🕷️ Crawler Inspector

URL Lookup

Direct Parameter Lookup

Raw Queries and Responses

1. Shard Calculation

Query:

Response:

Calculated Shard: 129 (from laksa033)

2. Crawled Status Check

Query:

curl -X POST \
  'http://laksa129.int.ahrefs:8124/' \
  -H 'Content-Type: text/plain' \
  -H 'X-ClickHouse-Database: crawler3' \
  -H 'Authorization: Basic YXBpOg==' \
  -d 'SELECT getAhrefsURLFromUnparsed(src_unparsed) AS found_url, ifNull(toUnixTimestamp(download_stamp), 0) AS crawl_time, ifNull(toUnixTimestamp(props_url_first_seen), 0) AS first_indexed_time, download_http_code AS http_code, src_unparsed AS src_unparsed, src_root_hash AS src_root_hash, history_drop_reason AS history_drop_reason, meta_title AS meta_title, meta_descriptions AS meta_descriptions, attrs_boilerpipe_text AS attrs_boilerpipe_text, attrs_markdown AS attrs_markdown, attrs_readable_markdown AS attrs_readable_markdown, meta_canonical AS meta_canonical FROM crawler3.page_info_local FINAL PREWHERE (src_root_hash, src_unparsed) IN ((getAhrefsRootHashFromUnparsed(getAhrefsUnparsedNoserviceFromURL(\'https://github.blog/ai-and-ml/github-copilot/60-million-copilot-code-reviews-and-counting/\')), getAhrefsUnparsedNoserviceFromURL(\'https://github.blog/ai-and-ml/github-copilot/60-million-copilot-code-reviews-and-counting/\'))) FORMAT JSONEachRow'

Response:

