At hundreds of agents, human review of every action stops scaling. Guardians are the supervisory layer: always-on agents that watch your operating agents, escalate exceptions to humans, and file their own evidence.
guardian roles: Reviewer · Monitor · Protector
supervision at machine speed
of interventions filed as evidence
escalation built into every path
A human can’t read every output of a hundred agents. Sampling misses exactly the cases that matter.
An agent that passed review in March behaves differently in August. Nobody re-checks until something breaks.
Even where monitoring exists, interventions vanish into logs — unauditable when the examiner asks who caught what.
Material outputs checked against policy conformance, groundedness, and citation integrity at machine speed — holding what falls below threshold for the right human.
Behavioral baselines per agent — with drift, anomalous tool use, and out-of-role data access surfaced the moment they diverge.
When thresholds are crossed, Protectors act inline — quarantine, permission revocation, circuit breakers, rollback — with every intervention governed, logged, and reversible by design.
Evaluate material outputs before they leave the institution — groundedness, policy conformance, citation integrity — at machine speed, escalating what falls below threshold to the right human.
Watch behavior across the estate continuously: drift from certified baselines, anomalous tool use, knowledge-access patterns that don't match an agent's role. File findings as evidence, automatically.
Intervene: quarantine a misbehaving agent, revoke a permission, trip a circuit breaker, roll back an action within its reversal window — each intervention itself governed, logged, and provable.
Every guardian is registered, certified, and evidenced like any other agent. Supervision without accountability is just another ungoverned agent — the chain of proof goes all the way up.
Guardians are the horizon layer of the Control tier — design partners are shaping the first supervisory policies now.
Yes. Every guardian is registered, certified, and evidenced like any operating agent — the chain of accountability goes all the way up.
Within governed bounds: interventions are policy-scoped, reversible where possible, and always escalated with full context.
Founding institutions shape what supervision looks like.
Start free