can also use next edit suggestions, which will predict the location of the next edit you are likely to make and suggest a completion for it.\n\n### Copilot pull request summaries\n\nAI-generated summaries of the changes that were made in a pull request, which files they impact, and what a reviewer should focus on when they conduct their review. See Creating a pull request summary with GitHub Copilot.\n\n### Copilot in GitHub Desktop\n\nAutomatically generate commit messages and descriptions with Copilot in GitHub Desktop based on the changes you make to your project.\n\n## Agentic features\n\nThese features can work autonomously without direct human supervision. However, they typically need human approval to perform sensitive actions, such as running commands in a developer's terminal or merging a pull request.\n\n### Copilot CLI\n\nA command line interface that lets you use Copilot in your terminal. Use the CLI to add features or fix bugs, then create a pull request. Start Copilot working on a task in your terminal, then continue working in the same session on GitHub.com, or on your mobile. See About GitHub Copilot CLI.\n\n### GitHub Copilot app\n\nA desktop application for agent-driven development. From the app, you can run multiple agent sessions in parallel across your repositories, manage issues and pull requests, and set up automations to run tasks on a schedule. See About the GitHub Copilot app.\n\n### Copilot cloud agent\n\nAn autonomous AI agent that can research a repository, create an implementation plan, and make code changes on a branch. You can review the diff, iterate, and create a pull request when you're ready. You can also assign a GitHub issue to Copilot or ask it to open a pull request directly to complete a task. See GitHub Copilot cloud agent.\n\n### Third-party coding agents (public preview)\n\nYou can use third-party coding agents alongside Copilot cloud agent. Third-party agents are subject to the same security protections, mitigations, and limitations as Copilot cloud agent. See About third-party coding agents.\n\n### Copilot code review\n\nAI-generated code review suggestions to help you write better code. See Using GitHub Copilot code review.\n\nSeveral tools in Copilot code review are in public preview and subject to change. See About GitHub Copilot code review.\n\n### Agent mode in IDEs\n\nAllow Copilot to work autonomously in the IDE. Copilot will determine which files to make changes to, offer code changes and terminal commands for the user's approval, and iterate to remediate issues until the original task is complete.\n\n## Features for customization\n\nThese features can be used to add context to Copilot and improve its performance. For a comparison of when to use each feature, see Copilot customization cheat sheet.\n\n### Copilot Spaces\n\nOrganize and centralize relevant content\u2014like code, docs, specs, and more\u2014into Spaces that ground Copilot\u2019s responses in the right context for a specific task. See About GitHub Copilot Spaces.\n\n### Custom instructions\n\nEnhance responses by providing contextual details on your preferences, tools, and requirements. See About customizing GitHub Copilot responses.\n\n### Copilot Memory (public preview)\n\nCopilot can deduce and store useful information about a repository, which Copilot cloud agent and Copilot code review can use to improve the quality of their output when working in that repository. For more information, see About GitHub Copilot Memory.\n\n### Prompt files\n\nBuild and share reusable prompt instructions with additional context. A prompt file is a Markdown file, stored in your workspace, that mimics the existing format of writing prompts. See About customizing GitHub Copilot responses.\n\n### MCP servers\n\nYou can configure Model Context Protocol (MCP) servers for many Copilot features, giving Copilot access to external tools or data sources. See About Model Context Protocol (MCP).\n\n### Agent skills\n\nCreate folders of instructions, scripts, and resources that Copilot can load when relevant to improve its performance in specialized tasks. See About agent skills.\n\n### Custom agents\n\nCreate specialized versions of Copilot cloud agent with access to specific tools, instructions, and MCP servers. See About custom agents.\n\n## Features for administrators\n\nThe following features are available to organization and enterprise owners with a Copilot Business or Copilot Enterprise plan.\n\n### Policy management\n\nManage policies for Copilot in your organization or enterprise. See Managing policies and features for GitHub Copilot in your organization and Managing policies and features for GitHub Copilot in your enterprise.\n\n### Access management\n\nEnterprise owners can specify which organizations in the enterprise can use Copilot, and organization owners can specify which organization members can use Copilot. See Managing access to GitHub Copilot in your organization and Managing access to Copilot in your enterprise.\n\n### Usage data\n\nReview Copilot usage data within your organization or enterprise to inform how to manage access and drive adoption of Copilot. See Reviewing user activity data for GitHub Copilot in your organization and Viewing Copilot license usage in your enterprise.\n\n### Audit logs\n\nReview audit logs for Copilot in your enterprise to understand what actions have been taken and by which users. See Reviewing audit logs for GitHub Copilot.\n\n### File exclusions\n\nConfigure Copilot to ignore certain files. This can be useful if you have files that you don't want to be available to Copilot. See Excluding content from GitHub Copilot.\n\n## Next steps\n\n- To learn more about the plans available for GitHub Copilot, see Plans for GitHub Copilot.\n- To start using Copilot, see Setting up GitHub Copilot.",
      "content_chars": 6468,
      "published_date": null
    },
    {
      "rank": 9,
      "url": "https://docs.github.com/en/copilot/concepts",
      "title": "Concepts for GitHub Copilot",
      "content": "# Concepts for GitHub Copilot\n\nLearn the core concepts that you'll need to understand GitHub Copilot.\n\n## Links\n\n* Completions for GitHub Copilot\n\n Learn how Copilot can provide inline suggestions.\n\n* About GitHub Copilot Chat\n\n Learn how you can use GitHub Copilot Chat to enhance your coding experience.\n\n* Concepts for GitHub Copilot agents\n\n Learn how GitHub Copilot can independently execute tasks across the software development lifecycle.\n\n* About cloud and local sandboxes for GitHub Copilot\n\n Cloud and local sandboxes provide isolated execution environments that let Copilot safely interact with code, tools, filesystem, and network resources securely on your local machine or in fully isolated cloud environments.\n\n* About GitHub Spark\n\n Learn about building and deploying intelligent apps with natural language using GitHub Spark.\n\n* GitHub Copilot usage metrics\n\n Track how your teams are using and adopting GitHub Copilot with detailed usage metrics.\n\n* Concepts for prompting GitHub Copilot\n\n Learn how to interact with GitHub Copilot to get the best results.\n\n* Concepts for providing context to GitHub Copilot\n\n Learn how GitHub Copilot gathers contextual information to provide relevant responses to your prompts.\n\n* Concepts for AI tools\n\n Learn about different Copilot tools and how they can be used to help develop software.\n\n* Models for GitHub Copilot\n\n Learn about the AI models available for GitHub Copilot.\n\n* Usage limits for GitHub Copilot\n\n Learn about GitHub Copilot usage limits and what to do if you hit a limit.\n\n* GitHub Copilot billing\n\n Understand billing and usage for GitHub Copilot.\n\n* About enterprise accounts for Copilot Business\n\n An enterprise account lets you manage only Copilot Business licenses, without consuming GitHub Enterprise Cloud licenses.\n\n* GitHub Copilot policies for enterprises and organizations\n\n Control the availability of GitHub Copilot features and models for your users.\n\n* MCP server usage in your company\n\n You can manage MCP server usage to provide your developers with valuable tools while maintaining security and compliance.\n\n* Network settings for GitHub Copilot\n\n You can connect to GitHub Copilot through an HTTP proxy and use custom certificates.\n\n* Learning about new features and models\n\n Stay informed about GitHub Copilot features and models, and make confident decisions about enabling them for your enterprise.",
      "content_chars": 2393,
      "published_date": null
    },
    {
      "rank": 10,
      "url": "https://docs.github.com/en/copilot/concepts/agents/copilot-cli/about-copilot-cli",
      "title": "About GitHub Copilot CLI",
      "content": "# About GitHub Copilot CLI\n\nFind out about using Copilot from the command line.\n\n## Introduction\n\nThe command-line interface (CLI) for GitHub Copilot allows you to use Copilot directly from your terminal. You can use it to answer questions, write and debug code, and interact with GitHub.com. For example, you can ask Copilot to make some changes to a project and create a pull request.\n\nGitHub Copilot CLI gives you quick access to a powerful AI agent, without having to leave your terminal. It can help you complete tasks more quickly by working on your behalf, and you can work iteratively with GitHub Copilot CLI to build the code you need.\n\n## Supported operating systems\n\n- Linux\n- macOS\n- Windows from within Powershell and Windows Subsystem for Linux (WSL)\n\nFor installation instructions, see Installing GitHub Copilot CLI.\n\n## Modes of use\n\nGitHub Copilot CLI has two user interfaces: interactive and programmatic.\n\n### Interactive interface\n\nTo start an interactive session, enter `copilot`. Within an interactive session, you can have a conversation with Copilot. You can prompt Copilot to perform one or more tasks, and you can give it feedback and steer the direction of the work.\n\nThe interactive interface has two modes. In addition to the default ask/execute mode there is also a plan mode in which Copilot will build a structured implementation plan for a task you want to complete.\n\nPress Shift+Tab to cycle between modes. In plan mode, Copilot analyzes your request, asks clarifying questions to understand scope and requirements, and builds a plan before writing any code. This helps you catch misunderstandings before any code is written, and stay in control of complex, multi-step tasks.\n\n### Programmatic interface\n\nYou can also pass the CLI a single prompt directly on the command line. The CLI completes the task and then exits.\n\nTo use the CLI programmatically, include the `-p` or `--prompt` command-line option in your command. To allow Copilot to modify and execute files you should also use one of the approval options described later in this article\u2014see Allowing tools to be used without manual approval ). For example:\n\n```bash\ncopilot -p \"Show me this week's commits and summarize them\" --allow-tool='shell(git)'\n\n```\n\nAlternatively, you can use a script to output command-line options and pipe this to `copilot`. For example:\n\n```bash\n./script-outputting-options.sh | copilot\n\n```\n\n> [!CAUTION]\n> If you use an automatic approval option such as `--allow-all-tools`, Copilot has the same access as you do to files on your computer, and can run any shell commands that you can run, without getting your prior approval. See Security considerations, later in this article.\n\n## Running Copilot CLI commands in a sandbox\n\n> [!NOTE]\n> Cloud and local sandboxes for GitHub Copilot are in public preview and subject to change.\n\nTo prevent Copilot from modifying files you don't want it to touch, you can force agents to run commands within a local sandboxed environment. Alternatively, you can run an entire CLI session in an isolated environment in the cloud. For more information, see About cloud and local sandboxes for GitHub Copilot.\n\n### Local sandboxing\n\nYou can enable local sandboxing inside a Copilot CLI session to restrict Copilot's access to your filesystem, network, and system capabilities. To enable it, run `/sandbox enable` inside a session.\n\n### Cloud sandboxing\n\nYou can start a Copilot CLI session inside an isolated, cloud-hosted environment with cloud sandboxes. This is useful when you want to run code without affecting your local machine, keep a session's state between uses, continue a session from a different machine, or run multiple tasks in parallel. Cloud sandbox policies inherit from Copilot cloud agent policies, so existing security controls like firewall rules extend to cloud sandboxes without additional setup.\n\nTo start a cloud-backed session, run:\n\n```bash\ncopilot \u2011\u2011cloud\n\n```\n\n## Use cases for GitHub Copilot CLI\n\nThe following sections provide examples of tasks you can complete with GitHub Copilot CLI.\n\n### Local tasks\n\n- From within a project directory you can ask Copilot to make a change to the code in the project. For example:`Change the background-color of H1 headings to dark blue` Copilot finds the CSS file where H1 headings are defined and changes the color value.\n- Ask Copilot to tell you about changes to a file:`Show me the last 5 changes made to the CHANGELOG.md file. Who changed the file, when, and give a brief summary of the changes they made`\n- Use Copilot to help you improve the code, or documentation, in your project.`Suggest improvements to content.js``Rewrite the readme in this project to make it more accessible to newcomers`\n- Use Copilot to help you perform Git operations.`Commit the changes to this repo``Revert the last commit, leaving the changes unstaged`\n- Ask Copilot to create an application from scratch\u2014for example, as a proof of concept.`Use the create-next-app kit and tailwind CSS to create a next.js app. The app should be a dashboard built with data from the GitHub API. It should track this project's build success rate, average build duration, number of failed builds, and automated test pass rate. After creating the app, give me easy to follow instructions on how to build, run, and view the app in my browser.`\n- Ask Copilot to explain why a change it made is not working as expected, or tell Copilot to fix a problem with the last change it made. For example:`You said: \"The application is now running on http://localhost:3002 and is fully functional!\" but when I browse to that URL I get \"This site can't be reached\"`\n\n### Tasks involving GitHub.com\n\n- Fetch and display details about your work from GitHub.com.`List my open PRs` This lists your open pull requests from any repository on GitHub. For more specific results, include the repository name in your prompt:`List all open issues assigned to me in OWNER/REPO`\n- Ask Copilot to work on an issue:`I've been assigned this issue: https://github.com/octo-org/octo-repo/issues/1234. Start working on this for me in a suitably named branch.`\n- Ask Copilot to make file changes and raise a pull request on GitHub.com.`In the root of this repo, add a Node script called user-info.js that outputs information about the user who ran the script. Create a pull request to add this file to the repo on GitHub.``Create a PR that updates the README at https://github.com/octo-org/octo-repo, changing the subheading \"How to run\" to \"Example usage\"` Copilot creates a pull request on GitHub.com, on your behalf. You are marked as the pull request author.\n- Ask Copilot to create an issue for you on GitHub.com.`Raise an improvement issue in octo-org/octo-repo. In src/someapp/somefile.py the `file = open('data.txt', 'r')` block opens a file but never closes it.`\n- Ask Copilot to check the code changes in a pull request.`Check the changes made in PR https://github.com/octo-org/octo-repo/pull/57575. Report any serious errors you find in these changes.` Copilot responds in the CLI with a summary of any problems it finds.\n- Manage pull requests from GitHub Copilot CLI.`Merge all of the open PRs that I've created in octo-org/octo-repo``Close PR #11 on octo-org/octo-repo`\n- Find specific types of issues.`Use the GitHub MCP server to find good first issues for a new team member to work on from octo-org/octo-repo` [!NOTE]\nIf you know that a specific MCP server can achieve a particular task, then specifying it in your prompt can help Copilot to deliver the results you want.\n- Find specific GitHub Actions workflows.`List any Actions workflows in this repo that add comments to PRs`\n- Create a GitHub Actions workflow.