Copilot code review adds adaptive effort and secret detection in public preview

GitHub's Copilot code review can now choose Lite, Balanced or Max effort per pull request and flag exposed secrets, both in public preview. Azure DevOps support is generally available.

On 17 November 2026 GitHub updated Copilot code review with several changes. Two matter most to anyone paying for software built with AI help.

Adaptive review effort (public preview). Copilot assesses each pull request’s complexity and risk, then reviews it at Lite, Balanced or Max effort and shows which level it chose. Balanced stays the default. Adaptive never exceeds the maximum effort set for the enterprise, organisation or repository.

Secret detection (public preview). Copilot flags exposed secrets, such as keys and passwords, in review comments before code is merged. GitHub says it matches over 500 known secret types from more than 150 partners, and uses AI models to catch secrets with no recognisable pattern. It is switched on in repository or organisation settings.

Also announced

The preview features are on Copilot Pro, Pro+, Max, Business and Enterprise, and GitHub notes preview features may change.

Why it matters

AI now writes a growing share of code, so the bottleneck is checking it. Leaked credentials are one of the most expensive mistakes a young product can make, and automated checks are becoming a normal part of the pipeline. Effort levels also mean review has a cost dial: more thorough means more spend.

So what

Ask any development partner what automated review and secret scanning run on your code, and who reads what they flag. Our AI-assisted development process pairs automated checks with human review. For bespoke builds, see custom software development.

← All research

More research.

MAI Code 2 and MAI Code 2 Flash arrive in GitHub Copilot, including a model for free-plan users

GitHub has added Microsoft's MAI Code 2 and MAI Code 2 Flash to Copilot across editors, the CLI, the cloud agent and mobile, with administrators able to control access through model policy.

Read ›

GitHub Copilot team customizations are generally available: set default agent plugins for a whole team

GitHub has made team customizations generally available, so team maintainers and organisation owners can set approved Copilot agent plugins as defaults for every member of a team.

Read ›

Claude Code 2.1.330: scheduled tasks run for 30 days, risky rm commands ask first, and enterprise sign-in arrives

Claude Code 2.1.330 extends scheduled tasks and /loop from 7 to 30 days, makes more destructive rm commands ask for approval, and adds sign-in for organisations managed in Anthropic's Enterprise Admin Console.

Read ›

OpenAI's GPT-6.2 Astra and Sol are generally available in GitHub Copilot, with a code review focus

GitHub made OpenAI's GPT-6.2 Astra and GPT-6.2 Sol generally available in Copilot for agentic coding and code review. GitHub reports early tests catching more real issues.

Read ›

Claude Code 2.1.329: /code-review now covers the whole branch, and saved scheduled tasks need rescheduling

Claude Code 2.1.329 makes /code-review review the whole branch against the default branch and adds fixes for Code Mode and sign-in. Saved scheduled tasks mostly need setting up again.

Read ›

GitHub Copilot adds Supabase, Webflow, Wix and five more connectors in public preview

GitHub Copilot now connects to eight more services, including Supabase, Webflow, Wix and Mixpanel, through verified MCP connectors in public preview. They join more than 25 existing ones.

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