{"found_url":"https:\/\/github.blog\/ai-and-ml\/github-copilot\/60-million-copilot-code-reviews-and-counting\/","crawl_time":1775512940,"first_indexed_time":1772742765,"http_code":200,"src_unparsed":"blog,github!\/ai-and-ml\/github-copilot\/60-million-copilot-code-reviews-and-counting\/ s443","src_root_hash":"7620767358965441529","history_drop_reason":null,"meta_title":"60 million Copilot code reviews and counting - The GitHub Blog","meta_descriptions":["How Copilot code review helps teams keep up with AI-accelerated code changes."],"attrs_boilerpipe_text":"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.\nBehind 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.\nCopilot code review handles pull request reviews and summaries, allowing teams to focus on more complex tasks.\nSuvarna Rane, Software Development Manager, General Motors\nRedefining a “good” code review\nAs 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.\nAccuracy\nOur 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:\nDeveloper feedback\n: Thumbs-up and thumbs-down reactions on comments help us understand whether suggestions are helpful.\nProduction signals\n: We measure whether flagged issues are resolved before merging.\nTogether, these signals help ensure that Copilot code review surfaces issues that matter, and that faster merges come from confident fixes, not less scrutiny.\nSignal\nIn 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.\nA high-signal comment helps a developer understand both the problem and the fix:\nSilence 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.\nAs 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.\nSpeed\nIn 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.\nWe 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%.\nFor 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.\nAbout the agentic architecture\nGiven our new definition of “good,” we redeveloped our code review system. Today’s agentic design can retrieve context intelligently and explore the repository to understand logic, architecture, and specific invariants.\nThis shift alone has driven an initial 8.1% increase in positive feedback.\nHere’s why:\nIt catches issues as it reads, not just at the end\n: Previously, agents waited until the end of a review to finalize results, which often led to “forgetting” early discoveries.\nIt can maintain memory across reviews\n: Now, every pull request doesn’t need to be an isolated event. If it flags a pattern in one part of the codebase, it can reuse that context in future reviews.\nIt keeps long pull requests reviewable with an explicit plan\n: It can map out its review strategy ahead of time, significantly improving its performance on long, complex pull requests, where context is easily lost.\nIt reads linked issues and pull requests\n: That extra context helps it flag subtle gaps. This includes cases where the code looks reasonable in isolation but doesn’t match the project’s requirements.\nMaking reviews easier to navigate\nBy iterating on how the agent interacts with pull requests, we’ve reduced noise and made feedback more actionable. Here’s what that means for you.\nQuickly understand feedback (and the fix) with multi-line comments\n: We moved away from pinning comments to single lines. By attaching feedback to logical code ranges, Copilot makes it easier to see what it’s referring to and apply the suggested change.\nKeep your pull request timeline readable\n: Instead of multiple separate comments for the same pattern error, which can be overwhelming, the agent clusters them into a single, cohesive unit to reduce cognitive load.\nFix whole classes of issues at once with batch autofixes\n: Apply suggested fixes in batches, resolving an entire class of logic bugs or style issues at once, rather than context-switching through a dozen individual suggestions.\nTake this with you\nAs AI continues to accelerate software development, it’s more important than ever to help teams review and trust code at scale. Copilot code review helps teams keep pace by surfacing high-signal feedback directly in pull requests, enabling developers to catch issues earlier and merge with greater confidence.\nMore than 12,000 organizations now run Copilot code review automatically on every pull request. At WEX, this shift toward default AI –assisted reviews has helped scale Copilot adoption across the engineering organization:\nToday, two-thirds of developers are using Copilot — including the organization’s most active contributors. WEX has since expanded adoption by making Copilot code review a default across every repository. Developers are also heavily utilizing agent mode and the coding agent to drive autonomy, helping WEX see a huge lift in deployments, with ~30% more code shipped. —\nWEX customer story\nGoing forward, we’re focused on deeper personalization and high-fidelity interactivity, refining the agent to learn your team’s unwritten preferences while enabling two-way conversations that let you refine fixes and explore alternatives before merging.\nAs Copilot capabilities continue to evolve, from coding and planning to review and automation, the goal is simple: help developers move faster while maintaining the trust and quality that great software demands.\nGet started today\nCopilot code review is a premium feature available with Copilot Pro, Copilot Pro+, Copilot Business, and Copilot Enterprise. See the following resources to:\nChoose a plan\nEnable Copilot code review without a Copilot license\nWatch a demo video\nAlready enabled Copilot code review? See these docs to\nset up automatic Copilot code reviews on every pull request\nwithin your repository or organization.\nHave thoughts or feedback? Please let us know in our\ncommunity discussion post\n.\nTags:\ncode quality\nGitHub Actions\nGitHub Copilot\nGitHub Copilot code review\nWritten by\nGitHub Product Manager\nSenior Director, Software Engineering\nExplore more from GitHub\nDocs\nEverything you need to master GitHub, all in one place.\nGo to Docs\nGitHub\nBuild what’s next on GitHub, the place for anyone from anywhere to build anything.\nStart building\nCustomer stories\nMeet the companies and engineering teams that build with GitHub.\nLearn more\nThe GitHub Podcast\nCatch up on the GitHub podcast, a show dedicated to the topics, trends, stories and culture in and around the open source developer community on GitHub.\nListen now","attrs_markdown":"[Skip to content](https:\/\/github.blog\/ai-and-ml\/github-copilot\/60-million-copilot-code-reviews-and-counting\/#start-of-content)   [Skip to sidebar](https:\/\/github.blog\/ai-and-ml\/github-copilot\/60-million-copilot-code-reviews-and-counting\/#sidebar)\n\n\/  [Blog](https:\/\/github.blog\/)\n\n- [Changelog](https:\/\/github.blog\/changelog\/)\n- [Docs](https:\/\/docs.github.com\/)\n- [Customer stories](https:\/\/github.com\/customer-stories)\n\n[Try GitHub Copilot](https:\/\/github.com\/features\/copilot?utm_source=blog-tap-nav&utm_medium=blog&utm_campaign=universe25)   [See what's new](https:\/\/github.com\/events\/universe\/recap?utm_source=k2k-blog-tap-nav&utm_medium=blog&utm_campaign=universe25)\n\n- [AI & ML](https:\/\/github.blog\/ai-and-ml\/)\n  - [AI & ML](https:\/\/github.blog\/ai-and-ml\/)\n    \n    Learn about artificial intelligence and machine learning across the GitHub ecosystem and the wider industry.\n    - [Generative AI](https:\/\/github.blog\/ai-and-ml\/generative-ai\/)\n      Learn how to build with generative AI.\n    - [GitHub Copilot](https:\/\/github.blog\/ai-and-ml\/github-copilot\/)\n      Change how you work with GitHub Copilot.\n    - [LLMs](https:\/\/github.blog\/ai-and-ml\/llms\/)\n      Everything developers need to know about LLMs.\n    - [Machine learning](https:\/\/github.blog\/ai-and-ml\/machine-learning\/)\n      Machine learning tips, tricks, and best practices.\n  - ![](https:\/\/github.blog\/wp-content\/uploads\/2024\/06\/AI-DarkMode-4.png?resize=800%2C425)\n    [How AI code generation works](https:\/\/github.blog\/ai-and-ml\/generative-ai\/how-ai-code-generation-works\/)\n    Explore the capabilities and benefits of AI code generation and how it can improve your developer experience.\n    Learn more\n- [Developer skills](https:\/\/github.blog\/developer-skills\/)\n  - [Developer skills](https:\/\/github.blog\/developer-skills\/)\n    \n    Resources for developers to grow in their skills and careers.\n    - [Application development](https:\/\/github.blog\/developer-skills\/application-development\/)\n      Insights and best practices for building apps.\n    - [Career growth](https:\/\/github.blog\/developer-skills\/career-growth\/)\n      Tips & tricks to grow as a professional developer.\n    - [GitHub](https:\/\/github.blog\/developer-skills\/github\/)\n      Improve how you use GitHub at work.\n    - [GitHub Education](https:\/\/github.blog\/developer-skills\/github-education\/)\n      Learn how to move into your first professional role.\n    - [Programming languages & frameworks](https:\/\/github.blog\/developer-skills\/programming-languages-and-frameworks\/)\n      Stay current on what’s new (or new again).\n  - ![](https:\/\/github.blog\/wp-content\/uploads\/2024\/05\/Enterprise-DarkMode-3.png?resize=800%2C425)\n    [Get started with GitHub documentation](https:\/\/docs.github.com\/en\/get-started)\n    Learn how to start building, shipping, and maintaining software with GitHub.\n    Learn more\n- [Engineering](https:\/\/github.blog\/engineering\/)\n  - [Engineering](https:\/\/github.blog\/engineering\/)\n    \n    Get an inside look at how we’re building the home for all developers.\n    - [Architecture & optimization](https:\/\/github.blog\/engineering\/architecture-optimization\/)\n      Discover how we deliver a performant and highly available experience across the GitHub platform.\n    - [Engineering principles](https:\/\/github.blog\/engineering\/engineering-principles\/)\n      Explore best practices for building software at scale with a majority remote team.\n    - [Infrastructure](https:\/\/github.blog\/engineering\/infrastructure\/)\n      Get a glimpse at the technology underlying the world’s leading AI-powered developer platform.\n    - [Platform security](https:\/\/github.blog\/engineering\/platform-security\/)\n      Learn how we build security into everything we do across the developer lifecycle.\n    - [User experience](https:\/\/github.blog\/engineering\/user-experience\/)\n      Find out what goes into making GitHub the home for all developers.\n  - ![](https:\/\/github.blog\/wp-content\/uploads\/2024\/07\/Screenshot-2024-07-23-at-8.42.45%E2%80%AFAM.png?resize=800%2C425)\n    [How we use GitHub to be more productive, collaborative, and secure](https:\/\/github.blog\/engineering\/how-we-use-github-to-be-more-productive-collaborative-and-secure\/)\n    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.\n    Learn more\n- [Enterprise software](https:\/\/github.blog\/enterprise-software\/)\n  - [Enterprise software](https:\/\/github.blog\/enterprise-software\/)\n    \n    Explore how to write, build, and deploy enterprise software at scale.\n    - [Automation](https:\/\/github.blog\/enterprise-software\/automation\/)\n      Automating your way to faster and more secure ships.\n    - [CI\/CD](https:\/\/github.blog\/enterprise-software\/ci-cd\/)\n      Guides on continuous integration and delivery.\n    - [Collaboration](https:\/\/github.blog\/enterprise-software\/collaboration\/)\n      Tips, tools, and tricks to improve developer collaboration.\n    - [DevOps](https:\/\/github.blog\/enterprise-software\/devops\/)\n      DevOps resources for enterprise engineering teams.\n    - [DevSecOps](https:\/\/github.blog\/enterprise-software\/devsecops\/)\n      How to integrate security into the SDLC.\n    - [Governance & compliance](https:\/\/github.blog\/enterprise-software\/governance-and-compliance\/)\n      Ensuring your builds stay clean.\n  - ![](https:\/\/github.blog\/wp-content\/uploads\/2024\/07\/Screenshot-2024-07-23-at-8.43.47%E2%80%AFAM.png?resize=800%2C425)\n    [GitHub recognized as a Leader in the Gartner® Magic Quadrant™ for AI Code Assistants](https:\/\/github.com\/resources\/whitepapers\/gartner-magic-quadrant-and-critical-capabilities-for-ai-code-assistants)\n    Learn why Gartner positioned GitHub as a Leader for the second year in a row.