GitHub Copilot

The cloud agent works natively across GitHub issues, pull requests and Actions, takes tasks from Slack, Teams, Jira, Linear and Azure Boards, and reaches further tools and data through MCP servers, with the GitHub and Playwright MCP servers on by default and enterprise policy restricting MCP servers.

Sourcedocs.github.com about-coding-agent and concepts/agents/enterprise-managementread 2026-09-29

The cloud agent researches, plans and changes code on a branch in its own environment, custom agents configured with tailored prompts, tools and context handle specialized tasks at enterprise, organization and repository level, and third party coding agents (Claude, Codex) run alongside it under the same protections.

Sourcedocs.github.com about-coding-agent and concepts/agents/enterprise-managementread 2026-09-29

Each repository gets a semantic code search index that is kept current automatically, typically updated within seconds of a new conversation, and used by Copilot Chat on GitHub and in VS Code and by the cloud agent, a maintained retrieval structure over the customer's code; MCP extends grounding to outside data and content exclusions bound what may be read.

Sourcedocs.github.com concepts/context/repository-indexingread 2026-09-29

The cloud agent works on a branch and a person reviews the diff, iterates and decides when to create the pull request, which then passes GitHub's own branch protection and review controls; managed settings files control agent command authorization across Copilot clients, and enterprise policy decides where the agent may run at all.

Sourcedocs.github.com about-coding-agent and concepts/agents/enterprise-managementread 2026-09-29

Enterprises set four agent policy states, including enabled for dynamic groups of organizations, manage custom agents at enterprise level through AI Controls or REST endpoints, restrict MCP servers and control plugin installs through managed settings; GitHub Copilot Business and Enterprise are covered by SOC 2 Type II reports available on the GitHub Enterprise Trust Center (github.blog changelog, December 2024).

Sourcedocs.github.com concepts/agents/enterprise-management and github.blog/changelogread 2026-09-29

The enterprise audit log records agent actions such as pull_request.create with actor_is_agent, the agent_session_id and the initiating user, filterable with actor:Copilot over 180 days and streamable to external destinations (public preview), and AI Controls lists and filters agent sessions across the enterprise. The limit: GitHub states the audit log does not include client session data, so prompts sent locally are not captured and a custom hook is needed to log CLI events.

Sourcedocs.github.com agentic-audit-log-events and concepts/agents/enterprise-managementread 2026-09-29

Copilot Memory stores repository facts and user preferences that Copilot writes from users' work, scoped to the repository or the user, validated against the current branch before use, deleted after 28 days unused, and reviewable and deletable by repository owners and by organization or enterprise admins; the cloud agent, code review, the CLI and agentic autofix use it. Copilot Memory is in public preview on all paid plans.

Sourcedocs.github.com concepts/agents/copilot-memoryread 2026-09-29

Copilot with data residency is offered in the United States and the European Union: requests route to model endpoints in the enterprise's region, code, prompts and responses stay in region during inference, and Copilot logs and telemetry are stored in region.

Sourcedocs.github.com github-copilot-with-data-residencyread 2026-09-29

Copilot ships separately adoptable agents that each do their own job, the cloud agent, Copilot code review, agentic autofix and the Copilot CLI, and third party coding agents from Anthropic and OpenAI (Claude, Codex) can be used alongside it in public preview; custom agents, skills and hooks let teams add their own.

Sourcedocs.github.com concepts/agents/copilot-memory, about-coding-agent and concepts/agents/enterprise-managementread 2026-09-29

An automation runs the cloud agent on a schedule or in response to events such as an issue being opened, with no person starting it; beyond that the agent is assigned issues, answers @copilot mentions in pull requests and takes tasks from Slack, Teams, Jira, Linear, Azure Boards, the agents panel and VS Code.

Sourcedocs.github.com about-coding-agentread 2026-09-29

Paid users select among models from OpenAI, Anthropic, Google, xAI, Moonshot AI and Microsoft, with an optional one million token context, or use auto model selection, and Business and Enterprise admins decide by policy which models are enabled; Free and Student plans get auto selection only.

Sourcedocs.github.com reference/ai-models/supported-modelsread 2026-09-29

The Copilot SDK exposes the agent loop, custom agents and cloud and remote sessions with server to server tokens, and REST endpoints manage custom agents at enterprise level, beside MCP and the CLI.

Sourcedocs.github.com get-started/features and concepts/agents/enterprise-managementread 2026-09-29

The cloud agent runs the project's tests, code review checks the customer's changes, admins can pilot a feature or model with a group of users, and agent sessions support troubleshooting. These test the customer's code or trial adoption, and no harness, scored test set or optimization loop for evaluating the agent's behavior is documented.

Sourcedocs.github.com get-started/features and about-coding-agentread 2026-09-29

The Playwright MCP server is enabled by default for the cloud agent, so the agent drives a browser in its own environment to open, interact with and screenshot the web app it is building, a browser the platform ships and runs with no separate account. The limit: the docs page states the default rather than walking through the browser steps.

Sourcedocs.github.com about-coding-agentread 2026-09-29