# DCL Trust Oracle Batch Evaluator

> DCL Trust Oracle Batch Evaluator is a paid API for AI agents from bazaar.fronesislabs.com, paid per call via x402, $0.1/call, status unknown (last checked 2026-10-13).

Evaluates a batch of up to 20 text items against named trust policies in a single paid call, returning verdicts for each item.

## Facts

- Endpoint: POST https://bazaar.fronesislabs.com/evaluate/batch?utm_source=zero.xyz
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/dcl-trust-oracle-batch-evaluator-9569267d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_TRytrF2nogIecTHeDVOxt

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 dcl-trust-oracle-batch-evaluator-9569267d -d '<json body>'
```

Example prompt: Run a batch trust evaluation on these 5 agent responses using the 'default' policy — my agent ID is 'agent-prod-42' — and tell me which ones pass or fail.

## When to prefer this

Use this endpoint when you need to evaluate multiple texts in a single paid call to minimize cost and latency compared to calling a single-item evaluator repeatedly. Ideal for pipeline checkpoints, end-of-batch QA sweeps, or any scenario where you have 2–20 items to screen simultaneously. Prefer this over the single-item evaluator when you have a known bounded list of responses ready at the same time.

## Known failure modes

- Call rejected if len(items) exceeds max_items (default 20) — reduce batch size
- Empty or missing 'response' field in any item causes validation error
- Invalid or unrecognized policy name may fall back to default or return an error
- Payment failure (insufficient USDC balance) results in 402 rejection before evaluation
- Missing agent_id may result in unattributed audit records or rejection

## How this service works

Evaluate a list of texts in one paid call. Each item may name a built-in policy. The call is rejected when the list is longer than max_items (default 20). POST JSON {"items","agent_id","max_items"}.

## Output

Returns a verdict for each submitted text item indicating whether it passes or fails the specified policy, along with confidence scores and audit records stored on the audit chain. Items exceeding the max_items cap cause the entire call to be rejected.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "items": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "response"
    ],
    "properties": {
     "policy": {
      "type": "string",
      "description": "Built-in policy name. Defaults to default."
     },
     "response": {
      "type": "string",
      "minLength": 1
     },
     "task_type": {
      "type": "string",
      "description": "Task tag stored on the audit record. Defaults to batch_item."
     }
    }
   },
   "description": "Texts to evaluate. Each item is capped by max_items."
  },
  "agent_id": {
   "type": "string"
  },
  "max_items": {
   "type": "integer",
   "default": 20,
   "description": "Reject the call when len(items) exceeds this value. Default 20."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/dcl-trust-oracle-batch-evaluator-9569267d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from bazaar.fronesislabs.com](https://www.zero.xyz/host/bazaar.fronesislabs.com/llms.txt)