\n    Learn more\n- [News & insights](https:\/\/github.blog\/news-insights\/)\n  - [News & insights](https:\/\/github.blog\/news-insights\/)\n    \n    Keep up with what’s new and notable from inside GitHub.\n    - [Company news](https:\/\/github.blog\/news-insights\/company-news\/)\n      An inside look at news and product updates from GitHub.\n    - [Product](https:\/\/github.blog\/news-insights\/product-news\/)\n      The latest on GitHub’s platform, products, and tools.\n    - [Octoverse](https:\/\/github.blog\/news-insights\/octoverse\/)\n      Insights into the state of open source on GitHub.\n    - [Policy](https:\/\/github.blog\/news-insights\/policy-news-and-insights\/)\n      The latest policy and regulatory changes in software.\n    - [Research](https:\/\/github.blog\/news-insights\/research\/)\n      Data-driven insights around the developer ecosystem.\n    - [The library](https:\/\/github.blog\/news-insights\/the-library\/)\n      Older news and updates from GitHub.\n  - ![](https:\/\/github.blog\/wp-content\/uploads\/2024\/07\/Screenshot-2024-07-23-at-8.44.23%E2%80%AFAM.png?resize=800%2C425)\n    [Unlocking the power of unstructured data with RAG](https:\/\/github.blog\/ai-and-ml\/llms\/unlocking-the-power-of-unstructured-data-with-rag\/)\n    Learn how to use retrieval-augmented generation (RAG) to capture more insights.\n    Learn more\n- [Open Source](https:\/\/github.blog\/open-source\/)\n  - [Open Source](https:\/\/github.blog\/open-source\/)\n    \n    Everything open source on GitHub.\n    - [Git](https:\/\/github.blog\/open-source\/git\/)\n      The latest Git updates.\n    - [Maintainers](https:\/\/github.blog\/open-source\/maintainers\/)\n      Spotlighting open source maintainers.\n    - [Social impact](https:\/\/github.blog\/open-source\/social-impact\/)\n      How open source is driving positive change.\n    - [Gaming](https:\/\/github.blog\/open-source\/gaming\/)\n      Explore open source games on GitHub.\n  - ![](https:\/\/github.blog\/wp-content\/uploads\/2024\/07\/Screenshot-2024-07-23-at-8.46.23%E2%80%AFAM.png?resize=800%2C425)\n    [An introduction to innersource](https:\/\/resources.github.com\/software-development\/innersource\/)\n    Organizations worldwide are incorporating open source methodologies into the way they build and ship their own software.\n    Learn more\n- [Security](https:\/\/github.blog\/security\/)\n  - [Security](https:\/\/github.blog\/security\/)\n    \n    Stay up to date on everything security.\n    - [Application security](https:\/\/github.blog\/security\/application-security\/)\n      Application security, explained.\n    - [Supply chain security](https:\/\/github.blog\/security\/supply-chain-security\/)\n      Demystifying supply chain security.\n    - [Vulnerability research](https:\/\/github.blog\/security\/vulnerability-research\/)\n      Updates from the GitHub Security Lab.\n    - [Web application security](https:\/\/github.blog\/security\/web-application-security\/)\n      Helpful tips on securing web applications.\n  - ![](https:\/\/github.blog\/wp-content\/uploads\/2024\/07\/Screenshot-2024-07-23-at-8.47.04%E2%80%AFAM.png?resize=800%2C425)\n    [The enterprise guide to AI-powered DevSecOps](https:\/\/resources.github.com\/security\/the-enterprise-guide-to-ai-powered-devsecops\/)\n    Learn about core challenges in DevSecOps, and how you can start addressing them with AI and automation.\n    Learn more\n\n## Categories\n- [AI & ML](https:\/\/github.blog\/ai-and-ml\/)\n  - Back\n    \n    [AI & ML](https:\/\/github.blog\/ai-and-ml\/)\n    \n    Learn about artificial intelligence and machine learning across the GitHub ecosystem and the wider industry.\n    - [Generative AI](https:\/\/github.blog\/ai-and-ml\/generative-ai\/)\n      Learn how to build with generative AI.\n    - [GitHub Copilot](https:\/\/github.blog\/ai-and-ml\/github-copilot\/)\n      Change how you work with GitHub Copilot.\n    - [LLMs](https:\/\/github.blog\/ai-and-ml\/llms\/)\n      Everything developers need to know about LLMs.\n    - [Machine learning](https:\/\/github.blog\/ai-and-ml\/machine-learning\/)\n      Machine learning tips, tricks, and best practices.\n  - [How AI code generation works](https:\/\/github.blog\/ai-and-ml\/generative-ai\/how-ai-code-generation-works\/)\n    \n    Explore the capabilities and benefits of AI code generation and how it can improve your developer experience.\n    \n    [Learn more](https:\/\/github.blog\/ai-and-ml\/generative-ai\/how-ai-code-generation-works\/)\n- [Developer skills](https:\/\/github.blog\/developer-skills\/)\n  - Back\n    \n    [Developer skills](https:\/\/github.blog\/developer-skills\/)\n    \n    Resources for developers to grow in their skills and careers.\n    - [Application development](https:\/\/github.blog\/developer-skills\/application-development\/)\n      Insights and best practices for building apps.\n    - [Career growth](https:\/\/github.blog\/developer-skills\/career-growth\/)\n      Tips & tricks to grow as a professional developer.\n    - [GitHub](https:\/\/github.blog\/developer-skills\/github\/)\n      Improve how you use GitHub at work.\n    - [GitHub Education](https:\/\/github.blog\/developer-skills\/github-education\/)\n      Learn how to move into your first professional role.\n    - [Programming languages & frameworks](https:\/\/github.blog\/developer-skills\/programming-languages-and-frameworks\/)\n      Stay current on what’s new (or new again).\n  - [Get started with GitHub documentation](https:\/\/docs.github.com\/en\/get-started)\n    \n    Learn how to start building, shipping, and maintaining software with GitHub.\n    \n    [Learn more](https:\/\/docs.github.com\/en\/get-started)\n- [Engineering](https:\/\/github.blog\/engineering\/)\n  - Back\n    \n    [Engineering](https:\/\/github.blog\/engineering\/)\n    \n    Get an inside look at how we’re building the home for all developers.\n    - [Architecture & optimization](https:\/\/github.blog\/engineering\/architecture-optimization\/)\n      Discover how we deliver a performant and highly available experience across the GitHub platform.\n    - [Engineering principles](https:\/\/github.blog\/engineering\/engineering-principles\/)\n      Explore best practices for building software at scale with a majority remote team.\n    - [Infrastructure](https:\/\/github.blog\/engineering\/infrastructure\/)\n      Get a glimpse at the technology underlying the world’s leading AI-powered developer platform.\n    - [Platform security](https:\/\/github.blog\/engineering\/platform-security\/)\n      Learn how we build security into everything we do across the developer lifecycle.\n    - [User experience](https:\/\/github.blog\/engineering\/user-experience\/)\n      Find out what goes into making GitHub the home for all developers.\n  - [How we use GitHub to be more productive, collaborative, and secure](https:\/\/github.blog\/engineering\/how-we-use-github-to-be-more-productive-collaborative-and-secure\/)\n    \n    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.\n    \n    [Learn more](https:\/\/github.blog\/engineering\/how-we-use-github-to-be-more-productive-collaborative-and-secure\/)\n- [Enterprise software](https:\/\/github.blog\/enterprise-software\/)\n  - Back\n    \n    [Enterprise software](https:\/\/github.blog\/enterprise-software\/)\n    \n    Explore how to write, build, and deploy enterprise software at scale.\n    - [Automation](https:\/\/github.blog\/enterprise-software\/automation\/)\n      Automating your way to faster and more secure ships.\n    - [CI\/CD](https:\/\/github.blog\/enterprise-software\/ci-cd\/)\n      Guides on continuous integration and delivery.\n    - [Collaboration](https:\/\/github.blog\/enterprise-software\/collaboration\/)\n      Tips, tools, and tricks to improve developer collaboration.\n    - [DevOps](https:\/\/github.blog\/enterprise-software\/devops\/)\n      DevOps resources for enterprise engineering teams.\n    - [DevSecOps](https:\/\/github.blog\/enterprise-software\/devsecops\/)\n      How to integrate security into the SDLC.\n    - [Governance & compliance](https:\/\/github.blog\/enterprise-software\/governance-and-compliance\/)\n      Ensuring your builds stay clean.\n  - [GitHub recognized as a Leader in the Gartner® Magic Quadrant™ for AI Code Assistants](https:\/\/github.com\/resources\/whitepapers\/gartner-magic-quadrant-and-critical-capabilities-for-ai-code-assistants)\n    \n    Learn why Gartner positioned GitHub as a Leader for the second year in a row.\n    \n    [Learn more](https:\/\/github.com\/resources\/whitepapers\/gartner-magic-quadrant-and-critical-capabilities-for-ai-code-assistants)\n- [News & insights](https:\/\/github.blog\/news-insights\/)\n  - Back\n    \n    [News & insights](https:\/\/github.blog\/news-insights\/)\n    \n    Keep up with what’s new and notable from inside GitHub.\n    - [Company news](https:\/\/github.blog\/news-insights\/company-news\/)\n      An inside look at news and product updates from GitHub.\n    - [Product](https:\/\/github.blog\/news-insights\/product-news\/)\n      The latest on GitHub’s platform, products, and tools.\n    - [Octoverse](https:\/\/github.blog\/news-insights\/octoverse\/)\n      Insights into the state of open source on GitHub.\n    - [Policy](https:\/\/github.blog\/news-insights\/policy-news-and-insights\/)\n      The latest policy and regulatory changes in software.\n    - [Research](https:\/\/github.blog\/news-insights\/research\/)\n      Data-driven insights around the developer ecosystem.\n    - [The library](https:\/\/github.blog\/news-insights\/the-library\/)\n      Older news and updates from GitHub.\n  - [Unlocking the power of unstructured data with RAG](https:\/\/github.blog\/ai-and-ml\/llms\/unlocking-the-power-of-unstructured-data-with-rag\/)\n    \n    Learn how to use retrieval-augmented generation (RAG) to capture more insights.\n    \n    [Learn more](https:\/\/github.blog\/ai-and-ml\/llms\/unlocking-the-power-of-unstructured-data-with-rag\/)\n- [Open Source](https:\/\/github.blog\/open-source\/)\n  - Back\n    \n    [Open Source](https:\/\/github.blog\/open-source\/)\n    \n    Everything open source on GitHub.\n    - [Git](https:\/\/github.blog\/open-source\/git\/)\n      The latest Git updates.\n    - [Maintainers](https:\/\/github.blog\/open-source\/maintainers\/)\n      Spotlighting open source maintainers.\n    - [Social impact](https:\/\/github.blog\/open-source\/social-impact\/)\n      How open source is driving positive change.\n    - [Gaming](https:\/\/github.blog\/open-source\/gaming\/)\n      Explore open source games on GitHub.\n  - [An introduction to innersource](https:\/\/resources.github.com\/software-development\/innersource\/)\n    \n    Organizations worldwide are incorporating open source methodologies into the way they build and ship their own software.\n    \n    [Learn more](https:\/\/resources.github.com\/software-development\/innersource\/)\n- [Security](https:\/\/github.blog\/security\/)\n  - Back\n    \n    [Security](https:\/\/github.blog\/security\/)\n    \n    Stay up to date on everything security.\n    - [Application security](https:\/\/github.blog\/security\/application-security\/)\n      Application security, explained.\n    - [Supply chain security](https:\/\/github.blog\/security\/supply-chain-security\/)\n      Demystifying supply chain security.\n    - [Vulnerability research](https:\/\/github.blog\/security\/vulnerability-research\/)\n      Updates from the GitHub Security Lab.\n    - [Web application security](https:\/\/github.blog\/security\/web-application-security\/)\n      Helpful tips on securing web applications.\n  - [The enterprise guide to AI-powered DevSecOps](https:\/\/resources.github.com\/security\/the-enterprise-guide-to-ai-powered-devsecops\/)\n    \n    Learn about core challenges in DevSecOps, and how you can start addressing them with AI and automation.