`Branch off from main and create a GitHub Actions workflow that will run on pull requests, or can be run manually. The workflow should run eslint to check for problems in the changes made in the PR. If warnings or errors are found these should be shown as messages in the diff view of the PR. I want to prevent code with errors from being merged into main so, if any errors are found, the workflow should cause the PR check to fail. Push the new branch and create a pull request.`\n\n## Steering the conversation\n\nYou can interact with Copilot while it's thinking to steer the conversation:\n\n- Enqueue additional messages: Send follow-up messages to steer the conversation in a different direction, or queue additional instructions for Copilot to process after it finishes its current response. This makes conversations feel more natural and keeps you in control.\n- Inline feedback on rejection: When you reject a tool permission request, you can give Copilot inline feedback about the rejection so it can adapt its approach without stopping entirely. This makes the conversation flow more naturally when you want to guide Copilot away from certain actions.\n\n## Automatic context management\n\nGitHub Copilot CLI automatically manages your conversation context:\n\n- Auto-compaction: When your conversation approaches 95% of the token limit, Copilot automatically compresses your history in the background without interrupting your workflow. This enables virtually infinite sessions.\n- Manual control: Use `/compact` to manually compress context anytime. Press Esc to cancel if you change your mind.\n- Visualize usage: The `/context` command shows a detailed token usage breakdown so you can understand how your context window is being used.\n\n## Customizing GitHub Copilot CLI\n\nYou can customize GitHub Copilot CLI in a number of ways:\n\n- Custom instructions: Custom instructions allow you to give Copilot additional context on your project and how to build, test and validate its changes. All custom instruction files now combine instead of using priority-based fallbacks. For more information, see Adding custom instructions for GitHub Copilot CLI.\n- Model Context Protocol (MCP) servers: MCP servers allow you to give Copilot access to different data sources and tools. For more information, see Using GitHub Copilot CLI.\n- Custom agents: Custom agents allow you to create different specialized versions of Copilot for different tasks. For example, you could customize Copilot to be an expert frontend engineer following your team's guidelines. GitHub Copilot CLI includes specialized custom agents that it automatically delegates common tasks to. For more information, see Using GitHub Copilot CLI.\n- Hooks: Hooks allow you to execute custom shell commands at key points during agent execution, enabling you to add validation, logging, security scanning, or workflow automation. See About hooks for GitHub Copilot.\n- Skills: Skills allow you to enhance the ability of Copilot to perform specialized tasks with instructions, scripts, and resources. For more information, see About agent skills.\n- Copilot Memory: Copilot Memory allows Copilot to build a persistent understanding of your repository by storing \"memories\", which are pieces of information about coding conventions, patterns, and preferences that Copilot deduces as it works. This reduces the need to repeatedly explain context in your prompts and makes future sessions more productive. For more information, see About GitHub Copilot Memory.\n\n## Security considerations\n\nWhen you use Copilot CLI, Copilot can perform tasks on your behalf, such as executing or modifying files, or running shell commands.\n\nYou should therefore always keep security considerations in mind when using Copilot CLI, just as you would when working directly with files yourself, or running commands directly in your terminal. You should always review suggested commands carefully when Copilot CLI requests your approval.\n\n### Content exclusion\n\nFor Copilot Business and Copilot Enterprise users, Copilot CLI respects content exclusion policies configured at the enterprise, organization, and repository levels. Excluded files are not used as context. For more information, see Content exclusion for GitHub Copilot.\n\n### Trusted directories\n\nTrusted directories control where Copilot CLI can read, modify, and execute files.\n\nYou should only launch Copilot CLI from directories that you trust. You should not use Copilot CLI in directories that may contain executable files you can't be sure you trust. Similarly, if you launch the CLI from a directory that contains sensitive or confidential data, or files that you don't want to be changed, you could inadvertently expose those files to risk. Typically, you should not launch Copilot CLI from your home directory.\n\nScoping of permissions is heuristic and GitHub does not guarantee that all files outside trusted directories will be protected. See Risk mitigation.\n\nWhen you start a GitHub Copilot CLI session, you'll be asked to confirm that you trust the files in, and below, the directory from which you launched the CLI. See Configuring GitHub Copilot CLI.\n\n### Allowed tools\n\nThe first time that Copilot needs to use a tool that could be used to modify or execute a file\u2014for example, `touch`, `chmod`, `node`, or `sed`\u2014it will ask you whether you want to allow it to use that tool.\n\nTypically, you can choose from three options:\n\n```text\n1. Yes\n2. Yes, and approve TOOL for the rest of the running session\n3. No, and tell Copilot what to do differently (Esc)\n\n```\n\nOption 1 allows Copilot to run this particular command, this time only. The next time it needs to use this tool, it will ask you again.\n\nOption 2 allows Copilot to use this tool again, without asking you for permission, for the duration of the currently running session. It will ask for your approval again in new sessions, or if you resume the current session in the future. If you choose this option, you are allowing Copilot to use this tool in any way it thinks is appropriate. For example, if Copilot asks you to allow it to run the command `rm ./this-file.txt`, and you choose option 2, then Copilot can run any `rm` command (for example, `rm -rf ./*`) during the current run of this session, without asking for your approval.\n\nOption 3 cancels the proposed command and allows you to tell Copilot to try a different approach.\n\n#### Allowing tools to be used without manual approval\n\nThere are three command-line options that you can use, in either interactive or programmatic sessions, to determine tools that Copilot can use without asking for your approval:\n\n- `--allow-all-tools` Allows Copilot to use any tool without asking for your approval. For example, you can use this option with a programmatic invocation of the CLI to allow Copilot to run any command. For example:\n\n```shell\ncopilot -p \"Revert the last commit\" --allow-all-tools\n\n```\n\n- `--deny-tool` Prevents Copilot from using a specific tool. This option takes precedence over the `--allow-all-tools` and `--allow-tool` options.\n- `--allow-tool` Allows Copilot to use a specific tool without asking for your approval.\n\n#### Using the approval options\n\nThe `--deny-tool` and `--allow-tool` options require one of the following arguments:\n\n- `'shell(COMMAND)'` For example, `copilot --deny-tool='shell(rm)'` prevents Copilot from using any `rm` command. For `git` and `gh` commands, you can specify a particular first-level subcommand to allow or deny. For example:\n\n```shell\ncopilot --deny-tool='shell(git push)'\n\n```\n\nThe tool specification is optional. For example, `copilot --allow-tool='shell'` allows Copilot to use any shell command without individual approval.\n\n- `'write'` This argument allows or denies tools\u2014other than shell commands\u2014permission to modify files. For example, `copilot --allow-tool='write'` allows Copilot to edit files without your individual approval.\n- `'MCP_SERVER_NAME'` This argument allows or denies tools from the specified MCP server, where `MCP_SERVER_NAME` is the name of an MCP server that you have configured. Tools from the server are specified in parentheses, using the tool name that is registered with the MCP server. Using the server name without specifying a tool allows or denies all tools from that server. For example, `copilot --deny-tool='My-MCP-Server(tool_name)'` prevents Copilot from using the tool called `tool_name` from the MCP server called `My-MCP-Server`. You can find an MCP server's name by entering `/mcp` in the CLI's interactive interface, then selecting the server from the list that's displayed.\n\n#### Combining approval options\n\nYou can use a combination of approval options to determine exactly which tools Copilot can use without asking for your approval.\n\nFor example, to prevent Copilot from using the `rm` and `git push` commands, but automatically allow all other tools, use:\n\n```shell\ncopilot --allow-all-tools --deny-tool='shell(rm)' --deny-tool='shell(git push)'\n\n```\n\nTo prevent Copilot from using the tool `tool_name` from the MCP server named `My-MCP-Server`, but allow all other tools from that server to be used without individual approval, use:\n\n```shell\ncopilot --allow-tool='My-MCP-Server' --deny-tool='My-MCP-Server(tool_name)'\n\n```\n\n#### Security implications of automatic tool approval\n\nIt's important to be aware of the security implications of using the approval command-line options. These options allow Copilot to execute commands needed to complete your request, without giving you the opportunity to review and approve those commands before they are run. While this streamlines workflows, and allows headless operation of the CLI, it increases the risk of unintended actions being taken that might result in data loss or corruption, or other security issues.\n\nYou can control which tools Copilot CLI can use by responding to approval prompts when Copilot attempts to use a tool, by specifying permissions with command-line flags, or (in an interactive session) by using slash commands (such as `/allow-all` and `/yolo`. See Configuring GitHub Copilot CLI.\n\n### Risk mitigation\n\nYou can mitigate the risks associated with using the automatic approval options by running Copilot CLI in a sandboxed environment. GitHub provides first-party sandboxing for this, with local sandboxing to restrict access on your machine and cloud sandboxing for fully isolated execution. For more information, see About cloud and local sandboxes for GitHub Copilot.\n\nAlternatively, you can run Copilot CLI in a virtual machine, container, or dedicated system with tightly controlled permissions and network access.\n\n### Known MCP server policy limitations\n\nCopilot CLI can't currently support the following organization-level MCP server policies:\n\n- MCP servers in Copilot, which controls whether MCP servers can be used at all by Copilot.\n- MCP Registry URL, which controls which MCP registry Copilot will allow MCP servers to be used from.\n\nFor more information about these policies, see MCP server usage in your company.\n\n## Model usage\n\nYou can change the model used by GitHub Copilot CLI by using the `/model` slash command or the `--model` command-line option. Enter this command, then select a model from the list.\n\nEach time you interact with Copilot in Copilot CLI's interactive interface, or use Copilot CLI programmatically, AI credits are consumed based on the number of tokens processed. The amount consumed per interaction varies depending on the model used. See Models and pricing for GitHub Copilot.\n\n### Models with extended capabilities\n\nThe latest models support a 1 million token context window, so you can work across larger codebases, longer documents, and complex multi-file projects without losing context. After you select a supported model, you will be prompted to choose between the default context size or an extended (1 million token) context.\n\nIn addition, these models also support configurable reasoning levels, which control the depth of the model's reasoning process before it generates a response.\n\nChoosing a larger context window or higher reasoning will impact AI credits consumption; more tokens will be consumed, so more credits will be used. For this reason, we recommend that you use the regular context window and regular reasoning by default, selecting the larger context window and higher reasoning for more complex tasks only.\n\nFor a list of models that support these capabilities, see Models with extended capabilities.\n\n### Using your own model provider\n\nYou can configure Copilot CLI to use your own model provider instead of GitHub-hosted models. This lets you connect to an OpenAI-compatible endpoint, Azure OpenAI, or Anthropic, including locally running models such as Ollama. You configure your model provider using environment variables.\n\n| Environment variable | Description |\n| --- | --- |\n| `COPILOT_PROVIDER_BASE_URL` | The base URL of your model provider's API endpoint. |\n| `COPILOT_PROVIDER_TYPE` | The provider type: `openai` (default), `azure`, or `anthropic`. The `openai` type works with any OpenAI-compatible endpoint, including Ollama and vLLM. |\n| `COPILOT_PROVIDER_API_KEY` | Your API key for authenticating with the provider. Not required for providers that don't use authentication, such as a local Ollama instance. |\n| `COPILOT_MODEL` | The model to use (required when using a custom provider). You can also set this with the `--model` command-line option. |\n\nModels used with Copilot CLI must support tool calling (function calling) and streaming. If the model does not support these capabilities, Copilot CLI will return an error. For best results, the model should have a context window of at least 128k tokens.\n\nFor details on how to configure your model provider, run `copilot help providers` in your terminal.\n\n## Use Copilot CLI via ACP\n\nACP (the Agent Client Protocol) is an open standard for interacting with AI agents. It allows you to use Copilot CLI as an agent in any third-party tools, IDEs, or automation systems that support this protocol.\n\nFor more information, see Copilot CLI ACP server.\n\n## Feedback\n\nIf you have any feedback about GitHub Copilot CLI, please let us know by using the `/feedback` slash command in an interactive session and choosing one of the options. You can complete a private feedback survey, submit a bug report, or suggest a new feature.\n\n## Further reading\n\n- Installing GitHub Copilot CLI\n- Using GitHub Copilot CLI\n- Application card: GitHub Copilot Agents",
      "content_chars": 22158,
      "published_date": null
    }
  ],
  "answer_text": null,
  "citations": [],
  "raw_response": {
    "requestId": "abbbd42db87964c784779f2fb3ca271f",
    "resolvedSearchType": "",
    "results": [
      {
        "id": "https://docs.github.com/en/get-started/using-github/exploring-early-access-releases-with-feature-preview",
        "title": "",
        "url": "https://docs.github.com/en/get-started/using-github/exploring-early-access-releases-with-feature-preview",
        "text": "# Exploring early access releases with feature preview\n\nYou can use feature preview to see products or features that are available in public preview and to enable or disable each feature for your personal account.\n\n## GitHub's release cycle\n\nGitHub's products and features can go through multiple release phases.\n\n| Phase | Description |\n| --- | --- |\n| Private preview | The product or feature is under heavy development and often has changing requirements and scope. The feature is available for demonstration and test purposes but may not be documented. Private preview releases are not necessarily feature complete, no service level agreements (SLAs) are provided, and there are no technical support obligations. |\n\nNote: A product or feature released as a \"Technology Preview\" is considered to be in the private preview release stage. Technology Preview releases share the same characteristics of private preview releases as described above.|\n| Public preview | The product or feature is ready for broader distribution. Public preview releases can be public or private, are documented, but do not have any SLAs or technical support obligations. |\n| General availability (GA) | The product or feature is fully tested and open publicly to all users. GA releases are ready for production use, and associated SLA and technical support obligations apply. |\n\n## Exploring public preview releases with feature preview\n\nYou can see a list of features that are available in public preview and a brief description for each feature. Each feature includes a link to give feedback.\n\n1. In the upper-right corner of any page, click your profile picture, then click Feature preview.\n2. To view details for a feature, in the left sidebar, click the feature's name.\n3. Optionally, to the right of a feature's name, click Enable or Disable."
