EYES · OBSERVABILITY
The observability OS for AI agents.
Trace, evaluate, guardrail. Every agent run becomes a typed graph of business objects — and every edge cites the trace node it came from.
What Eyes does
Five verbs over one operational graph.
Observe
Vitals, sessions, business identifiers normalized from every tool call. Patients, tickets, policies, escalations — not stack traces.
Diagnose
The operational graph. Typed entities, typed edges (TOUCHED · READ · WROTE · VIOLATED · MISSING), every edge cited to the trace that produced it.
Detect
Recipes match shapes, not strings. Monitors run on every run or on a schedule. Signals carry the patient, the offending edge, the recommended action.
Decide
One queue. Reviewers tag Accept · Expected · Dismiss. Two accepts become a guardrail candidate. Humans and agents share the same registry.
Harden
Every reviewed finding ships with a recommended guardrail. Shadow before active. Evals share their schema with production — regressions are visible, not statistical.
Rules over the graph — not regex over text.
mon_attending_approval fires when discharge_hold.amount ≥ $1k and approval.role != attending. Wording changes don’t break it. Backtest against history before you promote.
Reviews → guardrails, one click.
Two pharmacist-accepted findings on the same rule become a candidate guardrail. Shadow before active. The next discharge starts safer than the last.
Suggested → Shadow → Active.
Every reviewed finding ships with a recommended guardrail. Promote through shadow when the true-positive rate proves it. Active mode prevents execution.