Technology

local evaluation

1 synchronized story carry this tag.

GitHub Copilot Evals enters public preview with local Vally runs

GitHub Copilot Evals can create repeatable tests for skills, custom agents and MCP tools, require approval before each run, show passed and failed checks and compare behavior before and after a customization change. It uses the extensible local Vally engine.

Why it matters: Teams gain a productized regression loop for agent customizations rather than relying on one successful prompt, but local execution still needs trustworthy tasks, graders and environment isolation.

Read storyOriginal source · github.blog