60 million Copilot code reviews and counting
Since GitHub Blog's 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.
Academic or research source. Check the methodology, sample size, and whether it's been replicated.
Key Takeaways
- Major industry investment.
- Behind the scenes, GitHub Blog’ve been running continuous experiments to enhance comment quality.
- GitHub Blog also moved to an agentic architecture that retrieves repository context and reasons across changes.
What It Means
Context
Behind the scenes, GitHub Blog’ve been running continuous experiments to enhance comment quality. GitHub Blog also moved to an agentic architecture that retrieves repository context and reasons across changes. At every step of the way, GitHub Blog’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 GitHub Blog's 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 GitHub Blog's definition of a “good code review.” When GitHub Blog started building it in 2024, GitHub Blog's goal was simple thoroughness. Since then, GitHub Blog’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, GitHub Blog’ve used a continuous evaluation…
For builders
Behind the scenes, GitHub Blog’ve been running continuous experiments to enhance comment quality.
For Builders
Behind the scenes, GitHub Blog’ve been running continuous experiments to enhance comment quality.