Agent Assurance
The roster is a supervised population. Invigilator independently validates fellow agents; Quorum re-derives their decisions blind. Agents governing agents — with the committee holding the pen.
Inventory
The governed roster itself — every agent versioned, with evals, guardrails, and a decision ledger.
Assurance fleet
Re-runs a fellow agent's eval sample, challenges its trajectories, and issues a validation opinion.
- hands to Cerberus via run_eval_sample
- hands to Spark via run_eval_sample
Re-derives another agent's decision blind and concurs, dissents, or escalates (maker-checker).
- hands to Cerberus via rederive
- hands to Spark via rederive
Subjects under review
Resolve
Validation opinions and dissents land with the committee.
Tracking findings to closure. Open slot — no agent staffs this step yet.
The walkthrough
- 1
The roster itself is a supervised population: every agent ships with evals, guardrails, and a decision ledger.
- 2
Invigilator independently validates a fellow agent — re-running its eval sample and challenging its trajectories — and issues a validation opinion.
- 3
Quorum re-derives sampled decisions blind — concur, dissent, or escalate. Agents governing agents, on the record.
Replay the real runsc-quorum - 4
Opinions land with the model-risk committee; remediation tracking is the next slot in the cadre.