GitHub Copilot Code Review

Full Guide

GitHub Copilot Code Review is a product or capability from GitHub documented by first-party sources. GitHub updated Copilot code review on June 25, 2026 with organization defaults and visible attribution for the Medium review-effort preview, plus a new file-exploration path built on Copilot CLI and SDK tools.

What it does

Organizations can set a default review effort for repositories that do not have their own configuration, and Medium runs are identified in the pull-request overview. Behind the scenes, Copilot code review now uses built-in grep, rg, glob, and view tools from the CLI and SDK instead of custom file-exploration tools.

Availability and pricing

Medium review effort remains a public preview for eligible Copilot users. GitHub reports that the new file-tool path reduced Copilot code review costs by about 20 percent while maintaining its standard review quality in GitHub’s offline and online evaluations; this is a vendor-reported result, not an independent Kingy benchmark. Current plan eligibility and usage charges should be confirmed with GitHub.

Who it is for

Developers, engineering teams, security teams, and enterprise platform administrators configuring AI-assisted pull-request review.

What teams should review

Medium effort is still a preview, GitHub’s cost result is vendor-reported, and teams must measure finding quality, false positives, Actions usage, AI credit consumption, and repository-specific policy fit themselves.

Official sources

• Official announcement
• Product or documentation page
• Pricing or plan information