      },
      {
        "id": "https://docs.github.com/en/copilot/get-started/what-is-github-copilot",
        "title": "",
        "url": "https://docs.github.com/en/copilot/get-started/what-is-github-copilot",
        "text": "# What is GitHub Copilot?\n\nLearn what Copilot is and what you can do with it.\n\nGitHub Copilot is an AI coding assistant that helps you write code faster and with less effort. Then, you can focus more energy on problem solving and collaboration.\n\nResearch shows that Copilot increases developer productivity and accelerates software development. See Research: quantifying GitHub Copilot\u2019s impact on developer productivity and happiness in the GitHub blog.\n\n## Features\n\nYou can use Copilot to:\n\n- Get code suggestions as you type in your IDE.\n- Chat with Copilot to get help with your code.\n- Ask for help using the command line.\n- Organize and share context with Copilot Spaces to get more relevant answers.\n- Generate descriptions of changes in a pull request.\n- Research, plan, make code changes, and create pull requests for you to review.\n\nFor enterprises and organizations with data residency requirements: If you use GitHub Enterprise Cloud, Copilot can enforce geographic data residency. See GitHub Copilot with data residency.\n\nUse Copilot in the following places:\n\n- Your IDE\n- GitHub Mobile, as a chat interface\n- Windows Terminal Canary, through the Terminal Chat interface\n- The command line, through the GitHub CLI\n- The GitHub Copilot app, a desktop application for agent-driven development. See About the GitHub Copilot app.\n- The GitHub website\n\nSee GitHub Copilot features.\n\n## Get access\n\nYou can start using Copilot in several ways, depending on your role and needs.\n\n### Individuals\n\n- Try Copilot for free. Use Copilot Free to explore core features with no paid plan required.\n- Subscribe to a paid plan. Upgrade to Copilot Pro, Copilot Pro+, or Copilot Max for access to premium features, increased access to models, and higher available monthly allowance of AI credits.\n- Get free access if you're eligible. Students, teachers, and open source maintainers may qualify for access to premium features at no cost. See Access GitHub Copilot for free as a student and Access Copilot Pro for free as a teacher or open source maintainer.\n- Request access from your organization. If your organization or enterprise has a GitHub Copilot plan, you can request access by going to https://github.com/settings/copilot and request access under \"Get Copilot from an organization.\"\n\nSee Getting started with a GitHub Copilot plan for more information.\n\n### Organizations and enterprises\n\nOwners of organizations on GitHub Free or GitHub Team can purchase Copilot Business for their organization. Subscribe to Copilot Business.\n\nIf your organization is owned by an enterprise that has a Copilot subscription, you can ask your enterprise owner to enable Copilot for your organization. Go to https://github.com/settings/copilot and request access under \"Get Copilot from an organization.\"\n\nEnterprise owners can set up Copilot Business or Copilot Enterprise for their enterprise.\n\n- If you want to pay by credit card or PayPal, subscribe here. [!NOTE] If you are currently in a trial of GitHub Enterprise Cloud, you must convert to a paid enterprise before you can purchase GitHub Copilot.\n- For other payment methods, contact GitHub's Sales team.\n\n## Next steps\n\n- Learn more about Copilot features. See GitHub Copilot features.\n- Start using Copilot. See Setting up GitHub Copilot.\n\n## Further reading\n\n- Frequently asked questions about GitHub Copilot\n- GitHub Copilot Trust Center"
      },
      {
        "id": "https://docs.github.com/en/copilot/concepts/learning-about-new-features-and-models",
        "title": "",
        "url": "https://docs.github.com/en/copilot/concepts/learning-about-new-features-and-models",
        "text": "# Learning about new features and models\n\nStay informed about GitHub Copilot features and models, and make confident decisions about enabling them for your enterprise.\n\nGitHub Copilot is evolving rapidly, with new features and models released regularly. If you're an enterprise administrator, staying informed helps you make confident decisions about which capabilities to enable, when to adopt them, and how to manage risk across your organizations.\n\nThis article provides guidance on navigating the Copilot landscape, understanding different types of features and models, and preparing for upcoming changes.\n\n## Keeping up to date with Copilot changes\n\nYou can use GitHub Docs and the GitHub Blog to keep track of new releases.\n\n### Learning about new Copilot features\n\nTo learn about new Copilot features, we recommend monitoring these two locations:\n\n- Features overview: For a complete list of Copilot capabilities, see GitHub Copilot features.\n- Changelog: Follow the Copilot changelog for announcements about new and updated features.\n\nCopilot features generally fall into three categories:\n\n| Type | Description | Examples | Considerations |\n| --- | --- | --- | --- |\n| Assistive | Respond to prompts and provide suggestions, but require human review before changes are made. | Inline suggestions, Copilot Chat, Copilot pull request summaries. | All changes require user approval. |\n| Agentic | Autonomously research, plan, and make changes on behalf of users. | Copilot cloud agent, third-party agents. | Can work autonomously, but with built-in protections. |\n| Third-party | External coding agents that work alongside Copilot cloud agent to complete tasks asynchronously. | Anthropic Claude, OpenAI Codex. | Same as agentic. Review provider documentation and enable via policies. See About third-party coding agents. |\n\nEach feature has its own enablement requirements and policy settings. When a new feature is released:\n\n1. Review the feature documentation to understand its capabilities.\n2. Check the policy settings available at the enterprise and organization level. See GitHub Copilot policies for enterprises and organizations.\n3. Consider running a pilot with a subset of users before broader rollout.\n\n### Learning about new Copilot models\n\nGitHub Copilot uses multiple AI models from different providers to power its features. Different models have different strengths: some prioritize speed and cost-efficiency, while others are optimized for accuracy, reasoning, or working with multimodal inputs (like images and code together).\n\nUsers will have access to different models depending on the feature they're using and your enterprise's Copilot plan and policies.\n\nYou can find information about the models available and upcoming models in the following locations:\n\n- Supported models: For a complete list of available models and their capabilities, see Supported AI models in GitHub Copilot.\n- Model comparison: To compare model capabilities side by side, see AI model comparison.\n- Changelog: Model updates are announced in the Copilot changelog.\n\n#### Default enablement\n\nOn Copilot Business and Copilot Enterprise plans, a new policy will control whether unconfigured generally available (GA) models default to enabled or disabled. For more information, see About default availability of Copilot models.\n\n#### Special categories\n\nGitHub categorizes certain types of model, allowing you to plan for model transitions and set user expectations.\n\n| Model type | Description | Why it matters |\n| --- | --- | --- |\n| Utility model | A small set of models that power background GitHub features across surfaces. | Your enterprise cannot disable these models. Monitor these to ensure they are compliant. |\n| Base model | The default model when no other models are enabled. | Automatically enabled within 60 days of designation. |\n| LTS model | A model supported for one year from designation. | Allows enterprises to build workflows around a stable model. |\n\nFor more information, see Utility models and Base and long-term support (LTS) models.\n\n## Considering different release stages\n\nCopilot features and models progress through different release stages. Understanding release stages helps you decide when to enable features for your organization. Each stage has different expectations for stability and support.\n\n| Stage | Availability | Stability |\n| --- | --- | --- |\n| Private preview | Limited set of customers by invitation. | May change significantly based on feedback. |\n| Public preview | All eligible customers who opt in. | Functional but may have limitations or change. |\n| Generally available (GA) | All customers. | Fully supported and recommended for production. |\n\n> [!TIP] Many preview features are covered by the GitHub Data Protection Agreement, meaning you can test them without breaching compliance requirements. See GitHub DPA-Covered Previews for a list.\n\nPreview features are controlled by policy settings at the organization and enterprise level. The Opt in to preview features policy allows administrators to enable or disable preview features on the GitHub website specifically. See Managing policies and features for GitHub Copilot in your enterprise and Managing policies and features for GitHub Copilot in your organization.\n\n## Reviewing information about Responsible AI\n\nGitHub is committed to responsible AI development and provides transparency documentation for each Copilot feature.\n\nEach Copilot feature has a dedicated responsible use article describing its purpose, capabilities, and limitations. See Responsible use of GitHub Copilot features."
      },
      {
        "id": "https://docs.github.com/en/copilot/concepts/preparing-for-new-features-and-models",
        "title": "",
        "url": "https://docs.github.com/en/copilot/concepts/preparing-for-new-features-and-models",
        "text": "# Learning about new features and models\n\nStay informed about GitHub Copilot features and models, and make confident decisions about enabling them for your enterprise.\n\nGitHub Copilot is evolving rapidly, with new features and models released regularly. If you're an enterprise administrator, staying informed helps you make confident decisions about which capabilities to enable, when to adopt them, and how to manage risk across your organizations.\n\nThis article provides guidance on navigating the Copilot landscape, understanding different types of features and models, and preparing for upcoming changes.\n\n## Keeping up to date with Copilot changes\n\nYou can use GitHub Docs and the GitHub Blog to keep track of new releases.\n\n### Learning about new Copilot features\n\nTo learn about new Copilot features, we recommend monitoring these two locations:\n\n* **Features overview**: For a complete list of Copilot capabilities, see GitHub Copilot features.\n* **Changelog**: Follow the Copilot changelog for announcements about new and updated features.\n\nCopilot features generally fall into three categories:\n\n \n\n| Type | Description | Examples | Considerations |\n| ----------- | ------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Assistive | Respond to prompts and provide suggestions, but require human review before changes are made. | Inline suggestions, Copilot Chat, Copilot pull request summaries. | All changes require user approval. |\n| Agentic | Autonomously research, plan, and make changes on behalf of users. | Copilot cloud agent, third-party agents. | Can work autonomously, but with built-in protections. |\n| Third-party | External coding agents that work alongside Copilot cloud agent to complete tasks asynchronously. | Anthropic Claude, OpenAI Codex. | Same as agentic. Review provider documentation and enable via policies. See About third-party coding agents. |\n\n \n\nEach feature has its own enablement requirements and policy settings. When a new feature is released:\n\n1. Review the feature documentation to understand its capabilities.\n2. Check the policy settings available at the enterprise and organization level. See GitHub Copilot policies for enterprises and organizations.\n3. Consider running a pilot with a subset of users before broader rollout.\n\n### Learning about new Copilot models\n\nGitHub Copilot uses multiple AI models from different providers to power its features. Different models have different strengths: some prioritize speed and cost-efficiency, while others are optimized for accuracy, reasoning, or working with multimodal inputs (like images and code together).\n\nUsers will have access to different models depending on the feature they're using and your enterprise's Copilot plan and policies.\n\nYou can find information about the models available and upcoming models in the following locations:\n\n* **Supported models**: For a complete list of available models and their capabilities, see Supported AI models in GitHub Copilot.\n* **Model comparison**: To compare model capabilities side by side, see AI model comparison.\n* **Changelog**: Model updates are announced in the Copilot changelog.\n\n#### Default enablement\n\n \n\nOn Copilot Business and Copilot Enterprise plans, a new policy will control whether unconfigured generally available (GA) models default to enabled or disabled. For more information, see About default availability of Copilot models.\n\n \n\n#### Special categories\n\nGitHub categorizes certain types of model, allowing you to plan for model transitions and set user expectations.\n\n \n\n| Model type | Description | Why it matters |\n| ------------- | ---------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |\n| Utility model | A small set of models that power background GitHub features across surfaces. | Your enterprise cannot disable these models. Monitor these to ensure they are compliant. |\n| Base model | The default model when no other models are enabled. | Automatically enabled within 60 days of designation. |\n| LTS model | A model supported for one year from designation. | Allows enterprises to build workflows around a stable model. |\n\n \n\nFor more information, see Utility models and Base and long-term support (LTS) models.\n\n## Considering different release stages\n\nCopilot features and models progress through different release stages. Understanding release stages helps you decide when to enable features for your organization. Each stage has different expectations for stability and support.\n\n \n\n| Stage | Availability | Stability |\n| ------------------------ | --------------------------------------- | ----------------------------------------------- |\n| Private preview | Limited set of customers by invitation. | May change significantly based on feedback. |\n| Public preview | All eligible customers who opt in. | Functional but may have limitations or change. |\n| Generally available (GA) | All customers. | Fully supported and recommended for production. |\n\n \n\n> \\[!TIP] Many preview features are covered by the GitHub Data Protection Agreement, meaning you can test them without breaching compliance requirements. See GitHub DPA-Covered Previews for a list.\n\nPreview features are controlled by policy settings at the organization and enterprise level. The **Opt in to preview features** policy allows administrators to enable or disable preview features on the GitHub website specifically. See Managing policies and features for GitHub Copilot in your enterprise and Managing policies and features for GitHub Copilot in your organization.\n\n## Reviewing information about Responsible AI\n\nGitHub is committed to responsible AI development and provides transparency documentation for each Copilot feature.\n\nEach Copilot feature has a dedicated **responsible use** article describing its purpose, capabilities, and limitations. See Responsible use of GitHub Copilot features."
      },
      {
        "id": "https://docs.github.com/en/site-policy/github-terms/github-dpa-previews",
        "title": "GitHub DPA-Covered Previews - GitHub Docs",
        "url": "https://docs.github.com/en/site-policy/github-terms/github-dpa-previews",
        "publishedDate": "2025-10-27T00:00:00.000Z",
        "text": "# GitHub DPA-Covered Previews\n\n## GitHub DPA-Covered Previews\n\nThe pre-release products and features listed below use data handling that is the same as when the software becomes generally available. Under GitHub\u2019s Pre-Release License Terms, this software is governed by the GitHub Data Protection Agreement as of the date listed, and the Customer is the Data Controller beginning on that date (the \"DPA Coverage Date\"). The software is no longer considered a Preview on the date it becomes generally available (the \"GA Date\").\n\n| Product / Feature | DPA Coverage Date | GA Date |\n| --- | --- | --- |\n| Copilot CLI | 27 October 2025 | 25 February 2026 |\n| Copilot Enterprise & Users Usage Metrics Dashboard | 27 October 2025 | 27 February 2026 |\n| Spark | 27 October 2025 | [TBD] |"
      },
      {
        "id": "https://docs.github.com/en/copilot",
        "title": "GitHub Copilot documentation - GitHub Docs",
        "url": "https://docs.github.com/en/copilot",
        "text": "# GitHub Copilot documentation\n\nYou can use GitHub Copilot to enhance your productivity and assist as you work on code.\n\n## Links\n\n### Getting started\n\n- What is GitHub Copilot? Learn what Copilot is and what you can do with it.\n- Quickstart for GitHub Copilot Quickly learn how to use GitHub Copilot.\n\n## Articles\n\n- Quickstart for GitHub Copilot Quickly learn how to use GitHub Copilot.\n- Getting started with GitHub Copilot CLI Quickly learn how to use GitHub Copilot CLI.\n- Getting started with the GitHub Copilot app Sign in to the GitHub Copilot app, connect a repository or local folder, and create your first agent session to make code changes.\n- What is GitHub Copilot? Learn what Copilot is and what you can do with it.\n- Plans for GitHub Copilot Discover the plans available for Copilot.\n- GitHub Copilot features GitHub Copilot offers a suite of features for users and administrators.\n- Best practices for using GitHub Copilot Learn how to get the most out of Copilot.\n- Adopting GitHub Copilot in your enterprise Adopt the latest GitHub Copilot features without compromising on control and governance.\n- GitHub Copilot code suggestions in your IDE Learn about Copilot code suggestions in different IDEs.\n- GitHub Copilot code referencing GitHub Copilot checks suggestions for matches with publicly available code. Any matches are discarded or suggested with a code reference.\n- About GitHub Copilot Chat Learn how you can use GitHub Copilot Chat to enhance your coding experience.\n- About GitHub Copilot cloud agent Copilot can research a repository, create an implementation plan, and make code changes on a branch. You can review the diff, iterate, and create a pull request when you're ready.\n- About agent management Use one centralized control page to jump between agent sessions, check progress, and stay in control without losing your place.\n- About custom agents Custom agents enhance Copilot with assistance tailored to your needs.\n- About Copilot automations Automations let you run Copilot cloud agent automatically, on a schedule or in response to events in a repository.\n- About rationale, confidence, and approvals for issues When automations triage issues, it explains each change, rates its confidence, and holds lower-confidence changes for your review.\n- Managing access to GitHub Copilot cloud agent Find out about Copilot cloud agent policies available for GitHub Copilot Enterprise and GitHub Copilot Business, and about disabling the agent for specific repositories.\n- Model Context Protocol (MCP) and GitHub Copilot cloud agent Find out about using the Model Context Protocol (MCP) with Copilot cloud agent.\n- Risks and mitigations for GitHub Copilot cloud agent How do Copilot cloud agent's built-in security protections mitigate known risks?\n- About GitHub Copilot CLI Find out about using Copilot from the command line.\n- Comparing GitHub Copilot CLI customization features Find out about the various ways you can customize Copilot: what they do, and when to use them.\n- Canceling a GitHub Copilot CLI operation and rolling back changes Find out about the different ways to cancel an active Copilot operation, and how to roll back changes made during a session if the result isn't what you expected.\n- Managing context in GitHub Copilot CLI Understand how Copilot manages conversation context, what happens during long sessions, and how to stay in control of your context window.\n- About remote control of GitHub Copilot CLI sessions Remote control lets you monitor and steer a Copilot CLI session from GitHub.com or GitHub Mobile, even after you've stepped away from your machine.\n- About custom agents Custom agents enhance Copilot with assistance tailored to your needs.