\n    \n    [Learn more](https:\/\/resources.github.com\/security\/the-enterprise-guide-to-ai-powered-devsecops\/)\n\n- [Changelog](https:\/\/github.blog\/changelog\/)\n- [Docs](https:\/\/docs.github.com\/)\n- [Customer stories](https:\/\/github.com\/customer-stories)\n\n[See what's new](https:\/\/github.com\/events\/universe\/recap?utm_source=k2k-blog-tap-nav&utm_medium=blog&utm_campaign=universe25)   [Try GitHub Copilot](https:\/\/github.com\/features\/copilot?utm_source=blog-tap-nav&utm_medium=blog&utm_campaign=universe25)\n\n[Home](https:\/\/github.blog\/) \/ [AI & ML](https:\/\/github.blog\/ai-and-ml\/) \/ [GitHub Copilot](https:\/\/github.blog\/ai-and-ml\/github-copilot\/)\n\n# 60 million Copilot code reviews and counting\nHow Copilot code review helps teams keep up with AI-accelerated code changes.\n\n![Copilot appears among floating cubes alongside a refresh icon, suggesting an update or automated workflow theme.](https:\/\/github.blog\/wp-content\/uploads\/2026\/01\/generic-github-copilot-logo.png?resize=1600%2C850)\n\n[Ria Gopu](https:\/\/github.blog\/author\/ria-gopu\/ \"Posts by Ria Gopu\") & [David Apirian](https:\/\/github.blog\/author\/dapirian\/ \"Posts by David Apirian\")\n\nMarch 5, 2026\n\n\\|\n\n6 minutes\n\n- Share:\n\nSince 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.\n\nBehind 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.\n\n> Copilot code review handles pull request reviews and summaries, allowing teams to focus on more complex tasks.\n> \n> Suvarna Rane, Software Development Manager, General Motors\n## Redefining a “good” code review\nAs 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.\n\n### Accuracy\nOur 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:\n\n- **Developer feedback**: Thumbs-up and thumbs-down reactions on comments help us understand whether suggestions are helpful.\n- **Production signals**: We measure whether flagged issues are resolved before merging.\n\nTogether, these signals help ensure that Copilot code review surfaces issues that matter, and that faster merges come from confident fixes, not less scrutiny.\n\n![Copilot code review comment identifying a missing dependency in a React useCallback hook and suggesting a code change to add handleKeyboardDrag to the dependency array.](https:\/\/github.blog\/wp-content\/uploads\/2026\/03\/Screenshot-2026-03-05-at-10.29.41-AM.png?resize=1024%2C435)\n\n### Signal\nIn 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.\n\nA high-signal comment helps a developer understand both the problem and the fix:\n\n![Copilot code review comment warning that a retry loop could run indefinitely when an API returns HTTP 429 without a Retry-After header and suggesting adding a retry limit and backoff.](https:\/\/github.blog\/wp-content\/uploads\/2026\/03\/Screenshot-2026-03-05-at-11.07.14-AM.png?resize=1024%2C289)\n\nSilence 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.\n\nAs 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.\n\n### Speed\nIn 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.\n\nWe 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%.\n\nFor 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.\n\n## Try Copilot code review: AI code review agent that understands your codebase\nCopilot code review helps you catch bugs, improve readability, and speed up pull request feedback with AI suggestions right where you work on GitHub. It fits into your existing pull request workflow, so your team can ship faster with more confidence.\n\n[👉 Get started with Copilot code review on GitHub \\>](https:\/\/docs.github.com\/en\/copilot\/get-started\/quickstart)\n## About the agentic architecture\nGiven our new definition of “good,” we redeveloped our code review system. Today’s agentic design can retrieve context intelligently and explore the repository to understand logic, architecture, and specific invariants.\n\nThis shift alone has driven an initial 8.1% increase in positive feedback.\n\nHere’s why:\n\n- **It catches issues as it reads, not just at the end**: Previously, agents waited until the end of a review to finalize results, which often led to “forgetting” early discoveries.\n- **It can maintain memory across reviews**: Now, every pull request doesn’t need to be an isolated event. If it flags a pattern in one part of the codebase, it can reuse that context in future reviews.\n- **It keeps long pull requests reviewable with an explicit plan**: It can map out its review strategy ahead of time, significantly improving its performance on long, complex pull requests, where context is easily lost.\n- **It reads linked issues and pull requests**: That extra context helps it flag subtle gaps. This includes cases where the code looks reasonable in isolation but doesn’t match the project’s requirements.\n## Making reviews easier to navigate\nBy iterating on how the agent interacts with pull requests, we’ve reduced noise and made feedback more actionable. Here’s what that means for you.\n\n- **Quickly understand feedback (and the fix) with multi-line comments**: We moved away from pinning comments to single lines. By attaching feedback to logical code ranges, Copilot makes it easier to see what it’s referring to and apply the suggested change.\n\n![Copilot code review comment on a GitHub Actions workflow identifying a missing use\\_caches input parameter and suggesting a code change to add the boolean input to the workflow configuration.](https:\/\/github.blog\/wp-content\/uploads\/2026\/03\/Screenshot-2026-02-01-at-3.30.41-PM.png?resize=1024%2C1010)\n\n- **Keep your pull request timeline readable**: Instead of multiple separate comments for the same pattern error, which can be overwhelming, the agent clusters them into a single, cohesive unit to reduce cognitive load.\n- **Fix whole classes of issues at once with batch autofixes**: Apply suggested fixes in batches, resolving an entire class of logic bugs or style issues at once, rather than context-switching through a dozen individual suggestions.\n## Take this with you\nAs AI continues to accelerate software development, it’s more important than ever to help teams review and trust code at scale. Copilot code review helps teams keep pace by surfacing high-signal feedback directly in pull requests, enabling developers to catch issues earlier and merge with greater confidence.\n\nMore than 12,000 organizations now run Copilot code review automatically on every pull request. At WEX, this shift toward default AI –assisted reviews has helped scale Copilot adoption across the engineering organization:\n\nToday, two-thirds of developers are using Copilot — including the organization’s most active contributors. WEX has since expanded adoption by making Copilot code review a default across every repository. Developers are also heavily utilizing agent mode and the coding agent to drive autonomy, helping WEX see a huge lift in deployments, with ~30% more code shipped. — [WEX customer story](https:\/\/github.com\/customer-stories\/wex)\n\nGoing forward, we’re focused on deeper personalization and high-fidelity interactivity, refining the agent to learn your team’s unwritten preferences while enabling two-way conversations that let you refine fixes and explore alternatives before merging.\n\nAs Copilot capabilities continue to evolve, from coding and planning to review and automation, the goal is simple: help developers move faster while maintaining the trust and quality that great software demands.\n\n## Get started today\nCopilot code review is a premium feature available with Copilot Pro, Copilot Pro+, Copilot Business, and Copilot Enterprise. See the following resources to:\n\n- [Choose a plan](https:\/\/docs.github.com\/en\/copilot\/get-started\/plans#ready-to-choose-a-plan)\n- [Enable Copilot code review without a Copilot license](https:\/\/docs.github.com\/en\/copilot\/concepts\/agents\/code-review#copilot-code-review-without-a-copilot-license)\n- [Watch a demo video](https:\/\/youtu.be\/HDEGFNAUkX8?si=s9DauqsFZCdtpCtI)\n\nAlready enabled Copilot code review? See these docs to [set up automatic Copilot code reviews on every pull request](https:\/\/docs.github.com\/en\/copilot\/how-tos\/use-copilot-agents\/request-a-code-review\/configure-automatic-review) within your repository or organization.\n\nHave thoughts or feedback? Please let us know in our [community discussion post](https:\/\/github.com\/orgs\/community\/discussions\/186303).\n\n***\n## Tags:\n- [code quality](https:\/\/github.blog\/tag\/code-quality\/)\n- [GitHub Actions](https:\/\/github.blog\/tag\/github-actions\/)\n- [GitHub Copilot](https:\/\/github.blog\/tag\/github-copilot\/)\n- [GitHub Copilot code review](https:\/\/github.blog\/tag\/github-copilot-code-review\/)\n\n## Written by\n![Ria Gopu](https:\/\/avatars.githubusercontent.com\/u\/189655821?v=4&s=200)\n\n### [Ria Gopu](https:\/\/github.blog\/author\/ria-gopu\/)\n[@ria-gopu](https:\/\/github.com\/ria-gopu)\n\nGitHub Product Manager\n\n![David Apirian](https:\/\/avatars.githubusercontent.com\/u\/3904462?v=4&s=200)\n\n### [David Apirian](https:\/\/github.blog\/author\/dapirian\/)\n[@dapirian](https:\/\/github.com\/dapirian)\n\nSenior Director, Software Engineering\n\n- [code quality](https:\/\/github.blog\/tag\/code-quality\/)\n- [GitHub Actions](https:\/\/github.blog\/tag\/github-actions\/)\n- [GitHub Copilot](https:\/\/github.blog\/tag\/github-copilot\/)\n- [GitHub Copilot code review](https:\/\/github.blog\/tag\/github-copilot-code-review\/)\n\n## Table of Contents\n- [Redefining a “good” code review](https:\/\/github.blog\/ai-and-ml\/github-copilot\/60-million-copilot-code-reviews-and-counting\/#h-redefining-a-good-code-review)\n- [Try Copilot code review: AI code review agent that understands your codebase](https:\/\/github.blog\/ai-and-ml\/github-copilot\/60-million-copilot-code-reviews-and-counting\/#h-try-copilot-code-review-ai-code-review-agent-that-understands-your-codebase)\n- [About the agentic architecture](https:\/\/github.blog\/ai-and-ml\/github-copilot\/60-million-copilot-code-reviews-and-counting\/#h-about-the-agentic-architecture)\n- [Making reviews easier to navigate](https:\/\/github.blog\/ai-and-ml\/github-copilot\/60-million-copilot-code-reviews-and-counting\/#h-making-reviews-easier-to-navigate)\n- [Take this with you](https:\/\/github.blog\/ai-and-ml\/github-copilot\/60-million-copilot-code-reviews-and-counting\/#h-take-this-with-you)\n- [Get started today](https:\/\/github.blog\/ai-and-ml\/github-copilot\/60-million-copilot-code-reviews-and-counting\/#h-get-started-today)\n\n## More on [code quality](https:\/\/github.blog\/tag\/code-quality\/)\n### [Does GitHub Copilot improve code quality? Here’s what the data says](https:\/\/github.blog\/news-insights\/research\/does-github-copilot-improve-code-quality-heres-what-the-data-says\/)\nFindings in our latest study show that the quality of code written with GitHub Copilot is significantly more functional, readable, reliable, maintainable, and concise.\n\n[Jared Bauer](https:\/\/github.blog\/author\/jaredsb\/ \"Posts by Jared Bauer\")\n\n## Related posts\n![Copilot CLI welcome screen](https:\/\/github.blog\/wp-content\/uploads\/2026\/02\/554396112-02305897-302e-435b-862b-616faea6a7f5.png?resize=400%2C212)\n\n[AI & ML](https:\/\/github.blog\/ai-and-ml\/)\n\n### [Run multiple agents at once with \/fleet in Copilot CLI](https:\/\/github.blog\/ai-and-ml\/github-copilot\/run-multiple-agents-at-once-with-fleet-in-copilot-cli\/)\n\/fleet lets Copilot CLI dispatch multiple agents in parallel. Learn how to write prompts that split work across files, declare dependencies, and avoid common pitfalls.\n\n[Matt Nigh](https:\/\/github.blog\/author\/mattnigh\/ \"Posts by Matt Nigh\") & [Brian LaFlamme](https:\/\/github.blog\/author\/briancl2\/ \"Posts by Brian LaFlamme\")\n\n![Decorative background featuring two Copilot figures moving among abstract green and translucent blocks.](https:\/\/github.blog\/wp-content\/uploads\/2026\/01\/generic-mona-copilot-logo.png?resize=400%2C212)\n\n[AI & ML](https:\/\/github.blog\/ai-and-ml\/)\n\n### [Agent-driven development in Copilot Applied Science](https:\/\/github.blog\/ai-and-ml\/github-copilot\/agent-driven-development-in-copilot-applied-science\/)\nI used coding agents to build agents that automated part of my job. Here’s what I learned about working better with coding agents.