# Agent Receipt Audit

> Agent Receipt Audit is a paid API for AI agents from agent-receipt-audit.bonto.run, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-23).

Audits agent earning ledgers for overcounting, duplicate transactions, unsettled revenue, internal/bootstrap calls, and missing payer/receiver evidence.

## Facts

- Endpoint: POST https://agent-receipt-audit.bonto.run/v1/audit?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-23
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-receipt-audit-8d0a2f64
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_oOkaJO5uiJ-iiFNjGh_-m

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agent-receipt-audit-8d0a2f64 -d '<json body>'
```

Example prompt: Can you run an audit on my agent's earning ledger to check for any overcounting, duplicate transaction reuse, or missing payer/receiver evidence and tell me if it passes?

## When to prefer this

Choose this endpoint when you need to programmatically validate the integrity of an AI agent's earning ledger — specifically to detect overcounting, duplicate transaction reuse, unsettled revenue, internal bootstrap calls, or missing payer/receiver evidence before releasing funds or filing revenue reports. It is purpose-built for agent economics auditing rather than general accounting or blockchain explorers.

## Known failure modes

- Missing or malformed bodyFields input may result in an error or incomplete audit
- Ledger data lacking transaction identifiers may prevent duplicate detection
- Incomplete receipt data with no payer/receiver fields will flag all entries as missing evidence
- Network or service unavailability returns a non-200 error response
- Ambiguous internal vs external call classification may produce uncertain verdicts

## How this service works

Checks agent earning ledgers for overcounting, duplicate transaction reuse, unsettled revenue, internal/bootstrap calls, and missing payer/receiver evidence.

## Output

A JSON object containing a summary with the total overcount in USD, the evidence-backed external revenue in USD, and a verdict string ('pass' or 'fail') indicating whether the agent ledger is clean.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "bodyFields": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "summary": {
   "overcountUsd": 0,
   "evidenceBackedExternalRevenueUsd": 0.01
  },
  "verdict": "pass"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-receipt-audit-8d0a2f64/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-receipt-audit.bonto.run](https://www.zero.xyz/host/agent-receipt-audit.bonto.run/llms.txt)
