Pulse prototype

QUOKKA Pulse

Every step is scored. The next tokens go to the work that earned them.

Prototype replay available. API is not open yet.

For
When several agents run a job together, the platform can schedule them, but it still needs a referee. Pulse is the B2B API for that: send each step in, get a score, a constrained reward, and the next round of budget.
Solves
A busy-looking fleet still burns budget. Repeat one high-scoring move and the eval is gamed. Busywork and polish loops spend the same tokens. When the run ends, nobody can show who actually contributed, so the next round is split evenly or by guesswork.
Does
Every step is scored, including handoffs and send-backs. The model only proposes quality and risk. Budget, anti-exploit, and novelty are decided by deterministic rules — a high model score can still be cut. The ledger then gives the next round of tokens to the work that earned them.

Replay of a scripted run · not live traffic

QUOKKA Pulse · Inbox clusters and the weekly digest budget 12.00 · 30 steps · fixture

Press Run replay. This is a recording, not a live model call.

The live endpoint is up. To verify:

curl -s -X POST https://www.quokkalabs.io/api/demo/pulse/run

This page replays a scripted run. It does not call the model. AI DisclosureMindLog live demo