\n\n[Tyler McGoffin](https:\/\/github.blog\/author\/jtmcg\/ \"Posts by Tyler McGoffin\")\n\n![Copilot hovering beside a cluster of geometric cubes in a decorative scene.](https:\/\/github.blog\/wp-content\/uploads\/2026\/01\/generic-copilot-logo-github.png?resize=400%2C212)\n\n[AI & ML](https:\/\/github.blog\/ai-and-ml\/)\n\n### [Building AI-powered GitHub issue triage with the Copilot SDK](https:\/\/github.blog\/ai-and-ml\/github-copilot\/building-ai-powered-github-issue-triage-with-the-copilot-sdk\/)\nLearn how to integrate the Copilot SDK into a React Native app to generate AI-powered issue summaries, with production patterns for graceful degradation and caching.\n\n[Andrea Griffiths](https:\/\/github.blog\/author\/andreagriffiths11\/ \"Posts by Andrea Griffiths\")\n\n## Explore more from GitHub\n![Docs](https:\/\/github.blog\/wp-content\/uploads\/2024\/07\/Icon-Circle.svg)\n\n### Docs\nEverything you need to master GitHub, all in one place.\n\n[Go to Docs](https:\/\/docs.github.com\/)\n\n![GitHub](https:\/\/github.blog\/wp-content\/uploads\/2024\/07\/recirculation-github-icon.svg)\n\n### GitHub\nBuild what’s next on GitHub, the place for anyone from anywhere to build anything.\n\n[Start building](https:\/\/github.com\/)\n\n![Customer stories](https:\/\/github.blog\/wp-content\/uploads\/2024\/07\/Icon_da43dc.svg)\n\n### Customer stories\nMeet the companies and engineering teams that build with GitHub.\n\n[Learn more](https:\/\/github.com\/customer-stories)\n\n![The GitHub Podcast](https:\/\/github.blog\/wp-content\/uploads\/2023\/02\/galaxy23-icon.svg)\n\n### The GitHub Podcast\nCatch up on the GitHub podcast, a show dedicated to the topics, trends, stories and culture in and around the open source developer community on GitHub.\n\n[Listen now](https:\/\/the-github-podcast.simplecast.com\/)\n\n## We do newsletters, too\nDiscover tips, technical guides, and best practices in our biweekly newsletter just for devs.\n\nYour email address\n\n## Site-wide Links\n### Product\n- [Features](https:\/\/github.com\/features)\n- [Security](https:\/\/github.com\/security)\n- [Enterprise](https:\/\/github.com\/enterprise)\n- [Customer Stories](https:\/\/github.com\/customer-stories?type=enterprise)\n- [Pricing](https:\/\/github.com\/pricing)\n- [Resources](https:\/\/resources.github.com\/)\n\n### Platform\n- [Developer API](https:\/\/developer.github.com\/)\n- [Partners](https:\/\/partner.github.com\/)\n- [Atom](https:\/\/atom.io\/)\n- [Electron](https:\/\/www.electronjs.org\/)\n- [GitHub Desktop](https:\/\/desktop.github.com\/)\n\n### Support\n- [Docs](https:\/\/docs.github.com\/)\n- [Community Forum](https:\/\/github.community\/)\n- [Training](https:\/\/services.github.com\/)\n- [Status](https:\/\/www.githubstatus.com\/)\n- [Contact](https:\/\/support.github.com\/)\n\n### Company\n- [About](https:\/\/github.com\/about)\n- [Blog](https:\/\/github.blog\/)\n- [Careers](https:\/\/github.com\/about\/careers)\n- [Press](https:\/\/github.com\/about\/press)\n- [Shop](https:\/\/shop.github.com\/)\n\n- © 2026 GitHub, Inc.\n- [Terms](https:\/\/docs.github.com\/en\/github\/site-policy\/github-terms-of-service)\n- [Privacy](https:\/\/docs.github.com\/en\/github\/site-policy\/github-privacy-statement)\n- Manage Cookies\n- Do not share my personal information\n\n- [GitHub on LinkedIn](https:\/\/www.linkedin.com\/company\/github)\n- [GitHub on Instagram](https:\/\/www.instagram.com\/github\/)\n- [GitHub on YouTube](https:\/\/www.youtube.com\/github)\n- [GitHub on X](https:\/\/twitter.com\/github)\n- [GitHub on TikTok](https:\/\/www.tiktok.com\/@github)\n- [GitHub on Twitch](https:\/\/www.twitch.tv\/github)\n- [GitHub’s organization on GitHub](https:\/\/github.com\/github)","attrs_readable_markdown":"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.\n\nBehind 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.\n\n> Copilot code review handles pull request reviews and summaries, allowing teams to focus on more complex tasks.\n> \n> Suvarna Rane, Software Development Manager, General Motors\n## Redefining a “good” code review\nAs 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.\n\n### Accuracy\nOur 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:\n\n- **Developer feedback**: Thumbs-up and thumbs-down reactions on comments help us understand whether suggestions are helpful.\n- **Production signals**: We measure whether flagged issues are resolved before merging.\n\nTogether, these signals help ensure that Copilot code review surfaces issues that matter, and that faster merges come from confident fixes, not less scrutiny.\n\n![Copilot code review comment identifying a missing dependency in a React useCallback hook and suggesting a code change to add handleKeyboardDrag to the dependency array.](https:\/\/github.blog\/wp-content\/uploads\/2026\/03\/Screenshot-2026-03-05-at-10.29.41-AM.png?resize=1024%2C435)\n\n### Signal\nIn 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.\n\nA high-signal comment helps a developer understand both the problem and the fix:\n\n![Copilot code review comment warning that a retry loop could run indefinitely when an API returns HTTP 429 without a Retry-After header and suggesting adding a retry limit and backoff.](https:\/\/github.blog\/wp-content\/uploads\/2026\/03\/Screenshot-2026-03-05-at-11.07.14-AM.png?resize=1024%2C289)\n\nSilence 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.\n\nAs 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.\n\n### Speed\nIn 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.\n\nWe 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%.\n\nFor 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.\n\n## About the agentic architecture\nGiven our new definition of “good,” we redeveloped our code review system. Today’s agentic design can retrieve context intelligently and explore the repository to understand logic, architecture, and specific invariants.\n\nThis shift alone has driven an initial 8.1% increase in positive feedback.\n\nHere’s why:\n\n- **It catches issues as it reads, not just at the end**: Previously, agents waited until the end of a review to finalize results, which often led to “forgetting” early discoveries.\n- **It can maintain memory across reviews**: Now, every pull request doesn’t need to be an isolated event. If it flags a pattern in one part of the codebase, it can reuse that context in future reviews.\n- **It keeps long pull requests reviewable with an explicit plan**: It can map out its review strategy ahead of time, significantly improving its performance on long, complex pull requests, where context is easily lost.\n- **It reads linked issues and pull requests**: That extra context helps it flag subtle gaps. This includes cases where the code looks reasonable in isolation but doesn’t match the project’s requirements.\n## Making reviews easier to navigate\nBy iterating on how the agent interacts with pull requests, we’ve reduced noise and made feedback more actionable. Here’s what that means for you.\n\n- **Quickly understand feedback (and the fix) with multi-line comments**: We moved away from pinning comments to single lines. By attaching feedback to logical code ranges, Copilot makes it easier to see what it’s referring to and apply the suggested change.\n\n![Copilot code review comment on a GitHub Actions workflow identifying a missing use\\_caches input parameter and suggesting a code change to add the boolean input to the workflow configuration.](https:\/\/github.blog\/wp-content\/uploads\/2026\/03\/Screenshot-2026-02-01-at-3.30.41-PM.png?resize=1024%2C1010)\n\n- **Keep your pull request timeline readable**: Instead of multiple separate comments for the same pattern error, which can be overwhelming, the agent clusters them into a single, cohesive unit to reduce cognitive load.\n- **Fix whole classes of issues at once with batch autofixes**: Apply suggested fixes in batches, resolving an entire class of logic bugs or style issues at once, rather than context-switching through a dozen individual suggestions.\n## Take this with you\nAs AI continues to accelerate software development, it’s more important than ever to help teams review and trust code at scale. Copilot code review helps teams keep pace by surfacing high-signal feedback directly in pull requests, enabling developers to catch issues earlier and merge with greater confidence.\n\nMore than 12,000 organizations now run Copilot code review automatically on every pull request. At WEX, this shift toward default AI –assisted reviews has helped scale Copilot adoption across the engineering organization:\n\nToday, two-thirds of developers are using Copilot — including the organization’s most active contributors. WEX has since expanded adoption by making Copilot code review a default across every repository. Developers are also heavily utilizing agent mode and the coding agent to drive autonomy, helping WEX see a huge lift in deployments, with ~30% more code shipped. — [WEX customer story](https:\/\/github.com\/customer-stories\/wex)\n\nGoing forward, we’re focused on deeper personalization and high-fidelity interactivity, refining the agent to learn your team’s unwritten preferences while enabling two-way conversations that let you refine fixes and explore alternatives before merging.\n\nAs Copilot capabilities continue to evolve, from coding and planning to review and automation, the goal is simple: help developers move faster while maintaining the trust and quality that great software demands.\n\n## Get started today\nCopilot code review is a premium feature available with Copilot Pro, Copilot Pro+, Copilot Business, and Copilot Enterprise. See the following resources to:\n\n- [Choose a plan](https:\/\/docs.github.com\/en\/copilot\/get-started\/plans#ready-to-choose-a-plan)\n- [Enable Copilot code review without a Copilot license](https:\/\/docs.github.com\/en\/copilot\/concepts\/agents\/code-review#copilot-code-review-without-a-copilot-license)\n- [Watch a demo video](https:\/\/youtu.be\/HDEGFNAUkX8?si=s9DauqsFZCdtpCtI)\n\nAlready enabled Copilot code review? See these docs to [set up automatic Copilot code reviews on every pull request](https:\/\/docs.github.com\/en\/copilot\/how-tos\/use-copilot-agents\/request-a-code-review\/configure-automatic-review) within your repository or organization.\n\nHave thoughts or feedback? Please let us know in our [community discussion post](https:\/\/github.com\/orgs\/community\/discussions\/186303).\n\n***\n## Tags:\n- [code quality](https:\/\/github.blog\/tag\/code-quality\/)\n- [GitHub Actions](https:\/\/github.blog\/tag\/github-actions\/)\n- [GitHub Copilot](https:\/\/github.blog\/tag\/github-copilot\/)\n- [GitHub Copilot code review](https:\/\/github.blog\/tag\/github-copilot-code-review\/)\n\n## Written by\n![Ria Gopu](https:\/\/avatars.githubusercontent.com\/u\/189655821?v=4&s=200)\n\nGitHub Product Manager\n\n![David Apirian](https:\/\/avatars.githubusercontent.com\/u\/3904462?v=4&s=200)\n\nSenior Director, Software Engineering\n\n## Explore more from GitHub\n![Docs](https:\/\/github.blog\/wp-content\/uploads\/2024\/07\/Icon-Circle.svg)\n\n### Docs\nEverything you need to master GitHub, all in one place.\n\n[Go to Docs](https:\/\/docs.github.com\/)\n\n![GitHub](https:\/\/github.blog\/wp-content\/uploads\/2024\/07\/recirculation-github-icon.svg)\n\n### GitHub\nBuild what’s next on GitHub, the place for anyone from anywhere to build anything.\n\n[Start building](https:\/\/github.com\/)\n\n![Customer stories](https:\/\/github.blog\/wp-content\/uploads\/2024\/07\/Icon_da43dc.svg)\n\n### Customer stories\nMeet the companies and engineering teams that build with GitHub.\n\n[Learn more](https:\/\/github.com\/customer-stories)\n\n![The GitHub Podcast](https:\/\/github.blog\/wp-content\/uploads\/2023\/02\/galaxy23-icon.svg)\n\n### The GitHub Podcast\nCatch up on the GitHub podcast, a show dedicated to the topics, trends, stories and culture in and around the open source developer community on GitHub.\n\n[Listen now](https:\/\/the-github-podcast.simplecast.com\/)","meta_canonical":null}

