# CAPI2 Agent Commerce – Backtest Integrity Checker

> CAPI2 Agent Commerce – Backtest Integrity Checker is a paid API for AI agents from capi2-agent-commerce.vandurmedries.workers.dev, paid per call via x402, $0.2/call, status unknown (last checked 2026-09-16).

Validates a backtest report for integrity risks such as multiple-testing bias, simulation-only flags, and other findings, returning a risk score and decision recommendation.

## Facts

- Endpoint: POST https://capi2-agent-commerce.vandurmedries.workers.dev/v1/backtest-integrity
- Price: $0.2/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/capi2-agent-commerce-backtest-integrity-checker-482338c4
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_d4p3HLHioXf6Z29AgxO-C

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 capi2-agent-commerce-backtest-integrity-checker-482338c4 -d '<json body>'
```

Example prompt: Can you run an integrity check on this backtest report and tell me the risk score, any findings like multiple-testing risk, and whether it needs manual review before I go live?

## When to prefer this

Choose this endpoint when you need a programmatic, tamper-evident integrity check on a quantitative backtest report — especially when you want to detect multiple-testing bias, simulation-only artifacts, or other methodology risks before deploying an autonomous trading agent. It is suited for autonomous agent pipelines where a lightweight, pay-per-call (x402) validation gate is needed without setting up a full risk infrastructure.

## Known failure modes

- Missing or malformed 'report' object returns a 4xx validation error
- Ambiguous or empty report body may yield inconclusive findings with no actionable decision
- Payment failure via x402 protocol results in 402 response and no analysis
- Upstream worker unavailability may return 503 or timeout
- Report with insufficient data fields may produce a low-confidence or default risk score

## How this service works

Programmable authority checks and tamper-evident receipts for autonomous agents, sold through sustainable x402 commerce.

## Output

Returns a JSON object with a 'decision' field (e.g. 'manual_review'), a 'risk_score' integer (0–100), a 'findings' array of detected issues (e.g. [{"code":"multiple_testing_risk"}]), and a 'simulation_only' boolean indicating whether the report is based solely on simulated data.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "report": {
   "type": "object"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "decision": "manual_review",
  "findings": [
   {
    "code": "multiple_testing_risk"
   }
  ],
  "risk_score": 45,
  "simulation_only": true
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/capi2-agent-commerce-backtest-integrity-checker-482338c4/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from capi2-agent-commerce.vandurmedries.workers.dev](https://www.zero.xyz/host/capi2-agent-commerce.vandurmedries.workers.dev/llms.txt)