Four deployable reference scenarios to govern GitHub Copilot and custom AI agents like any other enterprise actor: identity, audit, per-team cost, safety, quality evals, and per-PR agent-vs-human attribution. Azure AI Foundry, APIM AI Gateway, App Insights, OpenTelemetry
4 files for Claude Code, Codex and OpenCode: corp, fraud-analyst, legal-counsel, agent-eval-poc AGENTS.md — 884 tokens loaded in every session.
AGENTS.md A 884 tok .github/agents/corp.agent.md A 75 tok .github/agents/fraud-analyst.agent.md A 74 tok .github/agents/legal-counsel.agent.md A 76 tok These files are jmfloreszazo/agent-eval-poc's own configuration — they tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.