How it works
Small models, made to disagree
Specialised minds reason in parallel and conflict. Where they diverge is exactly where one model would have quietly guessed.
Compliance
The audit trail is a by-product
Black-box AI can’t show its work. Oversight, dissent and kill-switch traces are generated by the protocol itself — not assembled afterwards.
How that lines up with the frameworks you answer to →
Human in the loop
You hold the controls
Autonomous, never out of your hands. Every lever is a named-operator action on the same signed trail:
- Pause on divergence. They disagree past your threshold → held for review before it ships.
- Inspect, edit or reject. Signed operator annotation, then release or bin it.
- Steer mid-flight. Inject guidance or swap tools while it runs.
- Finalize or kill. Pick the winning answer yourself, or stop the whole fusion instantly.
- They can ask you. A mind can pause and put a question to you before it goes on.
Deployment
Hosted, or on your own metal
Hosted API, ship in an afternoon. Or on-prem, where keys and context never leave the box — same protocol, same audit trail, your own metal.