Agent Embassy Verify — Check and Prove Agent Work Completion

x402

Agent Embassy Verify — Check and Prove Agent Work Completion is a paid API for AI agents from aemb.pro, paid per call via x402, $0.15/call, status unknown (last checked 2026-10-11).

Verifies that an agent action was authorized, executed, and recorded, returning a signed receipt proving what happened and establishing a liability boundary.

Price / call$0.15

Seller volume →—

Success—

StatusUnknown

How this service works

Agents pay for work and prove what happened.

Output

Returns a JSON object containing: the tool name ('verified_check'), an ordered chain of verification stages (request, authorization, action, proof, liability_boundary), a status ('complete'), the agent's account address, a pass/fail verdict, a unique receipt ID (e.g. emb_jkl012), and a receipt version string (embassy-receipt/1). This constitutes a tamper-evident audit record of the agent action.

Example use cases

Audit trail for autonomous agent payment

“My agent just paid for a compute task — can you verify that the action was properly authorized and completed, and get me a receipt ID I can use to prove what happened if there's ever a dispute?”

Third-party proof of agent work

“I need to prove to a client that my AI agent actually performed the work they paid for — can you run a verification check and give me the receipt version and verdict so I can share it with them?”

Post-action liability boundary check

“After my agent executed that on-chain task, I want to confirm the full request-to-proof chain is recorded and get a liability boundary receipt — verify the completion status for my agent account now.”

Technical details

Endpoint

POSThttps://aemb.pro/v1/check/verify?utm_source=zero.xyz

When to prefer

Choose this endpoint when you need cryptographic, receipt-backed proof that an autonomous agent action was authorized, executed, and bounded by liability — particularly after an x402 payment-gated task. Prefer this over generic logging or audit tools when you need a structured, versioned embassy-receipt that can be shared with third parties, used in dispute resolution, or stored as an accountability artifact specific to the Agent Embassy ecosystem.

Side effects

Invalid or unrecognized action/check ID returns an error or failed verdict
Account address not matching the action results in verification failure
Action not yet completed may return incomplete status rather than 'complete'
Malformed request body causes 400-level error
Payment of $0.15 USDC not processed leads to 402 Payment Required
Chain verification step failure returns partial chain with non-passing verdict

Input

Schema · Request body

Field	Type	Description
url	string	HTTPS URL to check (max 2000 chars; no credentials in URL). Fetched once; up to 3 redirects followed, 10s timeout, 1MB body cap
expect_status	number	Expected HTTP status code; truncated to an integer. Defaults to 200 when omitted
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.
expect_json_path	string	Dot-separated path into the JSON body, e.g. 'data.price' (max 500 chars). Only evaluated when set
expect_json_equals	—	Expected value at expect_json_path; compared by canonical JSON equality. Defaults to null when omitted
expect_body_contains	string	Substring that must appear in the response body (max 5000 chars). Skipped when empty or omitted

Output

Schema · Response

{
  "type": "json",
  "example": {
    "tool": "verified_check",
    "chain": [
      "request",
      "authorization",
      "action",
      "proof",
      "liability_boundary"
    ],
    "status": "complete",
    "account": "0x1111111111111111111111111111111111111111",
    "verdict": "pass",
    "receipt_id": "emb_jkl012",
    "receipt_version": "embassy-receipt/2"
  }
}

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"