6000 万次 Copilot 代码审查及持续增长

60 million Copilot code reviews and counting - The GitHub Blog Skip to content Skip to sidebar / Blog Changelog Docs Customer stories Try GitHub Copilot See what's new AI & ML AI & ML Learn about artificial intelligence and machine learning across the GitHub ecosystem and the wider industry. Generative AI Learn how to build with generative AI. GitHub Copilot Change how you work with GitHub Copilot. LLMs Everything developers need to know about LLMs. Machine learning Machine learning tips, tricks, and best practices. How AI code generation works Explore the capabilities and benefits of AI code generation and how it can improve your developer experience. Learn more Developer skills Developer skills Resources for developers to grow in their skills and careers. Application development Insights and best practices for building apps. Career growth Tips & tricks to grow as a professional developer. GitHub Improve how you use GitHub at work. GitHub Education Learn how to move into your first professional role. Programming languages & frameworks Stay current on what's new (or new again). Get started with GitHub documentation Learn how to start building, shipping, and maintaining software with GitHub. Learn more Engineering Engineering Get an inside look at how we're building the home for all developers. Architecture & optimization Discover how we deliver a performant and highly available experience across the GitHub platform. Engineering principles Explore best practices for building software at scale with a majority remote team. Infrastructure Get a glimpse at the technology underlying the world's leading AI-powered developer platform. Platform security Learn how we build security into everything we do across the developer lifecycle. User experience Find out what goes into making GitHub the home for all developers. How we use GitHub to be more productive, collaborative, and secure Our engineering and security teams do some incredible work. Let's take a look at how we use GitHub to be more productive, build collaboratively, and shift security left. Learn more Enterprise software Enterprise software Explore how to write, build, and deploy enterprise software at scale. Automation Automating your way to faster and more secure ships. CI/CD Guides on continuous integration and delivery. Collaboration Tips, tools, and tricks to improve developer collaboration. DevOps DevOps resources for enterprise engineering teams. DevSecOps How to integrate security into the SDLC. Governance & compliance Ensuring your builds stay clean. GitHub recognized as a Leader in the Gartner® Magic Quadrant™ for AI Code Assistants Learn why Gartner positioned GitHub as a Leader for the second year in a row. Learn more News & insights News & insights Keep up with what's new and notable from inside GitHub. Company news An inside look at news and product updates from GitHub. Product The latest on GitHub's platform, products, and tools. Octoverse Insights into the state of open source on GitHub. Policy The latest policy and regulatory changes in software. Research Data-driven insights around the developer ecosystem. The library Older news and updates from GitHub. Unlocking the power of unstructured data with RAG Learn how to use retrieval-augmented generation (RAG) to capture more insights. Learn more Open Source Open Source Everything open source on GitHub. Git The latest Git updates. Maintainers Spotlighting open source maintainers. Social impact How open source is driving positive change. Gaming Explore open source games on GitHub. An introduction to innersource Organizations worldwide are incorporating open source methodologies into the way they build and ship their own software. Learn more Security Security Stay up to date on everything security. Application security Application security, explained. Supply chain security Demystifying supply chain security. Vulnerability research Updates from the GitHub Security Lab. Web application security Helpful tips on securing web applications. The enterprise guide to AI-powered DevSecOps Learn about core challenges in DevSecOps, and how you can start addressing them with AI and automation. Learn more Search Categories AI & ML Back AI & ML Learn about artificial intelligence and machine learning across the GitHub ecosystem and the wider industry. Generative AI Learn how to build with generative AI. GitHub Copilot Change how you work with GitHub Copilot. LLMs Everything developers need to know about LLMs. Machine learning Machine learning tips, tricks, and best practices. How AI code generation works Explore the capabilities and benefits of AI code generation and how it can improve your developer experience. Learn more Developer skills Back Developer skills Resources for developers to grow in their skills and careers. Application development Insights and best practices for building apps. Career growth Tips & tricks to grow as a professional developer. GitHub Improve how you use GitHub at work. GitHub Education Learn how to move into your first professional role. Programming languages & frameworks Stay current on what's new (or new again). Get started with GitHub documentation Learn how to start building, shipping, and maintaining software with GitHub. Learn more Engineering Back Engineering Get an inside look at how we're building the home for all developers. Architecture & optimization Discover how we deliver a performant and highly available experience across the GitHub platform. Engineering principles Explore best practices for building software at scale with a majority remote team. Infrastructure Get a glimpse at the technology underlying the world's leading AI-powered developer platform. Platform security Learn how we build security into everything we do across the developer lifecycle. User experience Find out what goes into making GitHub the home for all developers. How we use GitHub to be more productive, collaborative, and secure Our engineering and security teams do