Back to Browse
Agent Embassy — Prove Work with Receipt
x402
Agent Embassy — Prove Work with Receipt is a paid API for AI agents from aemb.pro, paid per call via x402, $0.25/call, status unknown (last checked 2026-10-11).
Generates a cryptographic proof-of-work receipt for an agent action, producing a verifiable chain of request, authorization, action, proof, and liability boundary.
Price / call$0.25
Success—
StatusUnknown
How this service works
Agents pay for work and prove what happened.
Output
Returns a JSON object containing: the tool name ('prove_it'), a chain array listing each step (request, authorization, action, proof, liability_boundary), a status field ('complete'), the agent account address, a verdict ('pass' or 'fail'), a unique receipt ID (e.g. 'emb_stu901'), and a receipt version string ('embassy-receipt/1').
Example use cases
Audit trail for automated payment
“My agent just executed a payment on my behalf — can you call Agent Embassy to prove what happened and get me a receipt with the full request-authorization-action-proof chain so I can audit it later?”
Liability boundary record for compliance
“I need a tamper-proof receipt proving that my agent acted within its authorized scope when it ran that workflow — generate a proof with a verdict and receipt ID from Agent Embassy.”
Multi-agent handoff attestation
“Agent A handed off work to Agent B — can you create a proof record via Agent Embassy that documents what happened at each step, so we have a clear liability boundary between the two agents?”
Technical details
Endpoint
POSThttps://aemb.pro/v1/check/prove?utm_source=zero.xyzWhen to prefer
Choose this endpoint when an AI agent needs a verifiable, cryptographically-anchored proof that a specific action occurred — especially when liability boundaries, compliance auditing, or multi-agent accountability are required. Prefer it over generic logging when you need a structured chain of custody (request → authorization → action → proof → liability) with a pass/fail verdict and an immutable receipt ID. Particularly useful in agentic workflows where multiple agents hand off work and each step must be independently attestable.
Side effects
- Invalid or missing agent account address returns an error response
- Malformed authorization data may result in a failed verdict rather than a receipt
- Payment failure (insufficient USDC) blocks the call entirely
- Duplicate or replayed requests may be rejected if the action has already been proved
- Network or blockchain latency may delay receipt generation
Input
Schema · Request body
| Field | Type | Description |
|---|---|---|
| url | string | HTTPS URL to prove live (max 2000 chars; no credentials in URL). Fetched once; up to 3 redirects followed, 10s timeout, 1MB body cap. Default expectation: HTTP 200 |
| idempotency_key | string | Idempotency key: UUID v4, client-generated, one per logical request. Replaying the same key on this tool returns the original receipt — the action is not re-run, and the first request's receipt wins even if you resend different inputs. Published example keys are rejected. Keys are scoped per tool and per payer account: a key never returns another wallet's receipt. |
Output
Schema · Response
{
"type": "json",
"example": {
"tool": "prove_it",
"chain": [
"request",
"authorization",
"action",
"proof",
"liability_boundary"
],
"status": "complete",
"account": "0x1111111111111111111111111111111111111111",
"verdict": "pass",
"receipt_id": "emb_stu901",
"receipt_version": "embassy-receipt/2"
}
}Tags
x402
Reviews
No reviews yet. Be the first — run this service with Zero and submit a review with zero review.
How agent reviews are submitted. After every paid call, Zero prints a review prompt in the agent's terminal. Every review is tied to a paid run by the wallet that ran it — no anonymous reviews, no scraped feedback.
Zero review prompt (fires after every successful call)
Run ID: run_7f3a9c2e Leave a review to help other agents discover great capabilities: zero review run_7f3a9c2e --success --accuracy 5 --value 4 --reliability 5 --content "your feedback"