3. Robots.txt Check

Query:

Response:

4. Spam/Ban Check

Query:

Response:

5. Seen Status Check

ℹ️ Skipped - page is already crawled

📄

INDEXABLE

✅

CRAWLED

1 hour ago

🤖

ROBOTS ALLOWED

Page Info Filters

Filter	Status	Condition	Details
HTTP status	PASS	`download_http_code = 200`	HTTP 200
Age cutoff	PASS	`download_stamp > now() - 6 MONTH`	0 months ago
History drop	PASS	`isNull(history_drop_reason)`	No drop reason
Spam/ban	PASS	`fh_dont_index != 1 AND ml_spam_score = 0`	ml_spam_score=0
Canonical	PASS	`meta_canonical IS NULL OR = '' OR = src_unparsed`	Not set

Page Details

Property	Value
URL	https://github.blog/ai-and-ml/github-copilot/60-million-copilot-code-reviews-and-counting/
Last Crawled	2026-04-06 22:02:20 (1 hour ago)
First Indexed	2026-03-05 20:32:45 (1 month ago)
HTTP Status Code	200
Meta Title	60 million Copilot code reviews and counting - The GitHub Blog
Meta Description	How Copilot code review helps teams keep up with AI-accelerated code changes.
Meta Canonical	null
Boilerpipe Text	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. About the agentic architecture Given our new definition of “good,” we redeveloped our code review system. Today’s agentic design can retrieve context intelligently and explore the repository to understand logic, architecture, and specific invariants. This shift alone has driven an initial 8.1% increase in positive feedback. Here’s why: It catches issues as it reads, not just at the end : Previously, agents waited until the end of a review to finalize results, which often led to “forgetting” early discoveries. It can maintain memory across reviews : Now, every pull request doesn’t need to be an isolated event. If it flags a pattern in one part of the codebase, it can reuse that context in future reviews. It keeps long pull requests reviewable with an explicit plan : It can map out its review strategy ahead of time, significantly improving its performance on long, complex pull requests, where context is easily lost. It reads linked issues and pull requests : That extra context helps it flag subtle gaps. This includes cases where the code looks reasonable in isolation but doesn’t match the project’s requirements. Making reviews easier to navigate By iterating on how the agent interacts with pull requests, we’ve reduced noise and made feedback more actionable. Here’s what that means for you. Quickly understand feedback (and the fix) with multi-line comments : We moved away from pinning comments to single lines. By attaching feedback to logical code ranges, Copilot makes it easier to see what it’s referring to and apply the suggested change. Keep your pull request timeline readable : Instead of multiple separate comments for the same pattern error, which can be overwhelming, the agent clusters them into a single, cohesive unit to reduce cognitive load. Fix whole classes of issues at once with batch autofixes : Apply suggested fixes in batches, resolving an entire class of logic bugs or style issues at once, rather than context-switching through a dozen individual suggestions. Take this with you As AI continues to accelerate software development, it’s more important than ever to help teams review and trust code at scale. Copilot code review helps teams keep pace by surfacing high-signal feedback directly in pull requests, enabling developers to catch issues earlier and merge with greater confidence. More than 12,000 organizations now run Copilot code review automatically on every pull request. At WEX, this shift toward default AI –assisted reviews has helped scale Copilot adoption across the engineering organization: Today, two-thirds of developers are using Copilot — including the organization’s most active contributors. WEX has since expanded adoption by making Copilot code review a default across every repository. Developers are also heavily utilizing agent mode and the coding agent to drive autonomy, helping WEX see a huge lift in deployments, with ~30% more code shipped. — WEX customer story Going forward, we’re focused on deeper personalization and high-fidelity interactivity, refining the agent to learn your team’s unwritten preferences while enabling two-way conversations that let you refine fixes and explore alternatives before merging. As Copilot capabilities continue to evolve, from coding and planning to review and automation, the goal is simple: help developers move faster while maintaining the trust and quality that great software demands. Get started today Copilot code review is a premium feature available with Copilot Pro, Copilot Pro+, Copilot Business, and Copilot Enterprise. See the following resources to: Choose a plan Enable Copilot code review without a Copilot license Watch a demo video Already enabled Copilot code review? See these docs to set up automatic Copilot code reviews on every pull request within your repository or organization. Have thoughts or feedback? Please let us know in our community discussion post . Tags: code quality GitHub Actions GitHub Copilot GitHub Copilot code review Written by GitHub Product Manager Senior Director, Software Engineering Explore more from GitHub Docs Everything you need to master GitHub, all in one place. Go to Docs GitHub Build what’s next on GitHub, the place for anyone from anywhere to build anything. Start building Customer stories Meet the companies and engineering teams that build with GitHub. Learn more The GitHub Podcast Catch up on the GitHub podcast, a show dedicated to the topics, trends, stories and culture in and around the open source developer community on GitHub. Listen now
Markdown	[Skip to content](https://github.blog/ai-and-ml/github-copilot/60-million-copilot-code-reviews-and-counting/#start-of-content) [Skip to sidebar](https://github.blog/ai-and-ml/github-copilot/60-million-copilot-code-reviews-and-counting/#sidebar) / [Blog](https://github.blog/) - [Changelog](https://github.blog/changelog/) - [Docs](https://docs.github.com/) - [Customer stories](https://github.com/customer-stories) [Try GitHub Copilot](https://github.com/features/copilot?utm_source=blog-tap-nav&utm_medium=blog&utm_campaign=universe25) [See what's new](https://github.com/events/universe/recap?utm_source=k2k-blog-tap-nav&utm_medium=blog&utm_campaign=universe25) - [AI & ML](https://github.blog/ai-and-ml/) - [AI & ML](https://github.blog/ai-and-ml/) Learn about artificial intelligence and machine learning across the GitHub ecosystem and the wider industry. - [Generative AI](https://github.blog/ai-and-ml/generative-ai/) Learn how to build with generative AI. - [GitHub Copilot](https://github.blog/ai-and-ml/github-copilot/) Change how you work with GitHub Copilot. - [LLMs](https://github.blog/ai-and-ml/llms/) Everything developers need to know about LLMs. - [Machine learning](https://github.blog/ai-and-ml/machine-learning/) Machine learning tips, tricks, and best practices. - ![](https://github.blog/wp-content/uploads/2024/06/AI-DarkMode-4.png?resize=800%2C425) [How AI code generation works](https://github.blog/ai-and-ml/generative-ai/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](https://github.blog/developer-skills/) - [Developer skills](https://github.blog/developer-skills/) Resources for developers to grow in their skills and careers. - [Application development](https://github.blog/developer-skills/application-development/) Insights and best practices for building apps. - [Career growth](https://github.blog/developer-skills/career-growth/) Tips & tricks to grow as a professional developer. - [GitHub](https://github.blog/developer-skills/github/) Improve how you use GitHub at work. - [GitHub Education](https://github.blog/developer-skills/github-education/) Learn how to move into your first professional role. - [Programming languages & frameworks](https://github.blog/developer-skills/programming-languages-and-frameworks/) Stay current on what’s new (or new again). - ![](https://github.blog/wp-content/uploads/2024/05/Enterprise-DarkMode-3.png?resize=800%2C425) [Get started with GitHub documentation](https://docs.github.com/en/get-started) Learn how to start building, shipping, and maintaining software with GitHub. Learn more - [Engineering](https://github.blog/engineering/) - [Engineering](https://github.blog/engineering/) Get an inside look at how we’re building the home for all developers. - [Architecture & optimization](https://github.blog/engineering/architecture-optimization/) Discover how we deliver a performant and highly available experience across the GitHub platform. - [Engineering principles](https://github.blog/engineering/engineering-principles/) Explore best practices for building software at scale with a majority remote team. - [Infrastructure](https://github.blog/engineering/infrastructure/) Get a glimpse at the technology underlying the world’s leading AI-powered developer platform. - [Platform security](https://github.blog/engineering/platform-security/) Learn how we build security into everything we do across the developer lifecycle. - [User experience](https://github.blog/engineering/user-experience/) Find out what goes into making GitHub the home for all developers. - ![](https://github.blog/wp-content/uploads/2024/07/Screenshot-2024-07-23-at-8.42.45%E2%80%AFAM.png?resize=800%2C425) [How we use GitHub to be more productive, collaborative, and secure](https://github.blog/engineering/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](https://github.blog/enterprise-software/) - [Enterprise software](https://github.blog/enterprise-software/) Explore how to write, build, and deploy enterprise software at scale. - [Automation](https://github.blog/enterprise-software/automation/) Automating your way to faster and more secure ships. - [CI/CD](https://github.blog/enterprise-software/ci-cd/) Guides on continuous integration and delivery. - [Collaboration](https://github.blog/enterprise-software/collaboration/) Tips, tools, and tricks to improve developer collaboration. - [DevOps](https://github.blog/enterprise-software/devops/) DevOps resources for enterprise engineering teams. - [DevSecOps](https://github.blog/enterprise-software/devsecops/) How to integrate security into the SDLC. - [Governance & compliance](https://github.blog/enterprise-software/governance-and-compliance/) Ensuring your builds stay clean. - ![](https://github.blog/wp-content/uploads/2024/07/Screenshot-2024-07-23-at-8.43.47%E2%80%AFAM.png?resize=800%2C425) [GitHub recognized as a Leader in the Gartner® Magic Quadrant™ for AI Code Assistants](https://github.com/resources/whitepapers/gartner-magic-quadrant-and-critical-capabilities-for-ai-code-assistants) Learn why Gartner positioned GitHub as a Leader for the second year in a row. Learn more - [News & insights](https://github.blog/news-insights/) - [News & insights](https://github.blog/news-insights/) Keep up with what’s new and notable from inside GitHub. - [Company news](https://github.blog/news-insights/company-news/) An inside look at news and product updates from GitHub. - [Product](https://github.blog/news-insights/product-news/) The latest on GitHub’s platform, products, and tools. - [Octoverse](https://github.blog/news-insights/octoverse/) Insights into the state of open source on GitHub. - [Policy](https://github.blog/news-insights/policy-news-and-insights/) The latest policy and regulatory changes in software. - [Research](https://github.blog/news-insights/research/) Data-driven insights around the developer ecosystem. - [The library](https://github.blog/news-insights/the-library/) Older news and updates from GitHub. - ![](https://github.blog/wp-content/uploads/2024/07/Screenshot-2024-07-23-at-8.44.23%E2%80%AFAM.png?resize=800%2C425) [Unlocking the power of unstructured data with RAG](https://github.blog/ai-and-ml/llms/unlocking-the-power-of-unstructured-data-with-rag/) Learn how to use retrieval-augmented generation (RAG) to capture more insights. Learn more - [Open Source](https://github.blog/open-source/) - [Open Source](https://github.blog/open-source/) Everything open source on GitHub. - [Git](https://github.blog/open-source/git/) The latest Git updates. - [Maintainers](https://github.blog/open-source/maintainers/) Spotlighting open source maintainers. - [Social impact](https://github.blog/open-source/social-impact/) How open source is driving positive change. - [Gaming](https://github.blog/open-source/gaming/) Explore open source games on GitHub. - ![](https://github.blog/wp-content/uploads/2024/07/Screenshot-2024-07-23-at-8.46.23%E2%80%AFAM.png?resize=800%2C425) [An introduction to innersource](https://resources.github.com/software-development/innersource/) Organizations worldwide are incorporating open source methodologies into the way they build and ship their own software. Learn more - [Security](https://github.blog/security/) - [Security](https://github.blog/security/) Stay up to date on everything security. - [Application security](https://github.blog/security/application-security/) Application security, explained. - [Supply chain security](https://github.blog/security/supply-chain-security/) Demystifying supply chain security. - [Vulnerability research](https://github.blog/security/vulnerability-research/) Updates from the GitHub Security Lab. - [Web application security](https://github.blog/security/web-application-security/) Helpful tips on securing web applications. - ![](https://github.blog/wp-content/uploads/2024/07/Screenshot-2024-07-23-at-8.47.04%E2%80%AFAM.png?resize=800%2C425) [The enterprise guide to AI-powered DevSecOps](https://resources.github.com/security/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 ## Categories - [AI & ML](https://github.blog/ai-and-ml/) - Back [AI & ML](https://github.blog/ai-and-ml/) Learn about artificial intelligence and machine learning across the GitHub ecosystem and the wider industry. - [Generative AI](https://github.blog/ai-and-ml/generative-ai/) Learn how to build with generative AI. - [GitHub