some incredible work. Let's take a look at how we use GitHub to be more productive, build collaboratively, and shift security left. Learn more Enterprise software Back Enterprise software Explore how to write, build, and deploy enterprise software at scale. Automation Automating your way to faster and more secure ships. CI/CD Guides on continuous integration and delivery. Collaboration Tips, tools, and tricks to improve developer collaboration. DevOps DevOps resources for enterprise engineering teams. DevSecOps How to integrate security into the SDLC. Governance & compliance Ensuring your builds stay clean. GitHub recognized as a Leader in the Gartner® Magic Quadrant™ for AI Code Assistants Learn why Gartner positioned GitHub as a Leader for the second year in a row. Learn more News & insights Back News & insights Keep up with what's new and notable from inside GitHub. Company news An inside look at news and product updates from GitHub. Product The latest on GitHub's platform, products, and tools. Octoverse Insights into the state of open source on GitHub. Policy The latest policy and regulatory changes in software. Research Data-driven insights around the developer ecosystem. The library Older news and updates from GitHub. Unlocking the power of unstructured data with RAG Learn how to use retrieval-augmented generation (RAG) to capture more insights. Learn more Open Source Back Open Source Everything open source on GitHub. Git The latest Git updates. Maintainers Spotlighting open source maintainers. Social impact How open source is driving positive change. Gaming Explore open source games on GitHub. An introduction to innersource Organizations worldwide are incorporating open source methodologies into the way they build and ship their own software. Learn more Security Back Security Stay up to date on everything security. Application security Application security, explained. Supply chain security Demystifying supply chain security. Vulnerability research Updates from the GitHub Security Lab. Web application security Helpful tips on securing web applications. The enterprise guide to AI-powered DevSecOps Learn about core challenges in DevSecOps, and how you can start addressing them with AI and automation. Learn more Changelog Docs Customer stories See what's new Try GitHub Copilot Home / AI & ML / GitHub Copilot 60 million Copilot code reviews and counting How Copilot code review helps teams keep up with AI-accelerated code changes. Ria Gopu & David Apirian March 5, 2026 | 6 minutes Share: Since our initial launch of Copilot code review (CCR) last April, usage has grown 10X, now accounting for more than one in five code reviews on GitHub. Behind the scenes, we've been running continuous experiments to enhance comment quality. We also moved to an agentic architecture that retrieves repository context and reasons across changes. At every step of the way, we've listened to your feedback: your survey answers and even your simple thumbs-up and thumbs-down reactions on comments have helped us identify key issues and iterate on our UX to provide a comprehensive review experience. Copilot code review handles pull request reviews and summaries, allowing teams to focus on more complex tasks. Suvarna Rane, Software Development Manager, General Motors Redefining a "good" code review As Copilot code review evolved over time, so has our definition of a "good code review." When we started building it in 2024, our goal was simple thoroughness. Since then, we've learned that what developers actually value is high-signal feedback that helps them move a pull request forward quickly. Today, Copilot code review leverages the best models, memory, and agentic tool-calling to conduct comprehensive reviews. To get here, we've used a continuous evaluation loop to tune the agent's judgment, focusing on three qualities that shape that experience: accuracy, signal, and speed. Accuracy Our aim has been for Copilot code review to deliver sound judgment, prioritizing consequential logic and maintainability issues. We evaluate performance in two ways: through internal testing against known code issues, and through production signals from real pull requests. In production, we track two key indicators: Developer feedback : Thumbs-up and thumbs-down reactions on comments help us understand whether suggestions are helpful. Production signals : We measure whether flagged issues are resolved before merging. Together, these signals help ensure that Copilot code review surfaces issues that matter, and that faster merges come from confident fixes, not less scrutiny. Signal In code review, more comments don't necessarily mean a better review. Our goal isn't to maximize comment volume, but to surface issues that actually matter. A high-signal comment helps a developer understand both the problem and the fix: Silence is better than noise. In 71% of the reviews, Copilot code review surfaces actionable feedback. In the remaining 29%, the agent says nothing at all. As our ability to identify high-signal findings improves, we're also able to comment more confidently, now averaging about 5.1 comments per review without increasing review churn or lowering our quality threshold. Speed In code review, speed matters, but signal matters more. Copilot code review is designed to provide a reliable first pass shortly after a pull request is opened. That being said, meaningful reviews still require analysis. As reasoning capabilities improve, so does the computation required to surface deeper issues. We treat this as a deliberate trade-off. In one recent change, adopting a more advanced reasoning model improved positive feedback rates by 6%, even though review latency increased by 16%. For us, that's the right exchange. A slightly slower review that surfaces real issues is far more valuable than instant feedback that adds noise. We continue to reduce latency wherever possible, but never at the expense of high-signal findings developers can trust. Try Copilot c