GitHub Copilot's code review tool just went GA — AI reviewing AI is now the default workflow
GitHub made Copilot code review generally available on 18 September 2026, adding auto-resolution that closes out comments once they're addressed and groups findings into open versus resolved — a direct answer to the 'who reviews the AI-generated code' question buyers are increasingly searching for.
22 September 2026
GitHub took Copilot code review out of preview and into general availability on 18 September 2026. The headline feature is auto-resolution: Copilot now tracks whether its own review comments were actually addressed between passes, automatically closing out fixed issues and leaving only genuinely outstanding feedback open, sorted into “open issues” and “resolved since last review.” It also generates commit messages automatically when you accept a batch of its suggestions.
This lands one week after Sonar’s 2026 State of Code Developer Survey put a number on the problem it’s solving: AI now writes 42% of committed code, but 38% of developers say reviewing AI-generated code takes more effort than reviewing a human colleague’s — see our earlier signal on that finding. GitHub’s move is a direct product answer to that exact gap: if AI is generating a growing share of the code, the reasonable next step is AI doing a first pass on reviewing it too, rather than leaving human reviewers to absorb all of the extra volume.
Why this matters for anyone commissioning software
Automated first-pass review is a genuine productivity gain, but it changes what “code has been reviewed” means in a way that’s easy to gloss over in a project pitch. A PR that Copilot has reviewed and auto-resolved comments on is not the same guarantee as a PR a senior engineer has actually read. The tooling reduces noise and catches a real class of issues, but it doesn’t replace judgment about architecture, business logic correctness, or whether the code does the right thing rather than just clean-looking things.
So what
If a development partner tells you their review process includes AI code review tooling, that’s a good sign — it’s the direction the whole industry is moving. But it’s worth asking the follow-up: what does human review still cover, and where does the AI’s judgment end? That’s the balance we build into how we structure AI-assisted development engagements — automated tooling for the volume, human accountability for the decisions that actually matter. Get in touch if you want a project scoped with that balance built in from the start.