# audit-tools.ai Actor Evaluator

> audit-tools.ai Actor Evaluator is a paid API for AI agents from audit-tools.ai, paid per call via x402, $1/call, status unknown (last checked 2026-09-16).

Evaluates an Apify actor's quality by scoring it against up to 23 built-in and/or custom criteria, returning per-criterion evidence and a verdict.

## Facts

- Endpoint: POST https://audit-tools.ai/api/evaluations
- Price: $1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/audit-tools-ai-actor-evaluator-989b9ea2
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_jBIwcQpsFibxvWp-DAoCO

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 audit-tools-ai-actor-evaluator-989b9ea2 -d '<json body>'
```

Example prompt: Run a full audit on the apify/instagram-scraper actor — I want to see reliability scores, 30-day failure rate, whether it actually delivers the advertised fields, and cost per usable item, all backed by evidence.

## When to prefer this

Choose this endpoint when you need an objective, evidence-backed quality assessment of a specific Apify actor before committing to it in production, when comparing multiple actors for the same task, or when you want to apply a custom rubric beyond the 23 built-in criteria. It is particularly valuable for high-volume scraping pipelines where actor reliability and cost-per-usable-item directly affect operational costs.

## Known failure modes

- Actor ID not found on Apify — returns error indicating unknown target
- Live funded run required for deep-scan fails due to actor timeout or error
- Custom criteria descriptions too vague to score reliably — low-confidence scores returned
- Actor has insufficient run history for statistical failure-rate calculation
- Payment not confirmed — $1 USDC x402 payment required before evaluation proceeds

## How this service works

Evaluate an Apify actor before you use it. Send one actor ID (for example apify/instagram-scraper) and get an evidence-backed quality report: 23 built-in criteria like reliability, 30-day failure rate, advertised-field truth, and cost per usable item, deep-scan criteria measured from live funded runs, or your own rubric in plain English. Use it to audit a scraper, compare actor quality, or pick the best actor. Returns JSON with per-criterion scores, evidence, and a verdict.

## Output

A JSON object containing per-criterion scores, evidence backing each score, a failure rate over the last 30 days, cost-per-usable-item analysis, advertised-field truth scores, and an overall verdict on actor quality. Optionally includes scores for user-defined custom criteria.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "mode": {
   "enum": [
    "full"
   ],
   "type": "string",
   "description": "Full evaluation (all available deep-scan criteria)"
  },
  "targets": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "maxItems": 1,
   "minItems": 1,
   "description": "One Apify actor ID or URL, e.g. apify/instagram-scraper"
  },
  "customCriteria": {
   "type": "array",
   "description": "Optional custom rubric: your own criteria to score the actor against, each with a name and a plain-language description of what to measure"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/audit-tools-ai-actor-evaluator-989b9ea2/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from audit-tools.ai](https://www.zero.xyz/host/audit-tools.ai/llms.txt)