Copilot](https://github.blog/ai-and-ml/github-copilot/) Change how you work with GitHub Copilot. - [LLMs](https://github.blog/ai-and-ml/llms/) Everything developers need to know about LLMs. - [Machine learning](https://github.blog/ai-and-ml/machine-learning/) Machine learning tips, tricks, and best practices. - [How AI code generation works](https://github.blog/ai-and-ml/generative-ai/how-ai-code-generation-works/) Explore the capabilities and benefits of AI code generation and how it can improve your developer experience. [Learn more](https://github.blog/ai-and-ml/generative-ai/how-ai-code-generation-works/) - [Developer skills](https://github.blog/developer-skills/) - Back [Developer skills](https://github.blog/developer-skills/) Resources for developers to grow in their skills and careers. - [Application development](https://github.blog/developer-skills/application-development/) Insights and best practices for building apps. - [Career growth](https://github.blog/developer-skills/career-growth/) Tips & tricks to grow as a professional developer. - [GitHub](https://github.blog/developer-skills/github/) Improve how you use GitHub at work. - [GitHub Education](https://github.blog/developer-skills/github-education/) Learn how to move into your first professional role. - [Programming languages & frameworks](https://github.blog/developer-skills/programming-languages-and-frameworks/) Stay current on what’s new (or new again). - [Get started with GitHub documentation](https://docs.github.com/en/get-started) Learn how to start building, shipping, and maintaining software with GitHub. [Learn more](https://docs.github.com/en/get-started) - [Engineering](https://github.blog/engineering/) - Back [Engineering](https://github.blog/engineering/) Get an inside look at how we’re building the home for all developers. - [Architecture & optimization](https://github.blog/engineering/architecture-optimization/) Discover how we deliver a performant and highly available experience across the GitHub platform. - [Engineering principles](https://github.blog/engineering/engineering-principles/) Explore best practices for building software at scale with a majority remote team. - [Infrastructure](https://github.blog/engineering/infrastructure/) Get a glimpse at the technology underlying the world’s leading AI-powered developer platform. - [Platform security](https://github.blog/engineering/platform-security/) Learn how we build security into everything we do across the developer lifecycle. - [User experience](https://github.blog/engineering/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](https://github.blog/engineering/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](https://github.blog/engineering/how-we-use-github-to-be-more-productive-collaborative-and-secure/) - [Enterprise software](https://github.blog/enterprise-software/) - Back [Enterprise software](https://github.blog/enterprise-software/) Explore how to write, build, and deploy enterprise software at scale. - [Automation](https://github.blog/enterprise-software/automation/) Automating your way to faster and more secure ships. - [CI/CD](https://github.blog/enterprise-software/ci-cd/) Guides on continuous integration and delivery. - [Collaboration](https://github.blog/enterprise-software/collaboration/) Tips, tools, and tricks to improve developer collaboration. - [DevOps](https://github.blog/enterprise-software/devops/) DevOps resources for enterprise engineering teams. - [DevSecOps](https://github.blog/enterprise-software/devsecops/) How to integrate security into the SDLC. - [Governance & compliance](https://github.blog/enterprise-software/governance-and-compliance/) Ensuring your builds stay clean. - [GitHub recognized as a Leader in the Gartner® Magic Quadrant™ for AI Code Assistants](https://github.com/resources/whitepapers/gartner-magic-quadrant-and-critical-capabilities-for-ai-code-assistants) Learn why Gartner positioned GitHub as a Leader for the second year in a row. [Learn more](https://github.com/resources/whitepapers/gartner-magic-quadrant-and-critical-capabilities-for-ai-code-assistants) - [News & insights](https://github.blog/news-insights/) - Back [News & insights](https://github.blog/news-insights/) Keep up with what’s new and notable from inside GitHub. - [Company news](https://github.blog/news-insights/company-news/) An inside look at news and product updates from GitHub. - [Product](https://github.blog/news-insights/product-news/) The latest on GitHub’s platform, products, and tools. - [Octoverse](https://github.blog/news-insights/octoverse/) Insights into the state of open source on GitHub. - [Policy](https://github.blog/news-insights/policy-news-and-insights/) The latest policy and regulatory changes in software. - [Research](https://github.blog/news-insights/research/) Data-driven insights around the developer ecosystem. - [The library](https://github.blog/news-insights/the-library/) Older news and updates from GitHub. - [Unlocking the power of unstructured data with RAG](https://github.blog/ai-and-ml/llms/unlocking-the-power-of-unstructured-data-with-rag/) Learn how to use retrieval-augmented generation (RAG) to capture more insights. [Learn more](https://github.blog/ai-and-ml/llms/unlocking-the-power-of-unstructured-data-with-rag/) - [Open Source](https://github.blog/open-source/) - Back [Open Source](https://github.blog/open-source/) Everything open source on GitHub. - [Git](https://github.blog/open-source/git/) The latest Git updates. - [Maintainers](https://github.blog/open-source/maintainers/) Spotlighting open source maintainers. - [Social impact](https://github.blog/open-source/social-impact/) How open source is driving positive change. - [Gaming](https://github.blog/open-source/gaming/) Explore open source games on GitHub. - [An introduction to innersource](https://resources.github.com/software-development/innersource/) Organizations worldwide are incorporating open source methodologies into the way they build and ship their own software. [Learn more](https://resources.github.com/software-development/innersource/) - [Security](https://github.blog/security/) - Back [Security](https://github.blog/security/) Stay up to date on everything security. - [Application security](https://github.blog/security/application-security/) Application security, explained. - [Supply chain security](https://github.blog/security/supply-chain-security/) Demystifying supply chain security. - [Vulnerability research](https://github.blog/security/vulnerability-research/) Updates from the GitHub Security Lab. - [Web application security](https://github.blog/security/web-application-security/) Helpful tips on securing web applications. - [The enterprise guide to AI-powered DevSecOps](https://resources.github.com/security/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](https://resources.github.com/security/the-enterprise-guide-to-ai-powered-devsecops/) - [Changelog](https://github.blog/changelog/) - [Docs](https://docs.github.com/) - [Customer stories](https://github.com/customer-stories) [See what's new](https://github.com/events/universe/recap?utm_source=k2k-blog-tap-nav&utm_medium=blog&utm_campaign=universe25) [Try GitHub Copilot](https://github.com/features/copilot?utm_source=blog-tap-nav&utm_medium=blog&utm_campaign=universe25) [Home](https://github.blog/) / [AI & ML](https://github.blog/ai-and-ml/) / [GitHub Copilot](https://github.blog/ai-and-ml/github-copilot/) # 60 million Copilot code reviews and counting How Copilot code review helps teams keep up with AI-accelerated code changes. ![Copilot appears among floating cubes alongside a refresh icon, suggesting an update or automated workflow theme.](https://github.blog/wp-content/uploads/2026/01/generic-github-copilot-logo.png?resize=1600%2C850) [Ria Gopu](https://github.blog/author/ria-gopu/ "Posts by Ria Gopu") & [David Apirian](https://github.blog/author/dapirian/ "Posts by 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. ![Copilot code review comment identifying a missing dependency in a React useCallback hook and suggesting a code change to add handleKeyboardDrag to the dependency array.](https://github.blog/wp-content/uploads/2026/03/Screenshot-2026-03-05-at-10.29.41-AM.png?resize=1024%2C435) ### 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: ![Copilot code review comment warning that a retry loop could run indefinitely when an API returns HTTP 429 without a Retry-After header and suggesting adding a retry limit and backoff.](https://github.blog/wp-content/uploads/2026/03/Screenshot-2026-03-05-at-11.07.14-AM.png?resize=1024%2C289) 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 code review: AI code review agent that understands your codebase Copilot code review helps you catch bugs, improve readability, and speed up pull request feedback with AI suggestions right where you work on GitHub. It fits into your existing pull request workflow, so your team can ship faster with more confidence. [👉 Get started with Copilot code review on GitHub \>](https://docs.github.com/en/copilot/get-started/quickstart) ## About the agentic architecture Given our new definition of “good,” we redeveloped our code review system. Today’s agentic design can retrieve context intelligently and explore the repository to understand logic, architecture, and specific invariants. This shift alone has driven an initial 8.1% increase in positive feedback. Here’s why: - It catches issues as it reads, not just at the end: Previously, agents waited until the end of a review to finalize results, which often led to “forgetting” early discoveries. - It can maintain memory across reviews: Now, every pull request doesn’t need to be an isolated event. If it flags a pattern in one part of the codebase, it can reuse that context in future reviews. - It keeps long pull requests reviewable with an explicit plan: It can map out its review strategy ahead of time, significantly improving its performance on long, complex pull requests, where context is easily lost. - It reads linked issues and pull requests: That extra context helps it flag subtle gaps. This includes cases where the code looks reasonable in isolation but doesn’t match the project’s requirements. ## Making reviews easier to navigate By iterating on how the agent interacts with pull requests, we’ve reduced noise and made feedback more actionable. Here’s what that means for you. - Quickly understand feedback (and the fix) with multi-line comments: We moved away from pinning comments to single lines. By attaching feedback to logical code ranges, Copilot makes it easier to see what it’s referring to and apply the suggested change. ![Copilot code review comment on a GitHub Actions workflow identifying a missing use\_caches input parameter and suggesting a code change to add the boolean input to the workflow configuration.](https://github.blog/wp-content/uploads/2026/03/Screenshot-2026-02-01-at-3.30.41-PM.png?resize=1024%2C1010) - Keep your pull request timeline readable: Instead of multiple separate comments for the same pattern error, which can be overwhelming, the agent clusters them into a single, cohesive unit to reduce cognitive load. - Fix whole classes of issues at once with batch autofixes: Apply suggested fixes in batches, resolving an entire class of logic bugs or style issues at once, rather than context-switching through a dozen individual suggestions. ## Take this with you As AI continues to accelerate software development, it’s more important than ever to help teams review and trust code at scale. Copilot code review helps teams keep pace by surfacing high-signal feedback directly in pull requests, enabling developers to catch issues earlier and merge with greater confidence. More than 12,000 organizations now run Copilot code review automatically on every pull request. At WEX, this shift toward default AI –assisted reviews has helped scale Copilot adoption across the engineering organization: Today, two-thirds of developers are using Copilot — including the organization’s most active contributors. WEX has since expanded adoption by making Copilot code review a default across every repository. Developers are also heavily utilizing agent mode and the coding agent to drive autonomy, helping WEX see a huge lift in deployments, with ~30% more code shipped. — [WEX customer story](https://github.com/customer-stories/wex) Going forward, we’re focused on deeper personalization and high-fidelity interactivity, refining the agent to learn your team’s unwritten preferences while enabling two-way conversations that let you refine fixes and explore alternatives before merging. As Copilot capabilities continue to evolve, from coding and planning to review and automation, the goal is simple: help developers move faster while maintaining the trust and quality that great software demands. ## Get started today Copilot code review is a premium feature available with Copilot Pro, Copilot Pro+, Copilot Business, and Copilot Enterprise. See the following resources to: - [Choose a plan](https://docs.github.com/en/copilot/get-started/plans#ready-to-choose-a-plan) - [Enable Copilot code review without a Copilot license](https://docs.github.com/en/copilot/concepts/agents/code-review#copilot-code-review-without-a-copilot-license) - [Watch a demo video](https://youtu.be/HDEGFNAUkX8?si=s9DauqsFZCdtpCtI) Already enabled Copilot code review? See these docs to [set up automatic Copilot code reviews on every pull request](https://docs.github.com/en/copilot/how-tos/use-copilot-agents/request-a-code-review/configure-automatic-review) within your repository or organization. Have thoughts or feedback? Please let us know in our [community discussion post](https://github.com/orgs/community/discussions/186303). *** ## Tags: - [code quality](https://github.blog/tag/code-quality/) - [GitHub Actions](https://github.blog/tag/github-actions/) - [GitHub Copilot](https://github.blog/tag/github-copilot/) - [GitHub