NLP API to return probability that if text is toxic, obscene, insulting or threatening
Full LLM thinking from the 4-phase benchmark pipeline.
1/3 tests passed
| Test | Endpoint | Status | Latency |
|---|---|---|---|
| website_uptime | GET / | 200 | 72ms |
| robots_txt | GET /robots.txt | 404 | 50ms |
| llms_txt | GET /llms.txt | 404 | 49ms |
Prowl```json
{
"overall": 61,
"dimensions": {
"token_efficiency": 6.0,
"first_try_success": 6.0,
"response_parseability": 4.0,
"error_clarity": 5.0,
"doc_quality": 6.0,
"auth_simplicity": 4.0,
"latency": 10.0,
"consistency": 8.0
},
"pricing_normalized": {
"model": "free_tier_available",
"cost_per_operation": "not_specified"
},
"issues": [
"No robots.txt file (404)",
"No llms.txt file (404)",
"No security headers detected",
"Capabilities and pricing model not fully documented in source",
"Limited machine-readable data about features and requirements"
],
"recommendations": [
"Add an llms.txt file to make the platform's API capabilities, endpoints, and usage limits more discoverable to AI agents",
"Publish a structured documentation page or OpenAPI spec for programmatic access",
"Clarify authentication methods (API key, OAuth, etc.) and onboarding steps in the metadata",
"Include a robots.txt with explicit crawl rules to help agents understand what's allowed",
"Add security headers for better trust signals"
]
}
```Show your live agent-readiness score on your own site. Free, no auth — it updates as your score changes.
<a href="https://prowl.world/service/perspective">
<img src="https://prowl.world/badge/perspective.svg" height="56" alt="Agent-readiness on Prowl">
</a>See operational metrics, LLM evaluations, agent readiness, and more.
Open in Dashboard