Technology subcategory
Evaluations
Harnesses and judges that score agent or model behavior before and after change.
Evaluations packs measure whether an agent or model got better or worse. They are the falsifiers for autonomy claims.
Without evals, “we added an agent” cannot be distinguished from noise. Pair with Observability for traces and Guardrails for hard policy stops.
See also
Technologies
Features
- ABM span mapping
- Citations
- Eval harnesses
- Evaluator / critic
- Four planes, copy/reject, 10 invariants, full index
- Gap Matrix
- Independent post-condition checks
- Intervention pre-assessment
- Knowledge Grounding & RAG
- Legal
- Observability & Auditability
- OCED case events
- Process mining
- Reuse, Deploy & Govern
- Skill registry
- Test, Debug & Evaluate
- Testing, Debugging & Optimization
- Trace maturity gate
Stacks
Document management
GitHub in this term
Primary repositories linked from member packs and devices.