\n- Allowing GitHub Copilot CLI to work autonomously The CLI's autopilot mode lets Copilot CLI work autonomously on a task, carrying out multiple steps until the task is complete.\n- Running tasks in parallel with the `/fleet` command The `/fleet` slash command lets Copilot CLI break down a complex request into smaller tasks and run them in parallel, maximizing efficiency and throughput.\n- Researching with GitHub Copilot CLI The `/research` slash command turns Copilot into your research assistant, gathering in-depth information and insights on a topic.\n- About GitHub Copilot CLI session data Your Copilot CLI sessions build a searchable history of everything you have worked on. Query past sessions with natural language, generate standup reports, get personalized tips, and resume previous work.\n- About the rubber duck agent The rubber duck agent is a built-in critic that gives Copilot a constructive second opinion on its own plans, code, and tests\u2014using a different AI model from the one driving your session.\n- Using LSP servers with GitHub Copilot CLI LSP servers give Copilot CLI precise code intelligence, enabling it to navigate definitions, find references, and rename symbols accurately across your project.\n- About extensions for GitHub Copilot CLI Extensions let you add your own tools and slash commands to GitHub Copilot CLI, using only the SDK that ships with the CLI.\n- Loading tools on demand with tool search Tool search keeps your context small by letting Copilot CLI load external tools only when a task needs them.\n- Understanding filesystem policies for local sandboxing in GitHub Copilot CLI When local sandboxing is enabled, Copilot CLI runs each sandboxed process or operation under a filesystem policy that controls which files and directories it can read and write. Learn how that policy is built and how to check the access it grants.\n- About the GitHub Copilot app The GitHub Copilot app is a desktop application for agent-driven development that brings parallel workstreams, GitHub integration, and PR lifecycle management into one place.\n- Using GitHub Copilot in JetBrains IDEs Learn about the different ways to use GitHub Copilot in JetBrains IDEs, including the GitHub Copilot plugin, JetBrains AI Assistant, and Copilot CLI.\n- About GitHub Copilot code review Copilot reviews your pull requests, identifies issues, and suggests fixes you can apply in a couple of clicks.\n- About GitHub Agentic Workflows Automate repetitive repository work with natural language instructions executed by AI coding agents in GitHub Actions.\n- About GitHub Copilot Memory Copilot Memory helps Copilot become more effective over time by remembering facts about your repositories and your personal coding preferences.\n- About hooks for GitHub Copilot Extend and customize GitHub Copilot agent behavior by executing custom shell commands at key points during agent execution.\n- About GitHub Copilot plugins Plugins are installable packages that extend Copilot with reusable agents, skills, hooks, and integrations.\n- About enterprise-managed plugin standards Enterprise administrators can centrally define plugin policies for users, ensuring consistent plugin availability.\n- About third-party coding agents You can use third-party coding agents alongside Copilot cloud agent to work asynchronously on your development tasks on GitHub.\n- About agent apps Agent apps let you use partner-built agents directly in your workflows on GitHub, powered by your Copilot subscription.\n- OpenAI Codex Use the OpenAI Codex coding agent and Visual Studio Code extension powered by Copilot.\n- Anthropic Claude Use the Anthropic Claude coding agent powered by Copilot.\n- About agent skills Skills allow Copilot to perform specialized tasks.\n- Agent management for enterprises Maintain your enterprise's security and compliance standards and supercharge your developers by managing agents with AI Controls.\n- OpenTelemetry for agent monitoring Understand how Copilot agents perform and interact with models and tools.\n- About cloud and local sandboxes for GitHub Copilot Cloud and local sandboxes provide isolated execution environments that let Copilot safely interact with code, tools, filesystem, and network resources securely on your local machine or in fully isolated cloud environments.\n- GitHub Copilot usage metrics Copilot usage metrics provide visibility into how Copilot is adopted and used across your organization, including engagement, activity, code generation, and pull request lifecycle trends.\n- Prompt engineering for GitHub Copilot Chat Follow these strategies to improve your Copilot results.\n- About customizing GitHub Copilot responses Learn about customizing the behavior of GitHub Copilot to fit with your preferences and requirements.\n- About Model Context Protocol (MCP) Model Context Protocol (MCP) is a protocol that allows you to extend the capabilities of GitHub Copilot by integrating it with other systems.\n- About GitHub Copilot Spaces Understand how organizing and sharing context with Copilot Spaces can improve your Copilot Chat in GitHub results and help your collaborators.\n- Indexing repositories for GitHub Copilot Copilot improves responses by indexing your repositories.\n- Content exclusion for GitHub Copilot You can prevent Copilot from accessing certain files.\n- Choosing the right AI tool for your task Understand GitHub's AI tools and how they can be used to help develop software.\n- About Copilot integrations Integrate Copilot with other tools and platforms to streamline your workflow.\n- About default availability of Copilot models A policy controls whether unconfigured models default to enabled or disabled.\n- Bring your own key for GitHub Copilot Use your existing LLM provider with GitHub Copilot to save costs or consolidate billing.\n- Utility models Utility models power background Copilot features.\n- About Copilot auto model selection Automatically select the best model for each task.\n- FedRAMP-compliant models for GitHub Copilot Restrict users to models with FedRAMP Moderate certification.\n- Base and long-term support (LTS) models Learn about base models, long-term support (LTS) models, and how they affect model availability for enterprises using GitHub Copilot.\n- Usage limits for GitHub Copilot Learn about GitHub Copilot usage limits and what to do if you hit a limit.\n- Usage-based billing for individuals Your Copilot plan includes a monthly allowance of GitHub AI Credits. If you exhaust your AI credits, you can pay extra to keep working.\n- Usage-based billing for organizations and enterprises Under usage-based billing, Copilot usage in organizations and enterprises is measured in AI credits.\n- Budgets for usage-based billing Under usage-based billing, budget controls at the user, organization, cost center, and enterprise levels determine how Copilot usage is served, metered, or blocked.\n- About billing for GitHub Copilot in organizations and enterprises Learn about pricing and billing cycles for Copilot.\n- About enterprise accounts for Copilot Business An enterprise account lets you manage only Copilot Business licenses, without consuming GitHub Enterprise Cloud licenses.\n- GitHub Copilot policies for enterprises and organizations Control the availability of GitHub Copilot features and models for your users.\n- MCP server usage in your company You can manage MCP server usage to provide your developers with valuable tools while maintaining security and compliance.\n- Network settings for GitHub Copilot You can connect to GitHub Copilot through an HTTP proxy and use custom certificates.\n- Learning about new features and models Stay informed about GitHub Copilot features and models, and make confident decisions about enabling them for your enterprise.\n- Setting up GitHub Copilot for yourself Start using GitHub Copilot to write code faster on GitHub.\n- Setting up GitHub Copilot for your organization Enable GitHub Copilot for your organization so members can write code faster.\n- Setting up GitHub Copilot for your enterprise Enable GitHub Copilot across your enterprise so developers can write code faster.\n- Setting up an enterprise for GitHub Copilot Business only Use an enterprise account to manage Copilot Business licenses without consuming GitHub Enterprise Cloud licenses.\n- Access GitHub Copilot for free as a student Get free access to Copilot's premium features as a verified student.\n- Access Copilot Pro for free as a teacher or open source maintainer Get free access to Copilot Pro as a verified teacher or open-source maintainer.\n- Configuring access to AI models in GitHub Copilot Control which AI models your organization or enterprise can use with Copilot.\n- Configuring code review by GitHub Copilot Set up Copilot to review pull requests.\n- Configuring runners for GitHub Copilot code review Use self-hosted runners or larger GitHub-hosted runners for Copilot code review.\n- Getting started with prompts for Copilot Chat on GitHub Explore example prompts to ask Copilot Chat about code, repositories, pull requests, and more.\n- Asking GitHub Copilot questions in GitHub Get instant answers about your code, repositories, and development questions \u2014 right from GitHub.\n- Asking GitHub Copilot questions in GitHub Mobile Ask coding questions, explore repositories, and get help with pull requests in GitHub Mobile.\n- Customize Copilot for your project Set up custom instructions, create a specialized agent, and organize project context on GitHub.\n- Adding personal custom instructions for GitHub Copilot Customize GitHub Copilot Chat responses to match your personal preferences.\n- Adding repository custom instructions for GitHub Copilot Create repository custom instructions files that give Copilot additional context on how to understand your project and how to build, test and validate its changes.\n- Adding organization custom instructions for GitHub Copilot Customize Copilot responses for members of your organization.\n- Creating custom agents for Copilot cloud agent You can create specialized agents with tailored expertise for specific development tasks.\n- Adding agent skills for GitHub Copilot You can modify Copilot's behavior and abilities when it works on particular tasks.\n- Customize agent workflows with hooks Run automated checks\u2014like linting, formatting, or security scans\u2014at key points during agent execution to enforce quality standards.\n- Configure the development environment Pre-install tools and dependencies so Copilot cloud agent can build, test, and validate changes reliably.\n- Configure secrets and variables for Copilot cloud agent Securely pass secrets and variables to Copilot cloud agent so it can access private resources and configure MCP servers.\n- Testing and releasing custom agents in your organization or enterprise Ensure your custom agents are performant and compliant before releasing them to your company.\n- Customizing or disabling the firewall for GitHub Copilot Learn how to control the domains and URLs that Copilot cloud agent and Copilot code review can access.\n- Configure MCP servers for your repository Configure Model Context Protocol (MCP) servers for your repository to give Copilot cloud agent and Copilot code review access to external tools and data sources.\n- Creating GitHub Copilot Spaces Create spaces to organize and centralize relevant content that grounds Copilot's responses in the right context for a specific task.\n- Collaborating with others using GitHub Copilot Spaces Share Copilot Spaces to support collaboration and knowledge sharing.\n- Using GitHub Copilot to create or update issues Use Copilot to quickly generate structured, high-quality issues from natural language or images, without filling out every field manually.\n- Creating a pull request summary with GitHub Copilot Generate an AI-powered summary of your pull request changes to help reviewers quickly understand what you changed and why.\n- Using the GitHub MCP Server from Copilot Chat Perform GitHub tasks\u2014like creating branches, merging pull requests, and searching for users\u2014directly from Copilot Chat in GitHub, with no setup required.\n- Get started with Copilot agents on GitHub Try Copilot cloud agent end-to-end in about ten minutes.\n- Kick off a task with Copilot agents on GitHub Decide whether Copilot cloud agent creates a pull request immediately or works on a branch you review and iterate on first.\n- Research, plan, and iterate on code changes with Copilot cloud agent Perform deep research on a repository, create an implementation plan, and make iterative code changes on a branch, then create a pull request when you're ready.\n- Managing agent sessions Monitor an agent's progress in real time, steer it with follow-up prompts, and stop or archive sessions.\n- Using GitHub Copilot code review on GitHub GitHub Copilot reviews your pull requests and suggests ready-to-apply changes, so you get fast, actionable feedback on every commit.\n- Review output from Copilot Copilot pull requests deserve the same thorough review as any contribution.\n- Setting up GitHub Copilot for yourself Follow these steps to start using Copilot.\n- Installing the GitHub Copilot extension in your environment To use Copilot in your preferred coding environment, follow the steps for your chosen IDE.\n- Getting code suggestions in your IDE with GitHub Copilot Use GitHub Copilot to get code suggestions in your editor.\n- Finding public code that matches GitHub Copilot suggestions Learn how to view code references when GitHub Copilot makes suggestions that matches publicly available code.\n- Getting started with prompts for GitHub Copilot Chat in your IDE Get an overview of ways to use Copilot Chat in your IDE.\n- Asking GitHub Copilot questions in your IDE Use Copilot Chat in your editor to give you code suggestions, explain code, generate unit tests, and suggest code fixes.\n- Asking GitHub Copilot questions in Windows Terminal You can use Copilot in Windows Terminal to get suggestions and explanations for the command line.\n- Best practices for GitHub Copilot CLI Learn how to get the most out of GitHub Copilot CLI.\n- Installing GitHub Copilot CLI Learn how to install Copilot CLI so that you can use Copilot directly from the command line.\n- Configuring GitHub Copilot CLI Configure trusted directories, tool access, and path and URL permissions for Copilot CLI\n- Adding LSP servers for GitHub Copilot CLI You can add LSP servers to give Copilot CLI precise code intelligence, improving its ability to navigate definitions, find references, and rename symbols.\n- Using GitHub Copilot CLI Learn how to use GitHub Copilot from the command line.\n- Allowing and denying tool use Control which tools Copilot CLI can use to avoid unintended changes.\n- Use voice input with Copilot CLI Speak your prompts to GitHub Copilot CLI instead of typing them, using the CLI's speech-to-text feature.\n- Connecting GitHub Copilot CLI to VS Code Connect Copilot CLI to VS Code to share context, trust settings, and output.\n- Browsing issues, pull requests, and gists from GitHub Copilot CLI Use the tabs in an interactive Copilot CLI session to browse issues, pull requests and gists, without leaving the terminal.\n- Rolling back changes made during a GitHub Copilot CLI session Rewind your Copilot CLI session to a previous prompt to undo changes in conversation history, and optionally restore files.\n- Working with multiple GitHub Copilot CLI sessions Run several Copilot CLI sessions at once and use the sidebar to quickly move between them.\n- Steering a GitHub Copilot CLI session from another device Enable remote control for a Copilot CLI session so you can monitor progress, respond to prompts, and continue working from GitHub.com or GitHub Mobile.\n- Managing pull requests with the /pr command Use the `/pr` slash command to view, create, and fix pull requests directly from Copilot CLI.\n- Speeding up task completion with the `/fleet` command Learn how you can speed up the completion of a multi-step implementation plan by using the `/fleet` slash command.\n- Using GitHub Copilot CLI session data Resume previous Copilot CLI sessions, use the `/chronicle` slash command to get insights from your session history, and ask Copilot questions about your CLI usage.\n- Quickstart for automating with GitHub Copilot CLI Build an automation with Copilot CLI in minutes.\n- Running GitHub Copilot CLI programmatically Use Copilot CLI in the terminal, in scripts, or in Actions workflows.\n- Scheduling prompts in GitHub Copilot CLI Use the `/every` and `/after` slash commands to submit a prompt to Copilot on a recurring schedule, or after a specified delay.\n- Automating tasks with Copilot CLI and GitHub Actions Integrate GitHub Copilot CLI into your GitHub Actions workflows.\n- Overview of customizing GitHub Copilot CLI Copilot CLI works best when customized for your specific project and workflow.\n- Adding custom instructions for GitHub Copilot CLI Give Copilot additional context on how to understand your project and how to build, test and validate its changes.\n- Changing settings with the `/settings` command View and change your personal settings for GitHub Copilot CLI with the `/settings` slash command.\n- Using hooks with GitHub Copilot CLI Extend GitHub Copilot agent behavior with custom shell commands at key points during agent execution.\n- Adding agent skills for GitHub Copilot CLI Modify Copilot's behavior and abilities when it works on particular tasks.\n- Adding MCP servers for GitHub Copilot CLI Extend Copilot's capabilities by connecting Model Context Protocol (MCP) servers to provide additional tools and context.\n- Creating and using custom agents for GitHub Copilot CLI Create specialized agents with tailored expertise for specific development tasks.\n- Using your own LLM models in GitHub Copilot CLI Use a model from an external provider of your choice in Copilot by supplying your own API key.\n- Finding and installing plugins for GitHub Copilot CLI Extend Copilot's functionality by installing plugins created by the community or by your team.\n- Creating a plugin for GitHub Copilot CLI Create a plugin to share customizations in an easy-to-install package.\n- Creating a plugin marketplace for GitHub Copilot CLI You can make CLI plugins that you've created easy to install by adding them to a marketplace.\n- Administering Copilot CLI for your enterprise Control the use of Copilot CLI within your enterprise.\n- Using Copilot CLI in GitHub Actions with GITHUB_TOKEN Run Copilot CLI in a GitHub Actions workflow using the built-in `GITHUB_TOKEN`, without a personal access token.\n- Using local sandboxing Enable local sandboxing so that Copilot CLI runs the commands and tools it invokes on your behalf inside an operating-system sandbox.\n- Configuring local sandbox settings Use the `/sandbox` slash command in Copilot CLI to control how the local sandbox restricts filesystem access, network connectivity, and system capabilities.\n- Customizing the GitHub Copilot app Customize the GitHub Copilot app so it works the way you and your team do.\n- Working with agent sessions in the GitHub Copilot app Run multiple isolated agent sessions simultaneously, each with its own branch, and steer them using different session modes, models, and tools.\n- Working with canvas extensions in the GitHub Copilot app Use canvases in the GitHub Copilot app to build shared, agent-driven artifacts and interfaces for human-agent collaboration.\n- Managing issues and pull requests with the GitHub Copilot app Pick up an issue, direct an agent to implement changes, and land a pull request\u2014all without leaving the GitHub Copilot app.\n- Using automations in the GitHub Copilot app Automate recurring agent tasks so they run on a schedule or on demand, without manual intervention.\n- Using your own LLM models in the GitHub Copilot app Connect a model from an external provider of your choice by supplying your own API key, then use the model in agent sessions.\n- Using deep links to open the GitHub Copilot app Use deep links to launch the GitHub Copilot app from the terminal, tickets, and internal tools, so people can jump directly into the right repository, pull request, automation, or session.\n- Build your first Copilot-powered app In this tutorial, you'll use the Copilot SDK to build a command-line assistant. You'll start with the basics, add streaming responses, then add custom tools - giving Copilot the ability to call your code.\n- Authentication The GitHub Copilot SDK supports multiple authentication methods to fit different use cases. Choose the method that best matches your deployment scenario.