# Tolca Homework AI-Risk Checker

> Tolca Homework AI-Risk Checker is a paid API for AI agents from tolca.tonbot.ca, paid per call via x402, $0.25/call, status unknown (last checked 2026-10-29).

Analyzes a school assignment (by text or URL) and returns a per-question AI-risk score indicating how easily an AI could complete it, with improvement suggestions.

## Facts

- Endpoint: POST https://tolca.tonbot.ca/v1/homework-check?utm_source=zero.xyz
- Price: $0.25/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-29
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/tolca-homework-ai-risk-checker-330e55ad
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_9zOKf_CA4JGyVj3aPCIsD

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 tolca-homework-ai-risk-checker-330e55ad -d '<json body>'
```

Example prompt: Can you check this grade 10 French assignment and tell me how easily an AI could do it? Here's the text: 'Question 1: Résume le chapitre 3 du roman. Question 2: Donne ton opinion sur le personnage principal.' — respond in French.

## When to prefer this

Choose this endpoint when you need a structured, per-question AI-risk assessment of a school assignment — especially when you want actionable fix suggestions for each item. Prefer it over generic AI-detection tools when the goal is to help educators design better assignments rather than detect past cheating. Ideal for French-language (including Quebec) educational contexts.

## Known failure modes

- URL not publicly accessible — returns error if the provided URL requires authentication or is unavailable
- Text exceeds 20,000 character limit — request rejected with size error
- Unsupported language value — only 'fr' and 'en' are accepted
- Empty or missing both text and URL — returns validation error
- PDF URL that cannot be parsed — may return an error or degraded result

## How this service works

Ask about any company or Québec contractor and get a verdict grounded in official registries, not guesses. Plus web search that reads the pages for you. Pay per call, no account.

## Output

Returns a JSON object with a per-item list (each item has the question text, an AI risk score 0–100, a reason why AI can do it, and a suggested fix), an overall risk score, a verdict (e.g. 'high'), a human-readable verdict label, a summary paragraph, and general tips for improving AI-resistance.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public URL of the assignment (PDF or page), instead of text"
  },
  "lang": {
   "enum": [
    "fr",
    "en"
   ],
   "type": "string",
   "default": "fr"
  },
  "text": {
   "type": "string",
   "description": "Assignment text (up to 20k chars)"
  },
  "grade": {
   "type": "string",
   "example": "secondaire 3"
  },
  "subject": {
   "type": "string",
   "example": "français"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "items": [
   {
    "fix": "Demander de relier le chapitre à la discussion faite en classe lundi.",
    "why": "Un résumé générique se produit en secondes.",
    "item": "Question 1: résumé du chapitre 3",
    "risk": 95
   }
  ],
  "summary": "...",
  "verdict": "high",
  "general_tips": [
   "..."
  ],
  "overall_risk": 78,
  "verdict_label": "Risque élevé: une IA peut faire l'essentiel de ce devoir"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/tolca-homework-ai-risk-checker-330e55ad/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from tolca.tonbot.ca](https://www.zero.xyz/host/tolca.tonbot.ca/llms.txt)