Cinchor Playground
0 accountability actions · the metered unit you're billed on in production

Give an autonomous agent a spending policy, with your own numbers — then watch it allow and refuse the actions you throw at it, record a decision on the live chain, and catch yourself trying to fake it. Every call below is real and runs against the live network.

Prefer code to a UI? @cinchor/sdk runs this exact flow — enforce, attest, verify — straight against the chain, no playground required. See the SDK →
Your key stays in this browser tab — it's only ever sent to Cinchor.
STEP 1 · POLICY

Issue a capability

Grant the agent a budget and an expiry. It may spend up to your ceiling, until it runs out or the clock runs out — enforced on every action.

spend ceiling
seconds (3600 = 1h)
capability remaining
active spent 0 / 0 · 0 actions
STEP 2 · ENFORCE

Make the agent act

Enter an amount and try the action. Under budget → allowed. Over what's left → refused in real time, no human in the loop. Fire as many as you like and watch the meter above.

STEP 3 · ATTEST

Record a decision on-chain

Write whatever the agent decided. Cinchor commits a fingerprint of it to the chain — the full text stays with you; only the hash is anchored, so it's provable but private.

verdict: in-policy
↳ fingerprint committed to Omne
STEP 4 · VERIFY

Prove it — then try to fake it

First verify the record as written: the recomputed fingerprint matches the chain. Then change anything below and verify again — the faked version produces a different fingerprint and fails. That's the whole point: no one, us included, can rewrite it.

Now tamper with your own record and re-check:

Questions or feedback?