\n- BYOK (bring your own key) BYOK allows you to use the Copilot SDK with your own API keys from model providers, bypassing GitHub Copilot authentication. This is useful for enterprise deployments, custom model hosting, or when you want direct billing with your model provider.\n- Server-to-server authentication Use a short-lived installation access token when a service needs to make Copilot requests on behalf of an organization without a user's credentials. In GitHub Actions, use the built-in `GITHUB_TOKEN` instead.\n- The agent loop How the Copilot CLI processes a user message end-to-end: from prompt to `session.idle`.\n- Citations Citations link spans of an assistant response back to the sources that support them. Turn on `enableCitations` when you create or resume a session, then read the `citations` payload on `assistant.message` events to render footnotes, source lists, or inline links.\n- Cloud sessions Cloud sessions run Copilot work on GitHub-hosted compute and appear in the agents panel on GitHub. Use them when your app should create a session that executes remotely instead of starting a local GitHub Copilot CLI session on the user's machine or your server.\n- Context clearing and terminal tools Use `session.history.clearContext` when a host needs to replace the current conversation context without replacing the session. Typical uses include handoffs and host-managed context lifecycle policies.\n- Custom agents and sub-agent orchestration Define specialized agents with scoped tools and prompts, then let Copilot orchestrate them as sub-agents within a single session. For dispatching multiple sub-agents in parallel, see Fleet mode.\n- Fleet mode Fleet mode is Copilot's parallel orchestration pattern for work that can be split across independent sub-agents. In the runtime research notes, fleet mode is described as \"the runtime's built-in pattern for dispatching multiple sub-agents in parallel via the `task` tool, with SQL todos as the shared coordination state.\" Use it when one parent session should coordinate several workers, collect their results, and continue the conversation with the combined context.\n- Working with hooks Hooks let you plug custom logic into every stage of a Copilot session\u2014from the moment it starts, through each user prompt and tool call, to the moment it ends. This guide walks through practical use cases so you can ship permissions, auditing, notifications, and more without modifying the core agent behavior.\n- Image input Send images to Copilot sessions as attachments. There are two ways to attach images:\n- Using MCP servers with the GitHub Copilot SDK The Copilot SDK can integrate with MCP servers (Model Context Protocol) to extend the assistant's capabilities with external tools. MCP servers run as separate processes and expose tools (functions) that Copilot can invoke during conversations.\n- Plugin directories A plugin is a directory that bundles SDK extensions \u2014 skills, hooks, MCP servers, custom agents, and LSP configuration \u2014 behind a single manifest. Pointing the SDK at a plugin directory loads everything the plugin contributes, so you can ship reusable capability packs without writing per-extension wiring in every host application.\n- Remote sessions Remote sessions sync to GitHub so users can access locally running Copilot sessions from the agents panel or on mobile. When enabled, the SDK produces a URL to the session log that can be shared as a link or QR code.\n- Session limits Session limits let an application set an AI Credits budget for a Copilot session. Use `sessionLimits` when creating or resuming a session to set a soft cap for the current accounting window.\n- Session resume and persistence This guide walks you through the SDK's session persistence capabilities\u2014how to pause work, resume it later, and manage sessions in production environments.\n- Custom skills Skills are reusable prompt modules that extend Copilot's capabilities. Load skills from directories to give Copilot specialized abilities for specific domains or workflows.\n- Steering and queueing Two interaction patterns let users send messages while the agent is already working: steering redirects the agent mid-turn, and queueing buffers messages for sequential processing after the current turn completes.\n- Streaming session events Every action the Copilot agent takes\u2014thinking, writing code, running tools\u2014is emitted as a session event you can subscribe to. This guide is a field-level reference for each event type so you know exactly what data to expect without reading the SDK source.\n- Usage and billing metrics This guide shows how to read token counts, context-window utilization, AI credit cost, and account quota from a Copilot SDK application. Examples are shown for TypeScript, Python, Go, .NET, Java, and Rust.\n- Error handling hook The `onErrorOccurred` hook is called when errors occur during session execution. Use it to:\n- Session hooks Hooks allow you to intercept and customize the behavior of Copilot sessions at key points in the conversation lifecycle. Use hooks to:\n- Post-tool use hook The `onPostToolUse` hook is called after a tool executes successfully. Use it to:\n- Pre-tool use hook The `onPreToolUse` hook is called before a tool executes. Use it to:\n- Session lifecycle hooks Session lifecycle hooks let you respond to session start and end events. Use them to:\n- User prompt submitted hook The `onUserPromptSubmitted` hook is called when a user submits a message. Use it to:\n- User prompt transformed hook The `userPromptTransformed` hook runs after the runtime adds generated context to a submitted prompt, but before the resulting content is persisted to session history or sent to the model.\n- Microsoft agent framework integration Use the Copilot SDK as an agent provider inside the Microsoft Agent Framework (MAF) to compose multi-agent workflows alongside Azure OpenAI, Anthropic, and other providers.\n- OpenTelemetry instrumentation for Copilot SDK This guide shows how to add OpenTelemetry tracing to your Copilot SDK applications.\n- Azure managed identity with BYOK The GitHub Copilot SDK's BYOK (bring your own key) supports static API keys, but Azure deployments often use Managed Identity (Microsoft Entra ID) instead of long-lived keys. The GitHub Copilot SDK is designed to compose with the Azure Identity SDK for maximum flexibility. Supply a bearer token provider callback that can fetch fresh tokens on demand using an Azure Identity SDK API.\n- Backend services setup Run the Copilot SDK in server-side applications\u2014APIs, web backends, microservices, and background workers. The CLI runs as a headless server that your backend code connects to over the network.\n- Default setup (bundled CLI) The Node.js and .NET SDKs include the Copilot CLI as a dependency\u2014your app ships with everything it needs, with no extra installation or configuration required.\n- Setup guides These guides walk you through configuring the Copilot SDK for your specific use case\u2014from personal side projects to production platforms serving thousands of users.\n- GitHub OAuth setup Let users authenticate with their GitHub accounts to use Copilot through your application. This supports individual accounts, organization memberships, and enterprise identities.\n- Local CLI setup Use a specific CLI binary instead of the SDK's automatic CLI management. This is an advanced option\u2014you supply the CLI path explicitly, and you are responsible for ensuring version compatibility with the SDK.\n- Multi-tenancy and server deployments Multi-user server mode means running the Copilot SDK from backend code that serves more than one human, tenant, workspace, or integration account. In this setup, the application owns request routing and authorization, while the SDK and runtime provide per-session state, per-session authentication, and explicit tool registration so one user's session does not inherit another user's tools or identity.\n- Scaling and multi-tenancy Design your Copilot SDK deployment to serve multiple users, handle concurrent sessions, and scale horizontally across infrastructure. This guide covers session isolation patterns, scaling topologies, and production best practices.\n- SDK and CLI compatibility This document outlines which Copilot CLI features are available through the SDK and which are CLI-only.\n- Debugging guide This guide covers common issues and debugging techniques for the Copilot SDK across all supported languages.\n- MCP server debugging guide This guide covers debugging techniques specific to MCP (Model Context Protocol) servers when using the Copilot SDK.\n- Starting GitHub Copilot sessions Choose your preferred way to start Copilot cloud agent sessions.\n- Creating automations with Copilot cloud agent Create and manage automations to run Copilot cloud agent on a schedule or in response to events.\n- Managing rationale, confidence, and approvals for issues Set up and manage rationale, confidence, and approvals for issues handled by automation.\n- Changing the AI model for GitHub Copilot cloud agent In supported entrypoints, when starting a task with Copilot cloud agent, you can select the model used, and, for supported models, the reasoning level.\n- Configuring settings for GitHub Copilot cloud agent Learn how to configure settings for Copilot cloud agent\n- Creating custom agents for Copilot cloud agent in your IDE You can create specialized agents with tailored expertise for specific development tasks.\n- Using Copilot cloud agent on GitHub Start Copilot cloud agent sessions directly on GitHub, then iterate on the results without leaving your browser.\n- Using Copilot cloud agent on GitHub Mobile Start and track Copilot cloud agent sessions from the GitHub Mobile app.\n- Using agent apps Start a partner-built agent from an issue, a pull request comment, or the Agents UI on GitHub.\n- Using Copilot cloud agent in your IDE Start and track Copilot cloud agent sessions from Visual Studio Code, JetBrains IDEs, Eclipse, and Visual Studio.\n- Using Copilot cloud agent via the API You can start and manage Copilot cloud agent tasks programmatically using the REST API.\n- Using Copilot cloud agent from the GitHub CLI Start and track Copilot cloud agent sessions from the GitHub CLI.\n- Using Copilot cloud agent via the GitHub MCP Server Start Copilot cloud agent sessions from any IDE or agentic tool that supports Model Context Protocol (MCP).\n- Using Copilot cloud agent from Raycast Start and track Copilot cloud agent sessions from the Raycast launcher.\n- Troubleshooting GitHub Copilot cloud agent Learn how to resolve problems that may occur when you assign tasks to Copilot.\n- Using GitHub Copilot code review Learn how to request a code review from GitHub Copilot.\n- Managing Copilot Memory for your personal account Review and manage the coding conventions, preferences, and other details that Copilot has stored from your interactions.\n- Managing Copilot Memory for an organization or enterprise Manage Copilot Memory settings and stored memories for an organization or enterprise.\n- Integrating Copilot cloud agent with Slack Provide context to the Copilot cloud agent and open pull requests, all from within your Slack workspace.\n- Integrating Copilot cloud agent with Teams You can use the GitHub integration in Teams to provide context and open pull requests all from within your Teams channels.\n- Integrating Copilot cloud agent with Jira You can use the GitHub integration in Jira to provide context and open pull requests, all from within your Jira workspace.\n- Integrating Copilot cloud agent with Linear Use the Copilot integration in Linear to provide context, customize how the agent runs, and open pull requests, all from within your Linear workspace.\n- Integrating Copilot cloud agent with Azure Boards Use the Copilot integration in Azure Boards to send work items directly to Copilot cloud agent and generate pull requests, all from within your Azure DevOps workspace.\n- Changing the AI model for GitHub Copilot Chat Learn how to switch between models for Copilot Chat.\n- Changing the AI model for GitHub Copilot inline suggestions Learn how to change the default LLM for Copilot inline suggestions to a different model.\n- Using GitHub Copilot Spaces Use spaces to ground Copilot's responses in the right context for a specific task.\n- Extending GitHub Copilot Chat with Model Context Protocol (MCP) servers Connect MCP servers to Copilot Chat to share context from other applications.\n- Setting up the GitHub MCP Server Learn how to configure the GitHub Model Context Protocol (MCP) server.\n- Configuring the GitHub MCP Server for GitHub Enterprise Learn how to configure the GitHub Model Context Protocol (MCP) server to work with GitHub Enterprise Server or GitHub Enterprise Cloud with data residency.\n- Configuring toolsets for the GitHub MCP Server Learn how to configure toolsets and tools for the GitHub MCP server for fine-grained control and optimized performance.\n- Using the GitHub MCP Server in your IDE Learn how to use the GitHub Model Context Protocol (MCP) server to interact with repositories, issues, pull requests, and other GitHub features, directly from Copilot Chat in your IDE.\n- Changing your MCP registry in your IDE Customize the MCP registry you can use with Copilot Chat.\n- Adding repository custom instructions for GitHub Copilot in your IDE Create repository custom instructions files that give Copilot additional context on how to understand your project and how to build, test and validate its changes.\n- Excluding content from GitHub Copilot Learn how to prevent Copilot from accessing certain content.\n- Reviewing changes to content exclusions for GitHub Copilot You can monitor changes to content exclusions in your repositories and organizations.\n- Using the GitHub CLI Copilot extension This article provides details about the replacement for the Copilot extension for GitHub CLI.\n- Configuring network settings for GitHub Copilot You can connect to GitHub Copilot through an HTTP proxy and use custom certificates.\n- Configuring GitHub Copilot in your environment You can enable, configure, or disable GitHub Copilot in a supported IDE.\n- Using GitHub Copilot with an account on GHE.com Update your development environment to access a Copilot plan for an account on GHE.com.\n- Monitoring your GitHub AI Credits usage Learn how to monitor the AI credits you consume when using Copilot.\n- Managing your company's spending on GitHub Copilot Learn how to track spending, view usage, and optimize license distribution.\n- Getting started with a GitHub Copilot plan You can use Copilot for free, or choose a paid plan to unlock additional features, models, and limits.\n- Viewing and changing your GitHub Copilot plan Learn how to view, cancel, or update your Copilot plan.\n- Disabling GitHub Copilot Free Learn how to disable Copilot Free in your IDE or GitHub.com.\n- Managing GitHub Copilot policies as an individual subscriber Find out how to change your personal settings on GitHub to configure GitHub Copilot's behavior.\n- Canceling GitHub Copilot for your organization Removing all assigned GitHub Copilot seats in your organization will cancel your organization's Copilot plan.\n- Granting access to GitHub Copilot for members of your organization Grant access to GitHub Copilot for some or all of the members of your organization.\n- Managing requests for GitHub Copilot Business in your organization Approve or deny requests for Copilot access in your organization.\n- Revoking access to GitHub Copilot for members of your organization Remove access to GitHub Copilot for some or all of the members of your organization.\n- Managing GitHub Copilot access to your organization's network Learn how to use subscription-based network routing to control Copilot access to your network.\n- Managing policies and features for GitHub Copilot in your organization Control the availability of GitHub Copilot features and models for users granted a license by your organization.\n- Adding GitHub Copilot cloud agent to your organization Enable Copilot cloud agent for your members and control the repositories where it is available.\n- Configuring runners for GitHub Copilot cloud agent in your organization Configure the GitHub Actions runners used by Copilot cloud agent and control whether repositories can customize the runner type.\n- Preparing to use custom agents in your organization Configure the repository that stores custom agents for your organization.\n- Managing the availability of models in an organization Configure which default Copilot models are available to members of your organization.\n- Reviewing user activity data for GitHub Copilot in your organization Review GitHub Copilot usage in your organization to make informed decisions about seat assignment.\n- Enabling custom models for GitHub Copilot in your organization Integrate your preferred custom models with GitHub Copilot by using your own LLM API keys, and make them available to your organization members.\n- Subscribing to GitHub Copilot for your enterprise Enterprise owners can set up a Copilot Enterprise or Copilot Business plan for their enterprise.\n- Canceling GitHub Copilot for your enterprise Disabling GitHub Copilot for all organizations in your enterprise will cancel your enterprise's Copilot plan.\n- Upgrading GitHub Copilot for your enterprise Change your organizations' plans from Copilot Business to Copilot Enterprise.\n- Downgrading GitHub Copilot for your enterprise You can downgrade organizations in your enterprise from Copilot Enterprise to Copilot Business.\n- Granting users access to GitHub Copilot in your enterprise Enable Copilot for entire organizations or grant access directly to specific users.\n- Disabling Copilot for organizations in your enterprise Disable GitHub Copilot for some or all of the organizations in your enterprise.\n- Viewing Copilot license usage in your enterprise View how many users have access to GitHub Copilot across your enterprise.\n- Managing GitHub Copilot access to your enterprise's network Learn how to use subscription-based network routing to control Copilot access to your network.\n- Managing policies and features for GitHub Copilot in your enterprise Control the availability of features for GitHub Copilot in your enterprise using policies.\n- Preparing to use custom agents in your enterprise Set up your enterprise for custom agents by configuring their source organization and repository, availability, and management permissions.\n- Creating a `.github-private` repository A `.github-private` repository can serve as a designated source of governance settings for agents and plugins across your enterprise.\n- Configuring enterprise-managed settings Configure enterprise managed settings to centrally control Copilot client behavior across your enterprise using server-managed, MDM-managed, or file-based deployment.\n- Monitoring agentic activity in your enterprise Track agentic activity in your enterprise to ensure continued compliance.\n- Enabling GitHub Copilot cloud agent in your enterprise Choose which organizations can use Copilot cloud agent and connect it to MCP servers.\n- Blocking agentic features in your enterprise Disable features for all users and repositories.\n- Enabling GitHub Copilot code review in your enterprise Apply consistent standards by having Copilot review every pull request.\n- Managing availability of models in your enterprise Control which Copilot models are available to users.\n- Enabling custom models for GitHub Copilot in your enterprise Integrate your preferred custom models with GitHub Copilot by using your own LLM API keys, and make them available for organizations in your enterprise account.\n- Reviewing audit logs for GitHub Copilot Check for changes to settings or licenses in your Copilot plan.\n- Configuring an MCP server allowlist for your enterprise Define which MCP servers your users can and cannot use without the need for a private registry.\n- Configure an MCP registry for your organization or enterprise Create and host a list of MCP servers that your developers can access.\n- Restrict MCP server access to a custom registry You can configure an MCP registry URL and access control policy to determine which MCP servers developers can discover and use in supported IDEs and Copilot CLI.\n- Downloading a GitHub Copilot activity report for your organization or enterprise Monitor Copilot license usage with a detailed report.\n- Viewing the Copilot usage metrics dashboard Monitor adoption trends and use of Copilot to support long-term enablement.\n- Viewing the code generation dashboard The code generation dashboard shows how Copilot generates code across your enterprise, including activity from both users and agents.\n- Viewing the Copilot impact dashboard The impact dashboard shows how deeply your organization has adopted Copilot, and how that adoption connects to pull request output.