CI Integration #11

Objective

Demonstrate how evaluation becomes a CI gate in real workflows.

Scope

Provide a reference GitHub Actions workflow that runs evaluation automatically.

Tasks

• Create GitHub Actions workflow:

  • Install toolkit
  • Run evaluation
  • Upload results as artifacts

• Ensure failure blocks PR if thresholds are not met

• Document CI usage in README

Acceptance Criteria

• PR triggers evaluation
• Evaluation artifacts available for download
• PR fails when thresholds fail

Out of Scope

• Multi-environment CI
• Azure DevOps pipelines
• Observability export