Search results for: organization

AI can help you code faster, but knowing why the code works—and sharpening your human-in-the-loop skills—is what makes you a great developer.

We’ve introduced a new Dependabot metrics section in the Security tab, available at the organization level. This update helps application security managers cut through the noise and focus on remediating…

We’ve launched an enhanced ruleset selection experience for organization and enterprise rulesets, simplifying the process of finding and targeting the right repositories. Teams and Enterprise plan users can now leverage…

GitHub Desktop 3.5 is now generally available! This update marks a major milestone for GitHub Desktop, and we’re thrilled to highlight some of the improvements and features we’ve added recently.…

GitHub is consolidating Dependabot’s compute platform to GitHub Actions, and jobs that generate pull requests will be run as GitHub Actions workflows. This allows Dependabot to leverage GitHub Actions infrastructure,…

You can now add issues and pull requests as context in Copilot Spaces. Create a space and simply paste in the URL—the space will pull in the latest title, body,…

Last month, we launched GitHub Copilot coding agent (Public Preview), allowing users with Copilot Pro+ and Copilot Enterprise to delegate tasks to Copilot to work on in the background. Users…

Monthly premium request allowances for paid GitHub Copilot users are now in effect. What’s changed: The monthly allowance of premium requests per user for Copilot Pro, Pro+, Business, and Enterprise…

GitHub Models evaluations tooling now supports multiple variables with any names, not just {{input}}! Previously, the tooling only recognized a single variable named {{input}}. Prompts using variables like {{experience}} or…

Reduce context-switching, minimize manual work, and accelerate resolution times with these new AI-powered features.

Copilot code review now supports the same custom instructions used by Copilot Chat and coding agent—unlocking personalized, consistent AI reviews across your workflow.

You can now save and evaluate multi-turn conversations in the GitHub Models prompt editor and evaluations tooling! Until now, the evaluations tooling only supported a single user prompt. With this…

The GitHub MCP Server allows AI tools like GitHub Copilot in VS Code and Visual Studio, Claude Desktop, and others to seamlessly access live GitHub context and tools—like issues, pull…

We’ve enhanced scheduled reminders for Slack and Microsoft Teams to give you more control and ensure you’re focused on what matters most. These updates include: Receiving reminders for up to…

CodeQL can now access private dependencies stored in private registries for Go projects. This makes your scans more comprehensive, helping to ensure you receive all important alerts regardless of where…

Our best practices for quickly identifying, resolving, and preventing issues at scale.

You can now assign teams as the app managers of some or all of your organization’s GitHub Apps. The App Manager role has been converted to a standard organization role,…

Learn how to use GitHub Copilot to help review and polish your code.

You can now run prompt evaluations from the command line using the new gh models eval command. This evaluates prompts defined in a .prompt.yml file using the same built-in evaluators…

Evaluators are like continuous integration for your AI. They help you catch quality issues early and keep outputs aligned with your goals. Today, GitHub Models is adding two new scoring…