\n- Troubleshooting common issues with GitHub Copilot This guide describes the most common issues with GitHub Copilot and how to resolve them.\n- Viewing logs for GitHub Copilot in your environment View logs to troubleshoot GitHub Copilot-related errors in your IDE.\n- Troubleshooting firewall settings for GitHub Copilot Troubleshooting help for firewall-related errors.\n- Troubleshooting network errors for GitHub Copilot Resolve common errors related to proxies and custom certificates.\n- Troubleshooting slow responses from GitHub Copilot Troubleshooting help for slow responses from GitHub Copilot.\n- GitHub Copilot Chat cheat sheet Use this cheat sheet to quickly reference the most common commands and options for using GitHub Copilot Chat.\n- Copilot customization cheat sheet Compare the different customization options for GitHub Copilot.\n- Supported AI models in GitHub Copilot Learn about the supported AI models in GitHub Copilot.\n- AI model comparison Compare available AI models in Copilot Chat and choose the best model for your task.\n- Hosting of models for GitHub Copilot Learn how different AI models are hosted for GitHub Copilot.\n- Copilot feature matrix Identify which IDEs support which GitHub Copilot features.\n- Keyboard shortcuts for GitHub Copilot in the IDE Find a list of keyboard shortcuts for GitHub Copilot in the IDEs that support it.\n- GitHub Copilot CLI command reference Find commands and keyboard shortcuts to help you use Copilot CLI effectively.\n- GitHub Copilot CLI plugin reference Find commands and configuration details for CLI plugins.\n- GitHub Copilot CLI programmatic reference Find options for running Copilot CLI programmatically.\n- Copilot CLI ACP server Learn about GitHub Copilot CLI's Agent Client Protocol server.\n- GitHub Copilot CLI configuration directory Find information about the `~/.copilot` directory, where Copilot CLI stores configuration, session data, and customizations.\n- Repository configuration for the GitHub Copilot app Define repository-specific instructions, scripts, and automation behavior for the GitHub Copilot app.\n- Slash commands for the GitHub Copilot app Use slash commands in the GitHub Copilot app to switch modes, run common workflows, and manage sessions without writing a long prompt.\n- Built-in skills for the GitHub Copilot app Use this reference to find built-in agent skills available in the GitHub Copilot app.\n- Custom agents configuration Reference for configuring custom agents.\n- Support for different types of custom instructions Find out which environments support which types of custom instructions.\n- GitHub Copilot hooks reference Find hook events, configuration formats, and input payloads for hooks in Copilot CLI and Copilot cloud agent.\n- Supported surfaces for GitHub Copilot policies Which policies affect which Copilot features and surfaces?\n- Copilot allowlist reference Learn how to allow certain traffic through your firewall or proxy server for Copilot to work as intended in your organization.\n- Metrics data properties for GitHub Copilot See how GitHub calculates properties from APIs and reports.\n- Models and pricing for GitHub Copilot See per-token pricing for the models available in GitHub Copilot and reference rates for additional usage across plans.\n- GitHub Copilot billing cycle Learn about the billing cycle for GitHub Copilot in organizations and enterprises.\n- GitHub Copilot seat assignment Learn how seat assignment for GitHub Copilot works in organizations and enterprises, including billing, user eligibility, and assignment management.\n- Making changes to your GitHub Copilot license Learn how changes to GitHub Copilot licenses affect billing and user access for organizations, enterprises, and personal accounts.\n- GitHub Copilot billing through Azure Learn how metered billing for GitHub Copilot works when you are connected to an Azure subscription, including billing cycles, invoicing, and usage tracking.\n- What changed with Copilot billing (legacy) Learn about what changed with billing and what your options are as a Copilot Pro and Copilot Pro+ annual plan subscriber on the legacy billing model.\n- Requests in GitHub Copilot (legacy) Learn about requests in Copilot, including premium requests, how they work, and how to manage your usage effectively.\n- Monitoring your GitHub Copilot usage and entitlements (legacy) Learn how you can monitor your monthly usage of Copilot and get the most value out of your Copilot plan.\n- Model multipliers for annual plans on request-based billing (legacy) Model multipliers for Copilot Pro and Copilot Pro+ subscribers staying on annual plans under request-based billing.\n- Files excluded from GitHub Copilot code review Understand the types of files that are excluded from a review by Copilot.\n- Data available in Copilot usage metrics Copilot usage metrics data is available through the dashboard and APIs, using a consistent set of fields to represent adoption, usage, and code generation activity.\n- Interpreting usage and adoption metrics for GitHub Copilot Copilot usage and adoption metrics reveal patterns in how developers engage with Copilot across your enterprise.\n- Reconciling Copilot usage metrics across dashboards, APIs, and reports Copilot usage metrics are derived from the same underlying telemetry but are aggregated and presented differently across dashboards, APIs, and exported reports.\n- Lines of Code metrics Lines of Code metrics provide a directional measure of Copilot output by quantifying the lines of code suggested, added, or deleted across completions, chat, and agent features.\n- Team-level Copilot usage metrics Construct team-level GitHub Copilot usage metrics by joining the daily user-teams report with the daily per-user usage metrics report.\n- Example schema for Copilot usage metrics See an example schema of the data returned by the Copilot usage metrics API.\n- Available filters for agent sessions Search agentic activity in your enterprise with filters for agent sessions.\n- Audit log events for agents Understand the structure of audit log events for agents in your enterprise.\n- Enterprise managed settings Understand the enterprise managed settings schema used by Copilot clients.\n- MCP private registry enforcement Understand the logic and limitations of MCP private registry enforcement using a private registry server.\n- Feature availability when GitHub Copilot policies conflict in organizations Delegating Copilot policy decisions to organizations affects users granted a license by organizations with different policies.\n- Creating templates Copilot Chat can help you create templates to streamline your workflow and ensure consistency across your projects.\n- Triage and summarize repository activity Copilot can extract key information from repositories you follow to keep you up-to-date on recent activity.\n- Synthesizing research Copilot Chat can help you synthesize research findings and insights from multiple sources into a cohesive summary.\n- Creating diagrams GitHub Copilot Chat can help you create diagrams to better understand your data and communicate insights.\n- Generating tables Copilot Chat can help you create tables to organize information and present it clearly.\n- Debugging invalid JSON Copilot Chat can identify and resolve syntax errors or structural issues in JSON data.\n- Handling API rate limits Copilot Chat can help handle API rate limits by suggesting code that detects them and implements retry logic.\n- Diagnosing CI test failures Use Copilot CLI to pull CI logs, correlate failures to local code, and fix issues without leaving the terminal.\n- Exploring potential feature implementations Copilot Chat can help explore different approaches for implementing a single feature.\n- Analyzing and incorporating user feedback Copilot Chat can enhance the process of incorporating user feedback into your project.\n- Implementing a feature from a GitHub Issue Give a GitHub issue to GitHub Copilot CLI, then steer the conversation to implement the feature.\n- Improving code readability and maintainability Copilot Chat can suggest ways to make your code easier to understand and maintain.\n- Fixing lint errors Copilot Chat can suggest ways to fix issues identified by a code linter.\n- Refactoring for performance optimization Copilot Chat can suggest ways to speed up slow-running code.\n- Refactoring for environmental sustainability Copilot Chat can suggest ways to make code more environmentally friendly.\n- Refactoring to implement a design pattern Copilot Chat can suggest design patterns that you can use to improve your code.\n- Refactoring data access layers Copilot Chat can suggest ways to decouple your data access code from your business logic, making an application easier to maintain and scale.\n- Decoupling business logic from UI components Copilot Chat can help you separate your business logic from your user interface code, making it easier to maintain and scale your application.\n- Handling cross-cutting concerns Copilot Chat can help you avoid code that relates to a concern other than the core concern of the method or function in which the code is located.\n- Simplifying complex inheritance hierarchies Copilot Chat can help you to refactor code to avoid classes with multiple layers of inheritance.\n- Fixing database deadlocks or data integrity issues Copilot Chat can help you avoid code that causes slow or blocked database operations, or tables with missing or incorrect data.\n- Translating code to a different programming language Copilot Chat can help you rewrite code to perform the same operations but in a different programming language.\n- Filing issues without breaking your flow When something catches your attention mid-task, use Copilot CLI to file a GitHub issue with code context, linked PRs, and labels, then get back to what you were doing.\n- Documenting legacy code Copilot Chat can help with documenting legacy code.\n- Explaining legacy code Copilot Chat can help with explaining unfamiliar code.\n- Explaining complex algorithms or logic Copilot Chat can help add clear and concise documentation on complex algorithms or logic.\n- Syncing documentation with code changes Copilot Chat can help with keeping code documentation up-to-date.\n- Writing discussions or blog posts Copilot Chat can help you generate ideas, outline, or draft discussions or blog posts.\n- Generating unit tests Copilot Chat can help with generating unit tests for a function.\n- Creating mock objects to abstract layers Copilot Chat can help with creating mock objects that you can use for unit tests.\n- Creating end-to-end tests for a webpage Copilot Chat can help with generating end-to-end tests.\n- Updating unit tests to match code changes Copilot Chat can help with updating your tests.\n- Securing your repository Copilot Chat can help you to secure your repository and your code.\n- Managing dependency updates Copilot Chat can help you get set up with Dependabot to streamline dependency updates.\n- Finding existing vulnerabilities in code Copilot Chat can help find common vulnerabilities in your code and suggest fixes.\n- Your first custom instructions Create and test your first custom instruction with this simple example.\n- Concept explainer Instructions for breaking down complex technical concepts.\n- Debugging tutor Instructions for systematic debugging and troubleshooting.\n- Code reviewer Instructions for thorough and constructive code reviews.\n- GitHub Actions helper Generate and improve GitHub Actions workflows.\n- Pull request assistant Generate comprehensive pull request descriptions and reviews.\n- Issue manager Create well-structured issues and responses.\n- Accessibility auditor Instructions for comprehensive web accessibility testing and compliance.\n- Testing automation File-specific instructions for writing unit tests.\n- Your first prompt file Create your first Copilot prompt file with this simple code explanation example that works for any programming language.\n- Create README Generate comprehensive README files for your projects.\n- Onboarding plan A prompt file for getting personalized help with team onboarding.\n- Document API Generate comprehensive API documentation from your code.\n- Review code Perform comprehensive code reviews with structured feedback.\n- Generate unit tests Create focused unit tests for your code.\n- Your first custom agent Create and test your first custom agent with this simple README specialist example.\n- Implementation planner A custom agent that breaks down features into actionable tasks and creates detailed implementation plans.\n- Bug fix teammate A custom agent that identifies critical bugs in your project and implements targeted fixes.\n- Cleanup specialist A custom agent that cleans up messy code, removes duplication, and improves maintainability across code and documentation files.\n- Best practices for using GitHub Copilot to work on tasks Learn how to get the best results from Copilot cloud agent.\n- Piloting GitHub Copilot cloud agent in your organization Follow best practices to enable Copilot cloud agent in your organization.\n- Using GitHub Copilot cloud agent to improve a project Find and fix problems in a project with Copilot cloud agent.\n- Building guardrails for GitHub Copilot cloud agent Configure your enterprise so that Copilot cloud agent will operate in a secure, compliant environment.\n- Giving GitHub Copilot cloud agent access to resources in your organization Get more out of Copilot by giving it access to approved MCP servers and internal packages.\n- Getting started with budget controls Set up budget guardrails for your enterprise before your team starts consuming AI credits.\n- Optimizing your budget configuration Find the right combination of budget controls for your organization based on your size, structure, and spending goals.\n- Using custom instructions to unlock the power of Copilot code review Learn how to write effective custom instructions that help GitHub Copilot provide more relevant and actionable code reviews.\n- Use GitHub Copilot code review across the pull request lifecycle Build a repeatable workflow for Copilot code review from draft pull request to merge.\n- Enhancing GitHub Copilot agent mode with MCP Learn how to use the Model Context Protocol (MCP) to expand the agentic capabilities of Copilot Chat.\n- Comparing AI models using different tasks Explore real-world examples of common developer tasks along with sample prompts, responses, and guidance to help you choose the right AI model for your workflow.\n- Speeding up development work with GitHub Copilot Spaces Learn how to use Copilot Spaces to help you with development work.\n- Choosing your enterprise's plan for GitHub Copilot Choose between Copilot Business and Copilot Enterprise.\n- Setting up a self-serve process for GitHub Copilot licenses Learn how users can request a license and receive access immediately.\n- Tracking license activation and initial usage with Copilot usage metrics Identify and act on GitHub Copilot adoption signals and activation with usage metrics.\n- Reminding inactive users to use their GitHub Copilot license Use the GitHub API to identify inactive users and help them get started.\n- Resources for getting approval of GitHub Copilot Get ready to adopt Copilot by sending resources to legal and security teams in your company.\n- Establishing AI managers in your enterprise Reduce your administrative burden and empower your SMEs by creating a team of AI managers.\n- Maintaining codebase standards in a GitHub Copilot rollout Stay in control of your enterprise's code with rulesets, security features, and effective training.\n- Driving GitHub Copilot adoption in your company Learn how to plan an effective enablement process to drive Copilot adoption.\n- Integrating agentic AI into your enterprise's software development lifecycle See how agents can boost productivity across your enterprise.\n- Achieving your company's engineering goals with GitHub Copilot Plan your rollout based on GitHub's recommended approach for driving and measuring improvements.\n- Increasing test coverage in your company with GitHub Copilot Understand features, enable developers, and measure Copilot's impact.\n- Accelerating pull requests in your company with GitHub Copilot Understand features, enable developers, and measure Copilot's impact.\n- Reducing security debt in your company with GitHub Copilot Understand features, enable developers, and measure Copilot's impact.\n- Measure and demonstrate the impact of GitHub Copilot Understanding how Copilot is used across your enterprise is the first step to demonstrating its value. Follow this path to establish a usage baseline, see how code is being generated, and connect adoption to measurable outcomes.\n- Measuring the success of a GitHub Copilot trial Measure the success of a Copilot trial by analyzing adoption, engagement, and early usage patterns using Copilot usage metrics.\n- Using GitHub Copilot to explore a codebase GitHub Copilot Chat can help you gain an understanding of the content, structure, and functionality of a codebase.\n- Using GitHub Copilot to explore issues and discussions GitHub Copilot Chat can help you quickly gain context of lengthy discussions and issues.\n- Using GitHub Copilot to explore pull requests GitHub Copilot Chat can help you understand the content, functionality, and status of a pull request.\n- Writing tests with GitHub Copilot Use Copilot to generate unit and integration tests, and help improve code quality.\n- Refactoring code with GitHub Copilot Leverage Copilot artificial intelligence to help you refactor your code quickly and effectively.\n- Optimizing your AI usage to maximize efficiency and reduce cost Learn how to choose the right models, structure your prompts, and add guardrails so that Copilot completes tasks more efficiently and uses fewer AI credits.\n- Optimize GitHub Copilot Chat context to reduce AI credit usage Keep Copilot Chat responses focused and reduce AI credits usage by knowing when to continue a conversation and when to start a new one.\n- Build an optimized review process with Copilot Automate reviews with Copilot to optimize and improve your review process.\n- Using GitHub Copilot to reduce technical debt Use Copilot to automate refactoring and maintenance tasks, freeing your team to focus on feature development.\n- Review AI-generated code Learn techniques to verify and validate AI-generated code, and how Copilot Chat can help.\n- Learning a new programming language with GitHub Copilot GitHub Copilot Chat can help you extend your programming skills by learning how to code in a new programming language.\n- Modernizing legacy code with GitHub Copilot Copilot Chat helps modernize legacy code by suggesting refactors and creating tests to catch potential issues.\n- Modernizing Java applications with GitHub Copilot GitHub Copilot can help modernize and migrate Java applications by assessing your codebase, identifying upgrade paths, and automating remediation and containerization tasks.\n- Using GitHub Copilot to migrate a project to another programming language GitHub Copilot Chat can help you move a project to a different language. This guide describes what's involved in a migration process and gives an example of a PHP to Python migration.\n- Planning a project with GitHub Copilot Plan your next project by using GitHub Copilot to turn your ideas into issues.\n- Vibe coding with GitHub Copilot Create an application without writing any code yourself.\n- Upgrading projects with GitHub Copilot You can use GitHub Copilot to upgrade your Maven and Gradle Java applications and .NET applications.\n- Using hooks with Copilot CLI for predictable, policy-compliant execution Use hooks to log user prompts and control which tools Copilot CLI can run in a repository, so teams can automate safely within your organization's security and compliance requirements.\n- Using Copilot CLI as your AI SME Use Copilot CLI as an always-available subject matter expert to learn how a codebase works, so you can confidently maintain it or add new features.\n- Creating extensions for GitHub Copilot CLI Build extensions that add your own tools and slash commands to Copilot CLI.\n- Application card: GitHub Copilot Chat Learn how to use GitHub Copilot Chat responsibly by understanding its purposes, capabilities, and limitations.\n- Application card: GitHub Copilot inline suggestions Learn how to use GitHub Copilot inline suggestions responsibly by understanding their purposes, capabilities, and limitations.\n- Application card: GitHub Copilot Agents Learn how to use GitHub Copilot agentic features responsibly by understanding their purposes, capabilities, and limitations."
