AI news for builders and product teamsUpdated Nov 17, 2026, 13:01 UTC
GitHub Blog · AI & ML
First-party releases and research from GitHub Blog · AI & ML. Headlines and excerpts link to the original articles.
Latest stories
Newest first
GitHub published a practical guide to agent skills — versioned directories built around a SKILL.md file that capture repeatable task instructions — based on a GitHub Universe 2026 session with Shishir Tewari, Senior Manager of Data Engineering at Procore.

GitHub reports more than 1.2 billion commits in a single week in October, over 400% above a year earlier, but cites a Faros AI study showing pull requests sat 441% longer in review as teams moved from low to high AI adoption. Its guide argues the fix is agentic workflows spanning Plan, Build, Verify and Observe rather than faster code generation alone.

A GitHub blog post profiles three Java Champions—Vlad Mihalcea, Patrick Baumgartner and Frank Delporte—describing how they use GitHub Copilot in production and open source, from cutting a web app build from weeks to two days to migrating roughly 900 teaching slides in eight to ten hours.

GitHub has published research on a model for secret detection aimed at finding more leaked credentials with less noise, alongside related posts on Copilot customization and bug bounty methodology.

GitHub's beginner guide explains four ways to give Copilot repository context: custom instruction files, agent skills, custom agents, and MCP servers, each living in a dot-github folder.

GitHub reports that one in three pull requests now involves an AI agent, up from fewer than one in 10 a year ago, and has built a fine-tuned classifier with Microsoft Applied Sciences that extends push protection to unstructured secrets, assessing candidates in under two milliseconds.

GitHub has launched ReviewBench, an open benchmark for evaluating AI code review systems, modeled on over 100 million real pull requests and validated by senior engineers.

A GitHub Blog post outlines three skills for developers as AI changes their work: directing AI agents, reviewing AI output rather than trusting the first answer, and using saved implementation time on broader problems.

The GitHub Blog published a beginner's guide to creating customizable interfaces called canvases in the GitHub Copilot app using the /create-canvas skill. Users describe a desired workflow in plain English and the agent builds the interface, which can be refined, saved as an extension, and shared with a team.

GitHub introduced Project HydraFusion, a research preview available on all GitHub Copilot plans through /experimental in GitHub Copilot CLI. It orchestrates models across providers at runtime, selecting among Single, Cascade, and Critique execution patterns based on task needs.

GitHub published a beginner-focused post describing how its Copilot app lets developers run multiple agent sessions at once, each on its own Git worktree. The post walks through running three tasks in parallel in an example repository and includes a call to get started with the app.