GitHub Agentic Workflows

Imagine a world where improvements to your repositories are automatically delivered as pull requests each morning, ready for you to review. Issues are automatically triaged, CI failures analyzed, documentation maintained, test coverage improved and compliance monitored - all defined via simple markdown files.

GitHub Agentic Workflows deliver this: repository automation, running the coding agents you know and love, in GitHub Actions, with strong guardrails and security-first design principles.

Use GitHub Copilot, Claude by Anthropic or OpenAI Codex for event-triggered, recurring and scheduled jobs to improve, document and analyze your repository. GitHub Agentic Workflows are designed to augment your existing, deterministic CI/CD with Continuous AI capabilities

GitHub Agentic Workflows has been developed by GitHub Next and Microsoft Research with guardrails in mind. Agentic workflows run with minimal permissions by default, with explicit allowlisting for write operations and sandboxed execution to help keep your repository safe.

Workflows run with read-only permissions by default. Write operations require explicit approval through sanitized safe outputs (pre-approved GitHub operations), with sandboxed execution, tool allowlisting, and network isolation ensuring AI agents operate within controlled boundaries.

How they work:

1. Write - Create a .md file with your automation instructions in natural language
2. Compile - Run gh aw compile to transform it into a GitHub Actions workflow with guardrails (.lock.yml)
3. Run - GitHub Actions executes your workflow automatically based on your triggers

Here’s a simple workflow that runs daily to create an upbeat status report:

---
on:
 schedule: daily
permissions:
 contents: read
 issues: read
 pull-requests: read
safe-outputs:
 create-issue:
 title-prefix: "[team-status] "
 labels: [report, daily-status]
 close-older-issues: true
---
## Daily Issues Report
Create an upbeat daily status report for the team as a GitHub issue.

The gh aw cli converts this into a GitHub Actions Workflow (.yml) that runs an AI agent (Copilot, Claude, Codex, …) in a containerized environment on a schedule or manually.

The AI coding agent reads your repository context, analyzes issues, generates visualizations, and creates reports - all defined in natural language rather than complex code.

Install the extension, add a sample workflow, and trigger your first run - all from the command line in minutes.

Create custom agentic workflows directly from the GitHub web interface using natural language.