      },
      {
        "id": "https://docs.github.com/en/copilot/get-started",
        "title": "Get started with GitHub Copilot",
        "url": "https://docs.github.com/en/copilot/get-started",
        "text": "# Get started with GitHub Copilot\n\nLearn how to sign up for and use GitHub Copilot.\n\n## Links\n\n* Quickstart for GitHub Copilot\n\n Quickly learn how to use GitHub Copilot.\n\n* What is GitHub Copilot?\n\n Learn what Copilot is and what you can do with it.\n\n* Plans for GitHub Copilot\n\n Learn about the available plans for Copilot.\n\n* GitHub Copilot features\n\n GitHub Copilot offers a suite of features for users and administrators.\n\n* Best practices for using GitHub Copilot\n\n Learn how to get the most out of Copilot.\n\n* Adopting GitHub Copilot in your enterprise\n\n Adopt the latest GitHub Copilot features without compromising on control and governance."
      },
      {
        "id": "https://docs.github.com/en/copilot/get-started/features",
        "title": "",
        "url": "https://docs.github.com/en/copilot/get-started/features",
        "text": "# GitHub Copilot features\n\nGitHub Copilot offers a suite of features for users and administrators.\n\n## Assistive features\n\nThese tools are used synchronously, providing advice or suggestions as people work on a task.\n\n### Copilot Chat\n\nA chat interface that lets you ask coding-related questions. GitHub Copilot Chat is available on the GitHub website, in GitHub Mobile, in supported IDEs, and in Windows Terminal. Users can also use skills with Copilot Chat. See Asking GitHub Copilot questions in GitHub and Asking GitHub Copilot questions in your IDE.\n\n### Inline suggestions\n\nAutocomplete-style suggestions from Copilot in supported IDEs. See Getting code suggestions in your IDE with GitHub Copilot.\n\nIf you use VS Code, Xcode, or Eclipse, you can also use next edit suggestions, which will predict the location of the next edit you are likely to make and suggest a completion for it.\n\n### Copilot pull request summaries\n\nAI-generated summaries of the changes that were made in a pull request, which files they impact, and what a reviewer should focus on when they conduct their review. See Creating a pull request summary with GitHub Copilot.\n\n### Copilot in GitHub Desktop\n\nAutomatically generate commit messages and descriptions with Copilot in GitHub Desktop based on the changes you make to your project.\n\n## Agentic features\n\nThese features can work autonomously without direct human supervision. However, they typically need human approval to perform sensitive actions, such as running commands in a developer's terminal or merging a pull request.\n\n### Copilot CLI\n\nA command line interface that lets you use Copilot in your terminal. Use the CLI to add features or fix bugs, then create a pull request. Start Copilot working on a task in your terminal, then continue working in the same session on GitHub.com, or on your mobile. See About GitHub Copilot CLI.\n\n### GitHub Copilot app\n\nA desktop application for agent-driven development. From the app, you can run multiple agent sessions in parallel across your repositories, manage issues and pull requests, and set up automations to run tasks on a schedule. See About the GitHub Copilot app.\n\n### Copilot cloud agent\n\nAn autonomous AI agent that can research a repository, create an implementation plan, and make code changes on a branch. You can review the diff, iterate, and create a pull request when you're ready. You can also assign a GitHub issue to Copilot or ask it to open a pull request directly to complete a task. See GitHub Copilot cloud agent.\n\n### Third-party coding agents (public preview)\n\nYou can use third-party coding agents alongside Copilot cloud agent. Third-party agents are subject to the same security protections, mitigations, and limitations as Copilot cloud agent. See About third-party coding agents.\n\n### Copilot code review\n\nAI-generated code review suggestions to help you write better code. See Using GitHub Copilot code review.\n\nSeveral tools in Copilot code review are in public preview and subject to change. See About GitHub Copilot code review.\n\n### Agent mode in IDEs\n\nAllow Copilot to work autonomously in the IDE. Copilot will determine which files to make changes to, offer code changes and terminal commands for the user's approval, and iterate to remediate issues until the original task is complete.\n\n## Features for customization\n\nThese features can be used to add context to Copilot and improve its performance. For a comparison of when to use each feature, see Copilot customization cheat sheet.\n\n### Copilot Spaces\n\nOrganize and centralize relevant content\u2014like code, docs, specs, and more\u2014into Spaces that ground Copilot\u2019s responses in the right context for a specific task. See About GitHub Copilot Spaces.\n\n### Custom instructions\n\nEnhance responses by providing contextual details on your preferences, tools, and requirements. See About customizing GitHub Copilot responses.\n\n### Copilot Memory (public preview)\n\nCopilot can deduce and store useful information about a repository, which Copilot cloud agent and Copilot code review can use to improve the quality of their output when working in that repository. For more information, see About GitHub Copilot Memory.\n\n### Prompt files\n\nBuild and share reusable prompt instructions with additional context. A prompt file is a Markdown file, stored in your workspace, that mimics the existing format of writing prompts. See About customizing GitHub Copilot responses.\n\n### MCP servers\n\nYou can configure Model Context Protocol (MCP) servers for many Copilot features, giving Copilot access to external tools or data sources. See About Model Context Protocol (MCP).\n\n### Agent skills\n\nCreate folders of instructions, scripts, and resources that Copilot can load when relevant to improve its performance in specialized tasks. See About agent skills.\n\n### Custom agents\n\nCreate specialized versions of Copilot cloud agent with access to specific tools, instructions, and MCP servers. See About custom agents.\n\n## Features for administrators\n\nThe following features are available to organization and enterprise owners with a Copilot Business or Copilot Enterprise plan.\n\n### Policy management\n\nManage policies for Copilot in your organization or enterprise. See Managing policies and features for GitHub Copilot in your organization and Managing policies and features for GitHub Copilot in your enterprise.\n\n### Access management\n\nEnterprise owners can specify which organizations in the enterprise can use Copilot, and organization owners can specify which organization members can use Copilot. See Managing access to GitHub Copilot in your organization and Managing access to Copilot in your enterprise.\n\n### Usage data\n\nReview Copilot usage data within your organization or enterprise to inform how to manage access and drive adoption of Copilot. See Reviewing user activity data for GitHub Copilot in your organization and Viewing Copilot license usage in your enterprise.\n\n### Audit logs\n\nReview audit logs for Copilot in your enterprise to understand what actions have been taken and by which users. See Reviewing audit logs for GitHub Copilot.\n\n### File exclusions\n\nConfigure Copilot to ignore certain files. This can be useful if you have files that you don't want to be available to Copilot. See Excluding content from GitHub Copilot.\n\n## Next steps\n\n- To learn more about the plans available for GitHub Copilot, see Plans for GitHub Copilot.\n- To start using Copilot, see Setting up GitHub Copilot."
      },
      {
        "id": "https://docs.github.com/en/copilot/concepts",
        "title": "Concepts for GitHub Copilot",
        "url": "https://docs.github.com/en/copilot/concepts",
        "text": "# Concepts for GitHub Copilot\n\nLearn the core concepts that you'll need to understand GitHub Copilot.\n\n## Links\n\n* Completions for GitHub Copilot\n\n Learn how Copilot can provide inline suggestions.\n\n* About GitHub Copilot Chat\n\n Learn how you can use GitHub Copilot Chat to enhance your coding experience.\n\n* Concepts for GitHub Copilot agents\n\n Learn how GitHub Copilot can independently execute tasks across the software development lifecycle.\n\n* About cloud and local sandboxes for GitHub Copilot\n\n Cloud and local sandboxes provide isolated execution environments that let Copilot safely interact with code, tools, filesystem, and network resources securely on your local machine or in fully isolated cloud environments.\n\n* About GitHub Spark\n\n Learn about building and deploying intelligent apps with natural language using GitHub Spark.\n\n* GitHub Copilot usage metrics\n\n Track how your teams are using and adopting GitHub Copilot with detailed usage metrics.\n\n* Concepts for prompting GitHub Copilot\n\n Learn how to interact with GitHub Copilot to get the best results.\n\n* Concepts for providing context to GitHub Copilot\n\n Learn how GitHub Copilot gathers contextual information to provide relevant responses to your prompts.\n\n* Concepts for AI tools\n\n Learn about different Copilot tools and how they can be used to help develop software.\n\n* Models for GitHub Copilot\n\n Learn about the AI models available for GitHub Copilot.\n\n* Usage limits for GitHub Copilot\n\n Learn about GitHub Copilot usage limits and what to do if you hit a limit.\n\n* GitHub Copilot billing\n\n Understand billing and usage for GitHub Copilot.\n\n* About enterprise accounts for Copilot Business\n\n An enterprise account lets you manage only Copilot Business licenses, without consuming GitHub Enterprise Cloud licenses.\n\n* GitHub Copilot policies for enterprises and organizations\n\n Control the availability of GitHub Copilot features and models for your users.\n\n* MCP server usage in your company\n\n You can manage MCP server usage to provide your developers with valuable tools while maintaining security and compliance.\n\n* Network settings for GitHub Copilot\n\n You can connect to GitHub Copilot through an HTTP proxy and use custom certificates.\n\n* Learning about new features and models\n\n Stay informed about GitHub Copilot features and models, and make confident decisions about enabling them for your enterprise."
