Agent-Ready Evaluation

Evaluate how well a codebase supports autonomous agent execution based on the "How to Get Out of Your Agent's Way" principles.

Core Philosophy

Autonomous agents fail for predictable reasons—most are system design failures, not model failures. This evaluation checks whether infrastructure enables true autonomy: agents that run unattended, isolated, reproducible, and bounded by system constraints rather than human intervention.

Evaluation Process

1. Gather Evidence

Explore the codebase for indicators across all 12 principles. Key files to examine:

Environment & Isolation:

• Dockerfile, docker-compose.yml, .devcontainer/
• Makefile, setup.sh, bootstrap.sh
• CI configs (.github/workflows/, .gitlab-ci.yml, Jenkinsfile)
• Nix files, devbox.json, flake.nix