+ Try a request
Connecting- 01
Identity
—
- 02
Structural floors
—
- 03
Intent
—
- 04
AI judge
—
- 05
Fusion
—
Pick an example or type your own, then press Decide.
+The rules
Four ways fusion decides
Decision fusion is deliberately simple to reason about. It combines the signals with these four rules.
A floor fires
Instruction overrides, hidden instructions, real secrets and card numbers are strong enough to block on their own.
Two signals agree
When the AI judge and the intent check independently say hostile, the request is blocked.
One signal, no agreement
A judge-only concern is flagged for review instead of blocked — real work isn't stopped by a single guess.
Nothing to see
No floor, no hostile intent, no judge label. Allowed — and still logged with the decision.
+Also
A check can't finish
If a check times out or can't run, the request is blocked, never waved through.
Unmistakably hostile intent
Some intent is clear enough that the intent check blocks it without the judge.
Your own policy
Your organization's data-protection, topic and tool policies can block a request.
Personal data, masked
Where policy says so, personal data is masked and the request goes on without it.
+Why not just a model?
A model alone can't be the last word.
An AI judge is good at reading context and bad at being certain. If it could block on its own, every false positive would stop real work — and teams would turn it off.
So the judge is one voice. Structural signals that are never legitimate can block alone. Everything else needs a second, independent signal to agree. When they don't, the request is flagged for a person to look at.
Before every enforcer deploy, the enforcer runs against a corpus of benign requests that must keep passing — so tightening detection can't quietly break the allow path.
Go deeper in the Simulation Lab →+After the verdict
+Actions wait
High-stakes tool calls can be held until an approver with the right role decides, then run once with a single-use permit.
+Evidence stays
Each decision is stored with its signals and reason, per agent, for review and export.
+Monitor first
Start in monitor mode, where most checks flag instead of block. Credentials, card numbers and SSNs still block. Turn on enforcement per agent when the decisions look right.
+ The AI watching your AI
Run it on your own traffic.
Monitor mode shows you every verdict and its reason before you turn on enforcement. Credentials, card numbers and SSNs still block.