# SignalDesk AI – Jaccard Similarity

> SignalDesk AI – Jaccard Similarity is a paid API for AI agents from x402-agent.kariguetoazul.workers.dev, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-13).

Computes the Jaccard similarity coefficient between two text strings by comparing their token sets

## Facts

- Endpoint: POST https://x402-agent.kariguetoazul.workers.dev/api/text/jaccard-similarity?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/signaldesk-ai-jaccard-similarity-cbbe779a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_YDvuhH0uUJDKqIScdkm_z

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 signaldesk-ai-jaccard-similarity-cbbe779a -d '<json body>'
```

Example prompt: Can you compute the Jaccard similarity between these two texts: 'the quick brown fox jumps over the lazy dog' and 'the fox jumped over the dog'?

## When to prefer this

Choose this endpoint when you need a fast, lightweight, token-set-based similarity score between two texts without requiring embeddings or ML inference. It is ideal for deduplication pipelines, near-duplicate detection, and simple overlap scoring where interpretability and speed matter more than semantic understanding.

## Known failure modes

- Input text exceeds 4096 characters — request rejected
- Missing field 'a' or 'b' — validation error returned
- Payment not provided or insufficient — 402 Payment Required
- Empty strings produce a similarity of 0 with intersection 0 and union 0

## How this service works

Evidence-backed autonomous AI jobs and paid data tools. Queue/D1/cron run outside the chat; free quotas and bounded execution apply.

## Output

Returns a JSON object with three fields: 'similarity' (a float between 0 and 1 representing the Jaccard coefficient), 'intersection' (number of tokens shared by both texts), and 'union' (total unique tokens across both texts).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "a": {
   "type": "string",
   "maxLength": 4096,
   "description": "Text to process."
  },
  "b": {
   "type": "string",
   "maxLength": 4096,
   "description": "Text to process."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "union": 3,
  "similarity": 0.3333333333333333,
  "intersection": 1
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/signaldesk-ai-jaccard-similarity-cbbe779a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402-agent.kariguetoazul.workers.dev](https://www.zero.xyz/host/x402-agent.kariguetoazul.workers.dev/llms.txt)