When Copilot cloud agent writes code, it automatically runs GitHub’s security and quality validation tools, including CodeQL, the GitHub Advisory Database, secret scanning, and Copilot code review. If any problems are found, Copilot attempts to resolve them before finishing work and requesting review.

These validation tools now run in parallel rather than sequentially, reducing validation time by 20%. This means Copilot works faster while still maintaining the same quality.

You can configure which validation tools the cloud agent runs from the Copilot -> Cloud agent section in repository settings.

To learn more, head to our Copilot cloud agent documentation.