The eval harness your team keeps

At handover the Python runner, regression detector and CI/CD configs are yours. Zero ongoing dependency to keep testing.

The golden dataset — 100+ SME-reviewed Q-A-context records — is versioned and refreshed every 60 days or whenever your knowledge base changes. Yours to extend and re-run forever.

CI/CD gates fire on every commit, so regressions are caught before deploy, not after. Testing becomes part of how you ship.