      },
      {
        "id": "https://docs.github.com/en/copilot/concepts/agents/copilot-cli/about-copilot-cli",
        "title": "About GitHub Copilot CLI",
        "url": "https://docs.github.com/en/copilot/concepts/agents/copilot-cli/about-copilot-cli",
        "text": "# About GitHub Copilot CLI\n\nFind out about using Copilot from the command line.\n\n## Introduction\n\nThe command-line interface (CLI) for GitHub Copilot allows you to use Copilot directly from your terminal. You can use it to answer questions, write and debug code, and interact with GitHub.com. For example, you can ask Copilot to make some changes to a project and create a pull request.\n\nGitHub Copilot CLI gives you quick access to a powerful AI agent, without having to leave your terminal. It can help you complete tasks more quickly by working on your behalf, and you can work iteratively with GitHub Copilot CLI to build the code you need.\n\n## Supported operating systems\n\n- Linux\n- macOS\n- Windows from within Powershell and Windows Subsystem for Linux (WSL)\n\nFor installation instructions, see Installing GitHub Copilot CLI.\n\n## Modes of use\n\nGitHub Copilot CLI has two user interfaces: interactive and programmatic.\n\n### Interactive interface\n\nTo start an interactive session, enter `copilot`. Within an interactive session, you can have a conversation with Copilot. You can prompt Copilot to perform one or more tasks, and you can give it feedback and steer the direction of the work.\n\nThe interactive interface has two modes. In addition to the default ask/execute mode there is also a plan mode in which Copilot will build a structured implementation plan for a task you want to complete.\n\nPress Shift+Tab to cycle between modes. In plan mode, Copilot analyzes your request, asks clarifying questions to understand scope and requirements, and builds a plan before writing any code. This helps you catch misunderstandings before any code is written, and stay in control of complex, multi-step tasks.\n\n### Programmatic interface\n\nYou can also pass the CLI a single prompt directly on the command line. The CLI completes the task and then exits.\n\nTo use the CLI programmatically, include the `-p` or `--prompt` command-line option in your command. To allow Copilot to modify and execute files you should also use one of the approval options described later in this article\u2014see Allowing tools to be used without manual approval ). For example:\n\n```bash\ncopilot -p \"Show me this week's commits and summarize them\" --allow-tool='shell(git)'\n\n```\n\nAlternatively, you can use a script to output command-line options and pipe this to `copilot`. For example:\n\n```bash\n./script-outputting-options.sh | copilot\n\n```\n\n> [!CAUTION]\n> If you use an automatic approval option such as `--allow-all-tools`, Copilot has the same access as you do to files on your computer, and can run any shell commands that you can run, without getting your prior approval. See Security considerations, later in this article.\n\n## Running Copilot CLI commands in a sandbox\n\n> [!NOTE]\n> Cloud and local sandboxes for GitHub Copilot are in public preview and subject to change.\n\nTo prevent Copilot from modifying files you don't want it to touch, you can force agents to run commands within a local sandboxed environment. Alternatively, you can run an entire CLI session in an isolated environment in the cloud. For more information, see About cloud and local sandboxes for GitHub Copilot.\n\n### Local sandboxing\n\nYou can enable local sandboxing inside a Copilot CLI session to restrict Copilot's access to your filesystem, network, and system capabilities. To enable it, run `/sandbox enable` inside a session.\n\n### Cloud sandboxing\n\nYou can start a Copilot CLI session inside an isolated, cloud-hosted environment with cloud sandboxes. This is useful when you want to run code without affecting your local machine, keep a session's state between uses, continue a session from a different machine, or run multiple tasks in parallel. Cloud sandbox policies inherit from Copilot cloud agent policies, so existing security controls like firewall rules extend to cloud sandboxes without additional setup.\n\nTo start a cloud-backed session, run:\n\n```bash\ncopilot \u2011\u2011cloud\n\n```\n\n## Use cases for GitHub Copilot CLI\n\nThe following sections provide examples of tasks you can complete with GitHub Copilot CLI.\n\n### Local tasks\n\n- From within a project directory you can ask Copilot to make a change to the code in the project. For example:`Change the background-color of H1 headings to dark blue` Copilot finds the CSS file where H1 headings are defined and changes the color value.\n- Ask Copilot to tell you about changes to a file:`Show me the last 5 changes made to the CHANGELOG.md file. Who changed the file, when, and give a brief summary of the changes they made`\n- Use Copilot to help you improve the code, or documentation, in your project.`Suggest improvements to content.js``Rewrite the readme in this project to make it more accessible to newcomers`\n- Use Copilot to help you perform Git operations.`Commit the changes to this repo``Revert the last commit, leaving the changes unstaged`\n- Ask Copilot to create an application from scratch\u2014for example, as a proof of concept.`Use the create-next-app kit and tailwind CSS to create a next.js app. The app should be a dashboard built with data from the GitHub API. It should track this project's build success rate, average build duration, number of failed builds, and automated test pass rate. After creating the app, give me easy to follow instructions on how to build, run, and view the app in my browser.`\n- Ask Copilot to explain why a change it made is not working as expected, or tell Copilot to fix a problem with the last change it made. For example:`You said: \"The application is now running on http://localhost:3002 and is fully functional!\" but when I browse to that URL I get \"This site can't be reached\"`\n\n### Tasks involving GitHub.com\n\n- Fetch and display details about your work from GitHub.com.`List my open PRs` This lists your open pull requests from any repository on GitHub. For more specific results, include the repository name in your prompt:`List all open issues assigned to me in OWNER/REPO`\n- Ask Copilot to work on an issue:`I've been assigned this issue: https://github.com/octo-org/octo-repo/issues/1234. Start working on this for me in a suitably named branch.`\n- Ask Copilot to make file changes and raise a pull request on GitHub.com.`In the root of this repo, add a Node script called user-info.js that outputs information about the user who ran the script. Create a pull request to add this file to the repo on GitHub.``Create a PR that updates the README at https://github.com/octo-org/octo-repo, changing the subheading \"How to run\" to \"Example usage\"` Copilot creates a pull request on GitHub.com, on your behalf. You are marked as the pull request author.\n- Ask Copilot to create an issue for you on GitHub.com.`Raise an improvement issue in octo-org/octo-repo. In src/someapp/somefile.py the `file = open('data.txt', 'r')` block opens a file but never closes it.`\n- Ask Copilot to check the code changes in a pull request.`Check the changes made in PR https://github.com/octo-org/octo-repo/pull/57575. Report any serious errors you find in these changes.` Copilot responds in the CLI with a summary of any problems it finds.\n- Manage pull requests from GitHub Copilot CLI.`Merge all of the open PRs that I've created in octo-org/octo-repo``Close PR #11 on octo-org/octo-repo`\n- Find specific types of issues.`Use the GitHub MCP server to find good first issues for a new team member to work on from octo-org/octo-repo` [!NOTE]\nIf you know that a specific MCP server can achieve a particular task, then specifying it in your prompt can help Copilot to deliver the results you want.\n- Find specific GitHub Actions workflows.`List any Actions workflows in this repo that add comments to PRs`\n- Create a GitHub Actions workflow.`Branch off from main and create a GitHub Actions workflow that will run on pull requests, or can be run manually. The workflow should run eslint to check for problems in the changes made in the PR. If warnings or errors are found these should be shown as messages in the diff view of the PR. I want to prevent code with errors from being merged into main so, if any errors are found, the workflow should cause the PR check to fail. Push the new branch and create a pull request.`\n\n## Steering the conversation\n\nYou can interact with Copilot while it's thinking to steer the conversation:\n\n- Enqueue additional messages: Send follow-up messages to steer the conversation in a different direction, or queue additional instructions for Copilot to process after it finishes its current response. This makes conversations feel more natural and keeps you in control.\n- Inline feedback on rejection: When you reject a tool permission request, you can give Copilot inline feedback about the rejection so it can adapt its approach without stopping entirely. This makes the conversation flow more naturally when you want to guide Copilot away from certain actions.\n\n## Automatic context management\n\nGitHub Copilot CLI automatically manages your conversation context:\n\n- Auto-compaction: When your conversation approaches 95% of the token limit, Copilot automatically compresses your history in the background without interrupting your workflow. This enables virtually infinite sessions.\n- Manual control: Use `/compact` to manually compress context anytime. Press Esc to cancel if you change your mind.\n- Visualize usage: The `/context` command shows a detailed token usage breakdown so you can understand how your context window is being used.\n\n## Customizing GitHub Copilot CLI\n\nYou can customize GitHub Copilot CLI in a number of ways:\n\n- Custom instructions: Custom instructions allow you to give Copilot additional context on your project and how to build, test and validate its changes. All custom instruction files now combine instead of using priority-based fallbacks. For more information, see Adding custom instructions for GitHub Copilot CLI.\n- Model Context Protocol (MCP) servers: MCP servers allow you to give Copilot access to different data sources and tools. For more information, see Using GitHub Copilot CLI.\n- Custom agents: Custom agents allow you to create different specialized versions of Copilot for different tasks. For example, you could customize Copilot to be an expert frontend engineer following your team's guidelines. GitHub Copilot CLI includes specialized custom agents that it automatically delegates common tasks to. For more information, see Using GitHub Copilot CLI.\n- Hooks: Hooks allow you to execute custom shell commands at key points during agent execution, enabling you to add validation, logging, security scanning, or workflow automation. See About hooks for GitHub Copilot.\n- Skills: Skills allow you to enhance the ability of Copilot to perform specialized tasks with instructions, scripts, and resources. For more information, see About agent skills.\n- Copilot Memory: Copilot Memory allows Copilot to build a persistent understanding of your repository by storing \"memories\", which are pieces of information about coding conventions, patterns, and preferences that Copilot deduces as it works. This reduces the need to repeatedly explain context in your prompts and makes future sessions more productive. For more information, see About GitHub Copilot Memory.\n\n## Security considerations\n\nWhen you use Copilot CLI, Copilot can perform tasks on your behalf, such as executing or modifying files, or running shell commands.\n\nYou should therefore always keep security considerations in mind when using Copilot CLI, just as you would when working directly with files yourself, or running commands directly in your terminal. You should always review suggested commands carefully when Copilot CLI requests your approval.\n\n### Content exclusion\n\nFor Copilot Business and Copilot Enterprise users, Copilot CLI respects content exclusion policies configured at the enterprise, organization, and repository levels. Excluded files are not used as context. For more information, see Content exclusion for GitHub Copilot.\n\n### Trusted directories\n\nTrusted directories control where Copilot CLI can read, modify, and execute files.\n\nYou should only launch Copilot CLI from directories that you trust. You should not use Copilot CLI in directories that may contain executable files you can't be sure you trust. Similarly, if you launch the CLI from a directory that contains sensitive or confidential data, or files that you don't want to be changed, you could inadvertently expose those files to risk. Typically, you should not launch Copilot CLI from your home directory.\n\nScoping of permissions is heuristic and GitHub does not guarantee that all files outside trusted directories will be protected. See Risk mitigation.\n\nWhen you start a GitHub Copilot CLI session, you'll be asked to confirm that you trust the files in, and below, the directory from which you launched the CLI. See Configuring GitHub Copilot CLI.\n\n### Allowed tools\n\nThe first time that Copilot needs to use a tool that could be used to modify or execute a file\u2014for example, `touch`, `chmod`, `node`, or `sed`\u2014it will ask you whether you want to allow it to use that tool.\n\nTypically, you can choose from three options:\n\n```text\n1. Yes\n2. Yes, and approve TOOL for the rest of the running session\n3. No, and tell Copilot what to do differently (Esc)\n\n```\n\nOption 1 allows Copilot to run this particular command, this time only. The next time it needs to use this tool, it will ask you again.\n\nOption 2 allows Copilot to use this tool again, without asking you for permission, for the duration of the currently running session. It will ask for your approval again in new sessions, or if you resume the current session in the future. If you choose this option, you are allowing Copilot to use this tool in any way it thinks is appropriate. For example, if Copilot asks you to allow it to run the command `rm ./this-file.txt`, and you choose option 2, then Copilot can run any `rm` command (for example, `rm -rf ./*`) during the current run of this session, without asking for your approval.\n\nOption 3 cancels the proposed command and allows you to tell Copilot to try a different approach.\n\n#### Allowing tools to be used without manual approval\n\nThere are three command-line options that you can use, in either interactive or programmatic sessions, to determine tools that Copilot can use without asking for your approval:\n\n- `--allow-all-tools` Allows Copilot to use any tool without asking for your approval. For example, you can use this option with a programmatic invocation of the CLI to allow Copilot to run any command. For example:\n\n```shell\ncopilot -p \"Revert the last commit\" --allow-all-tools\n\n```\n\n- `--deny-tool` Prevents Copilot from using a specific tool. This option takes precedence over the `--allow-all-tools` and `--allow-tool` options.\n- `--allow-tool` Allows Copilot to use a specific tool without asking for your approval.\n\n#### Using the approval options\n\nThe `--deny-tool` and `--allow-tool` options require one of the following arguments:\n\n- `'shell(COMMAND)'` For example, `copilot --deny-tool='shell(rm)'` prevents Copilot from using any `rm` command. For `git` and `gh` commands, you can specify a particular first-level subcommand to allow or deny. For example:\n\n```shell\ncopilot --deny-tool='shell(git push)'\n\n```\n\nThe tool specification is optional. For example, `copilot --allow-tool='shell'` allows Copilot to use any shell command without individual approval.\n\n- `'write'` This argument allows or denies tools\u2014other than shell commands\u2014permission to modify files. For example, `copilot --allow-tool='write'` allows Copilot to edit files without your individual approval.\n- `'MCP_SERVER_NAME'` This argument allows or denies tools from the specified MCP server, where `MCP_SERVER_NAME` is the name of an MCP server that you have configured. Tools from the server are specified in parentheses, using the tool name that is registered with the MCP server. Using the server name without specifying a tool allows or denies all tools from that server. For example, `copilot --deny-tool='My-MCP-Server(tool_name)'` prevents Copilot from using the tool called `tool_name` from the MCP server called `My-MCP-Server`. You can find an MCP server's name by entering `/mcp` in the CLI's interactive interface, then selecting the server from the list that's displayed.\n\n#### Combining approval options\n\nYou can use a combination of approval options to determine exactly which tools Copilot can use without asking for your approval.\n\nFor example, to prevent Copilot from using the `rm` and `git push` commands, but automatically allow all other tools, use:\n\n```shell\ncopilot --allow-all-tools --deny-tool='shell(rm)' --deny-tool='shell(git push)'\n\n```\n\nTo prevent Copilot from using the tool `tool_name` from the MCP server named `My-MCP-Server`, but allow all other tools from that server to be used without individual approval, use:\n\n```shell\ncopilot --allow-tool='My-MCP-Server' --deny-tool='My-MCP-Server(tool_name)'\n\n```\n\n#### Security implications of automatic tool approval\n\nIt's important to be aware of the security implications of using the approval command-line options. These options allow Copilot to execute commands needed to complete your request, without giving you the opportunity to review and approve those commands before they are run. While this streamlines workflows, and allows headless operation of the CLI, it increases the risk of unintended actions being taken that might result in data loss or corruption, or other security issues.\n\nYou can control which tools Copilot CLI can use by responding to approval prompts when Copilot attempts to use a tool, by specifying permissions with command-line flags, or (in an interactive session) by using slash commands (such as `/allow-all` and `/yolo`. See Configuring GitHub Copilot CLI.\n\n### Risk mitigation\n\nYou can mitigate the risks associated with using the automatic approval options by running Copilot CLI in a sandboxed environment. GitHub provides first-party sandboxing for this, with local sandboxing to restrict access on your machine and cloud sandboxing for fully isolated execution. For more information, see About cloud and local sandboxes for GitHub Copilot.\n\nAlternatively, you can run Copilot CLI in a virtual machine, container, or dedicated system with tightly controlled permissions and network access.\n\n### Known MCP server policy limitations\n\nCopilot CLI can't currently support the following organization-level MCP server policies:\n\n- MCP servers in Copilot, which controls whether MCP servers can be used at all by Copilot.\n- MCP Registry URL, which controls which MCP registry Copilot will allow MCP servers to be used from.\n\nFor more information about these policies, see MCP server usage in your company.\n\n## Model usage\n\nYou can change the model used by GitHub Copilot CLI by using the `/model` slash command or the `--model` command-line option. Enter this command, then select a model from the list.\n\nEach time you interact with Copilot in Copilot CLI's interactive interface, or use Copilot CLI programmatically, AI credits are consumed based on the number of tokens processed. The amount consumed per interaction varies depending on the model used. See Models and pricing for GitHub Copilot.\n\n### Models with extended capabilities\n\nThe latest models support a 1 million token context window, so you can work across larger codebases, longer documents, and complex multi-file projects without losing context. After you select a supported model, you will be prompted to choose between the default context size or an extended (1 million token) context.\n\nIn addition, these models also support configurable reasoning levels, which control the depth of the model's reasoning process before it generates a response.\n\nChoosing a larger context window or higher reasoning will impact AI credits consumption; more tokens will be consumed, so more credits will be used. For this reason, we recommend that you use the regular context window and regular reasoning by default, selecting the larger context window and higher reasoning for more complex tasks only.\n\nFor a list of models that support these capabilities, see Models with extended capabilities.\n\n### Using your own model provider\n\nYou can configure Copilot CLI to use your own model provider instead of GitHub-hosted models. This lets you connect to an OpenAI-compatible endpoint, Azure OpenAI, or Anthropic, including locally running models such as Ollama. You configure your model provider using environment variables.\n\n| Environment variable | Description |\n| --- | --- |\n| `COPILOT_PROVIDER_BASE_URL` | The base URL of your model provider's API endpoint. |\n| `COPILOT_PROVIDER_TYPE` | The provider type: `openai` (default), `azure`, or `anthropic`. The `openai` type works with any OpenAI-compatible endpoint, including Ollama and vLLM. |\n| `COPILOT_PROVIDER_API_KEY` | Your API key for authenticating with the provider. Not required for providers that don't use authentication, such as a local Ollama instance. |\n| `COPILOT_MODEL` | The model to use (required when using a custom provider). You can also set this with the `--model` command-line option. |\n\nModels used with Copilot CLI must support tool calling (function calling) and streaming. If the model does not support these capabilities, Copilot CLI will return an error. For best results, the model should have a context window of at least 128k tokens.\n\nFor details on how to configure your model provider, run `copilot help providers` in your terminal.\n\n## Use Copilot CLI via ACP\n\nACP (the Agent Client Protocol) is an open standard for interacting with AI agents. It allows you to use Copilot CLI as an agent in any third-party tools, IDEs, or automation systems that support this protocol.\n\nFor more information, see Copilot CLI ACP server.\n\n## Feedback\n\nIf you have any feedback about GitHub Copilot CLI, please let us know by using the `/feedback` slash command in an interactive session and choosing one of the options. You can complete a private feedback survey, submit a bug report, or suggest a new feature.\n\n## Further reading\n\n- Installing GitHub Copilot CLI\n- Using GitHub Copilot CLI\n- Application card: GitHub Copilot Agents",
        "image": "https://docs.github.com/assets/images/help/copilot/copilot-cli-welcome.png"
      }
    ],
    "searchTime": 4581.9,
    "costDollars": {
      "total": 0.007,
      "search": {
        "neural": 0.007
      }
    }
  }
}