Copilot code review](https://github.blog/tag/github-copilot-code-review/) ## Written by ![Ria Gopu](https://avatars.githubusercontent.com/u/189655821?v=4&s=200) ### [Ria Gopu](https://github.blog/author/ria-gopu/) [@ria-gopu](https://github.com/ria-gopu) GitHub Product Manager ![David Apirian](https://avatars.githubusercontent.com/u/3904462?v=4&s=200) ### [David Apirian](https://github.blog/author/dapirian/) [@dapirian](https://github.com/dapirian) Senior Director, Software Engineering - [code quality](https://github.blog/tag/code-quality/) - [GitHub Actions](https://github.blog/tag/github-actions/) - [GitHub Copilot](https://github.blog/tag/github-copilot/) - [GitHub Copilot code review](https://github.blog/tag/github-copilot-code-review/) ## Table of Contents - [Redefining a “good” code review](https://github.blog/ai-and-ml/github-copilot/60-million-copilot-code-reviews-and-counting/#h-redefining-a-good-code-review) - [Try Copilot code review: AI code review agent that understands your codebase](https://github.blog/ai-and-ml/github-copilot/60-million-copilot-code-reviews-and-counting/#h-try-copilot-code-review-ai-code-review-agent-that-understands-your-codebase) - [About the agentic architecture](https://github.blog/ai-and-ml/github-copilot/60-million-copilot-code-reviews-and-counting/#h-about-the-agentic-architecture) - [Making reviews easier to navigate](https://github.blog/ai-and-ml/github-copilot/60-million-copilot-code-reviews-and-counting/#h-making-reviews-easier-to-navigate) - [Take this with you](https://github.blog/ai-and-ml/github-copilot/60-million-copilot-code-reviews-and-counting/#h-take-this-with-you) - [Get started today](https://github.blog/ai-and-ml/github-copilot/60-million-copilot-code-reviews-and-counting/#h-get-started-today) ## More on [code quality](https://github.blog/tag/code-quality/) ### [Does GitHub Copilot improve code quality? Here’s what the data says](https://github.blog/news-insights/research/does-github-copilot-improve-code-quality-heres-what-the-data-says/) Findings in our latest study show that the quality of code written with GitHub Copilot is significantly more functional, readable, reliable, maintainable, and concise. [Jared Bauer](https://github.blog/author/jaredsb/ "Posts by Jared Bauer") ## Related posts ![Copilot CLI welcome screen](https://github.blog/wp-content/uploads/2026/02/554396112-02305897-302e-435b-862b-616faea6a7f5.png?resize=400%2C212) [AI & ML](https://github.blog/ai-and-ml/) ### [Run multiple agents at once with /fleet in Copilot CLI](https://github.blog/ai-and-ml/github-copilot/run-multiple-agents-at-once-with-fleet-in-copilot-cli/) /fleet lets Copilot CLI dispatch multiple agents in parallel. Learn how to write prompts that split work across files, declare dependencies, and avoid common pitfalls. [Matt Nigh](https://github.blog/author/mattnigh/ "Posts by Matt Nigh") & [Brian LaFlamme](https://github.blog/author/briancl2/ "Posts by Brian LaFlamme") ![Decorative background featuring two Copilot figures moving among abstract green and translucent blocks.](https://github.blog/wp-content/uploads/2026/01/generic-mona-copilot-logo.png?resize=400%2C212) [AI & ML](https://github.blog/ai-and-ml/) ### [Agent-driven development in Copilot Applied Science](https://github.blog/ai-and-ml/github-copilot/agent-driven-development-in-copilot-applied-science/) I used coding agents to build agents that automated part of my job. Here’s what I learned about working better with coding agents. [Tyler McGoffin](https://github.blog/author/jtmcg/ "Posts by Tyler McGoffin") ![Copilot hovering beside a cluster of geometric cubes in a decorative scene.](https://github.blog/wp-content/uploads/2026/01/generic-copilot-logo-github.png?resize=400%2C212) [AI & ML](https://github.blog/ai-and-ml/) ### [Building AI-powered GitHub issue triage with the Copilot SDK](https://github.blog/ai-and-ml/github-copilot/building-ai-powered-github-issue-triage-with-the-copilot-sdk/) Learn how to integrate the Copilot SDK into a React Native app to generate AI-powered issue summaries, with production patterns for graceful degradation and caching. [Andrea Griffiths](https://github.blog/author/andreagriffiths11/ "Posts by Andrea Griffiths") ## Explore more from GitHub ![Docs](https://github.blog/wp-content/uploads/2024/07/Icon-Circle.svg) ### Docs Everything you need to master GitHub, all in one place. [Go to Docs](https://docs.github.com/) ![GitHub](https://github.blog/wp-content/uploads/2024/07/recirculation-github-icon.svg) ### GitHub Build what’s next on GitHub, the place for anyone from anywhere to build anything. [Start building](https://github.com/) ![Customer stories](https://github.blog/wp-content/uploads/2024/07/Icon_da43dc.svg) ### Customer stories Meet the companies and engineering teams that build with GitHub. [Learn more](https://github.com/customer-stories) ![The GitHub Podcast](https://github.blog/wp-content/uploads/2023/02/galaxy23-icon.svg) ### The GitHub Podcast Catch up on the GitHub podcast, a show dedicated to the topics, trends, stories and culture in and around the open source developer community on GitHub. [Listen now](https://the-github-podcast.simplecast.com/) ## We do newsletters, too Discover tips, technical guides, and best practices in our biweekly newsletter just for devs. Your email address ## Site-wide Links ### Product - [Features](https://github.com/features) - [Security](https://github.com/security) - [Enterprise](https://github.com/enterprise) - [Customer Stories](https://github.com/customer-stories?type=enterprise) - [Pricing](https://github.com/pricing) - [Resources](https://resources.github.com/) ### Platform - [Developer API](https://developer.github.com/) - [Partners](https://partner.github.com/) - [Atom](https://atom.io/) - [Electron](https://www.electronjs.org/) - [GitHub Desktop](https://desktop.github.com/) ### Support - [Docs](https://docs.github.com/) - [Community Forum](https://github.community/) - [Training](https://services.github.com/) - [Status](https://www.githubstatus.com/) - [Contact](https://support.github.com/) ### Company - [About](https://github.com/about) - [Blog](https://github.blog/) - [Careers](https://github.com/about/careers) - [Press](https://github.com/about/press) - [Shop](https://shop.github.com/) - © 2026 GitHub, Inc. - [Terms](https://docs.github.com/en/github/site-policy/github-terms-of-service) - [Privacy](https://docs.github.com/en/github/site-policy/github-privacy-statement) - Manage Cookies - Do not share my personal information - [GitHub on LinkedIn](https://www.linkedin.com/company/github) - [GitHub on Instagram](https://www.instagram.com/github/) - [GitHub on YouTube](https://www.youtube.com/github) - [GitHub on X](https://twitter.com/github) - [GitHub on TikTok](https://www.tiktok.com/@github) - [GitHub on Twitch](https://www.twitch.tv/github) - [GitHub’s organization on GitHub](https://github.com/github)
Readable Markdown	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. ![Copilot code review comment identifying a missing dependency in a React useCallback hook and suggesting a code change to add handleKeyboardDrag to the dependency array.](https://github.blog/wp-content/uploads/2026/03/Screenshot-2026-03-05-at-10.29.41-AM.png?resize=1024%2C435) ### 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: ![Copilot code review comment warning that a retry loop could run indefinitely when an API returns HTTP 429 without a Retry-After header and suggesting adding a retry limit and backoff.](https://github.blog/wp-content/uploads/2026/03/Screenshot-2026-03-05-at-11.07.14-AM.png?resize=1024%2C289) 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. ## About the agentic architecture Given our new definition of “good,” we redeveloped our code review system. Today’s agentic design can retrieve context intelligently and explore the repository to understand logic, architecture, and specific invariants. This shift alone has driven an initial 8.1% increase in positive feedback. Here’s why: - It catches issues as it reads, not just at the end: Previously, agents waited until the end of a review to finalize results, which often led to “forgetting” early discoveries. - It can maintain memory across reviews: Now, every pull request doesn’t need to be an isolated event. If it flags a pattern in one part of the codebase, it can reuse that context in future reviews. - It keeps long pull requests reviewable with an explicit plan: It can map out its review strategy ahead of time, significantly improving its performance on long, complex pull requests, where context is easily lost. - It reads linked issues and pull requests: That extra context helps it flag subtle gaps. This includes cases where the code looks reasonable in isolation but doesn’t match the project’s requirements. ## Making reviews easier to navigate By iterating on how the agent interacts with pull requests, we’ve reduced noise and made feedback more actionable. Here’s what that means for you. - Quickly understand feedback (and the fix) with multi-line comments: We moved away from pinning comments to single lines. By attaching feedback to logical code ranges, Copilot makes it easier to see what it’s referring to and apply the suggested change. ![Copilot code review comment on a GitHub Actions workflow identifying a missing use\_caches input parameter and suggesting a code change to add the boolean input to the workflow configuration.](https://github.blog/wp-content/uploads/2026/03/Screenshot-2026-02-01-at-3.30.41-PM.png?resize=1024%2C1010) - Keep your pull request timeline readable: Instead of multiple separate comments for the same pattern error, which can be overwhelming, the agent clusters them into a single, cohesive unit to reduce cognitive load. - Fix whole classes of issues at once with batch autofixes: Apply suggested fixes in batches, resolving an entire class of logic bugs or style issues at once, rather than context-switching through a dozen individual suggestions. ## Take this with you As AI continues to accelerate software development, it’s more important than ever to help teams review and trust code at scale. Copilot code review helps teams keep pace by surfacing high-signal feedback directly in pull requests, enabling developers to catch issues earlier and merge with greater confidence. More than 12,000 organizations now run Copilot code review automatically on every pull request. At WEX, this shift toward default AI –assisted reviews has helped scale Copilot adoption across the engineering organization: Today, two-thirds of developers are using Copilot — including the organization’s most active contributors. WEX has since expanded adoption by making Copilot code review a default across every repository. Developers are also heavily utilizing agent mode and the coding agent to drive autonomy, helping WEX see a huge lift in deployments, with ~30% more code shipped. — [WEX customer story](https://github.com/customer-stories/wex) Going forward, we’re focused on deeper personalization and high-fidelity interactivity, refining the agent to learn your team’s unwritten preferences while enabling two-way conversations that let you refine fixes and explore alternatives before merging. As Copilot capabilities continue to evolve, from coding and planning to review and automation, the goal is simple: help developers move faster while maintaining the trust and quality that great software demands. ## Get started today Copilot code review is a premium feature available with Copilot Pro, Copilot Pro+, Copilot Business, and Copilot Enterprise. See the following resources to: - [Choose a plan](https://docs.github.com/en/copilot/get-started/plans#ready-to-choose-a-plan) - [Enable Copilot code review without a Copilot license](https://docs.github.com/en/copilot/concepts/agents/code-review#copilot-code-review-without-a-copilot-license) - [Watch a demo video](https://youtu.be/HDEGFNAUkX8?si=s9DauqsFZCdtpCtI) Already enabled Copilot code review? See these docs to [set up automatic Copilot code reviews on every pull request](https://docs.github.com/en/copilot/how-tos/use-copilot-agents/request-a-code-review/configure-automatic-review) within your repository or organization. Have thoughts or feedback? Please let us know in our [community discussion post](https://github.com/orgs/community/discussions/186303). *** ## Tags: - [code quality](https://github.blog/tag/code-quality/) - [GitHub Actions](https://github.blog/tag/github-actions/) - [GitHub Copilot](https://github.blog/tag/github-copilot/) - [GitHub Copilot code review](https://github.blog/tag/github-copilot-code-review/) ## Written by ![Ria Gopu](https://avatars.githubusercontent.com/u/189655821?v=4&s=200) GitHub Product Manager ![David Apirian](https://avatars.githubusercontent.com/u/3904462?v=4&s=200) Senior Director, Software Engineering ## Explore more from GitHub ![Docs](https://github.blog/wp-content/uploads/2024/07/Icon-Circle.svg) ### Docs Everything you need to master GitHub, all in one place. [Go to Docs](https://docs.github.com/) ![GitHub](https://github.blog/wp-content/uploads/2024/07/recirculation-github-icon.svg) ### GitHub Build what’s next on GitHub, the place for anyone from anywhere to build anything. [Start building](https://github.com/) ![Customer stories](https://github.blog/wp-content/uploads/2024/07/Icon_da43dc.svg) ### Customer stories Meet the companies and engineering teams that build with GitHub. [Learn more](https://github.com/customer-stories) ![The GitHub Podcast](https://github.blog/wp-content/uploads/2023/02/galaxy23-icon.svg) ### The GitHub Podcast Catch up on the GitHub podcast, a show dedicated to the topics, trends, stories and culture in and around the open source developer community on GitHub. [Listen now](https://the-github-podcast.simplecast.com/)
Shard	129 (laksa)
Root Hash	7620767358965441529
Unparsed URL	blog,github!/ai-and-ml/github-copilot/60-million-copilot-code-reviews-and-counting/ s443