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.

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.

← All research

More research.

GitHub's Copilot metrics now flag developers whose usage data is missing

GitHub's 5 November 2026 changelog adds fields to the Copilot usage metrics API showing which users send no telemetry or run outdated editors. AI coding tool reporting now admits its own blind spots.

Read ›

Claude Code 2.1.323 adds experimental Code Mode and plugin version ranges

Claude Code 2.1.323 adds an opt-in Code Mode where Claude writes JavaScript to call its tools, and lets plugins declare which Claude Code versions they support. Claude Code teams get more control over extensions.

Read ›

GitHub Apps can now manage enterprise Copilot seats through the API

GitHub's 10 November 2026 changelog lets enterprise GitHub Apps assign and remove Copilot seats through a new permission. Seat management for AI coding tools can now be automated.

Read ›

GitHub will switch off Dependabot alerts on year-old inactive repositories from 8 December

From 8 December 2026, GitHub will turn off Dependabot alerts on most repositories with no activity in the past year. If you own software that is stable but unmaintained, your security alerts go quiet.

Read ›

Gemini 4 Carbon arrives in GitHub Copilot, and it can switch itself on for your whole organisation

GitHub made Gemini 4 Carbon generally available in Copilot on 10 November 2026 across ten clients. Under default model enablement, Business and Enterprise organisations get new models automatically unless an admin opts out.

Read ›

Claude Code 2.1.322 adds fast mode on Google Vertex, with a quiet fallback to standard speed

Claude Code 2.1.322, released 10 November 2026, adds fast mode on Vertex in the global, US and EU regions. If Vertex refuses it, Claude Code falls back to standard speed.

Read ›

Start a project

Building with AI? Let's talk.

Tell us what you are building. We'll give you an honest view of the right approach.

Start a projectSee our work