# SentEdge Trust Agent Score

> SentEdge Trust Agent Score is a paid API for AI agents from sentedge.ai, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-12).

Returns a confidence score and visibility signal for an agent's trustworthiness, derived from signed bilateral attestations, with full component breakdowns for both metrics

## Facts

- Endpoint: POST https://sentedge.ai/trust/x402/attention/score?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sentedge-trust-agent-score-2c475468
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_iQGi7XGVWVggMs65EuIeo

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 sentedge-trust-agent-score-2c475468 -d '<json body>'
```

Example prompt: Before I let this agent handle my crypto transfers, can you check its SentEdge trust score for the DeFi domain? The agent ID is agent:0xabc123.

## When to prefer this

Use this endpoint when you need a cryptographically grounded, tamper-resistant trust score for a specific agent in a specific domain, and you require the full component breakdown distinguishing confidence (attestation-based) from visibility (promotion-based). Prefer this over the free GET /v1/signals endpoint when you need the detailed breakdown or when operating in high-stakes automated pipelines where trust assurance is critical. Use the batch endpoint instead if evaluating up to 10 agents simultaneously.

## Known failure modes

- Unknown or unregistered agent_id returns no attestation data or a zero-confidence score
- Invalid agent_id format (not ERC-8004 or A2A) may result in a validation error
- Domain not recognized may return a null or generic score
- Payment failure (insufficient USDC balance for $0.01 per call) blocks the request
- Rate limiting if too many rapid calls are made against the x402 endpoint

## How this service works

SentEdge Trust: is this agent trustworthy? Returns a confidence score derived from signed bilateral attestations (both parties sign each outcome), plus a separate visibility signal, with the full component breakdown for both. Confidence and visibility are deliberately separate — paid boosts and curator endorsements move visibility only and can never inflate trust. Free alternative: GET /v1/signals. Full API: https://sentedge.ai/trust/skill.md

## Output

A JSON response containing a numeric confidence score (derived from signed bilateral attestations where both parties signed each outcome) and a separate visibility signal, plus the full component breakdown for each. Paid boosts and curator endorsements affect visibility only and cannot inflate the confidence score, keeping trust and promotion cleanly separated.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "domain": {
   "type": "string",
   "description": "Context domain for scoring"
  },
  "agent_id": {
   "type": "string",
   "description": "Agent identifier (ERC-8004 or A2A)"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/sentedge-trust-agent-score-2c475468/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from sentedge.ai](https://www.zero.xyz/host/sentedge.ai/llms.txt)