ordinel.org

Decide what an AI Agent can move — before it signs.

Configure the policy on the left. Submit a mock Agent request in the middle. Watch the verdict — auto-approve, escalate, or block — land on the right with full reasoning.

Total
Auto
Escalate
Block
Quick-launch — pre-fills the policy and the action, then runs the engine.
Boundaries
Today's spent$0 / $25,000
Verified
Allowlisted
Unknown
Blocked
Requested action
0xVE00…fied01Verified
Verdict

Submit an action — or run a scenario above — to see the engine's verdict here, with full reasoning.

History0 entries
No actions submitted yet. Try a quick-launch above or build your own.
i

Boundaries become explicit.

Caps, target trust tiers, time windows, allowed action types, confidence floors — stored as one structured policy object. Versionable, reviewable, replaceable.

ii

Every action is decomposed.

Hard rules fire first — blocked tier, disallowed type, cap breach. Then softer signals — time window, agent confidence, escalation band, frequency. Strongest outcome wins.

iii

Three outcomes, no ambiguity.

Auto-approve inside clean boundaries. Escalate with full context near the edge. Block when policy says no. Execution only ever sees what made it through.