# DubbleBlack Evidence-Ranked Product Recommendation API

> DubbleBlack Evidence-Ranked Product Recommendation API is a paid API for AI agents from agents.dubbleblack.com, paid per call via MPP or x402, $0.1/call, status healthy (last checked 2026-10-12, last successful call 2026-10-07).

Returns ranked product recommendations with evidence scores, confidence bands, and provenance metadata derived from aggregated first-party behavioral and verified transaction data for a given vertical, category, and purchase intent.

## Facts

- Endpoint: POST https://agents.dubbleblack.com/api/agent/evidence?utm_source=zero.xyz
- Price: $0.1/call
- Payment: MPP, x402
- Status: healthy
- Last checked: 2026-10-12
- Last successful call: 2026-10-07
- Success rate: 98% of calls made through Zero
- Rating: 2.5 / 5 from 5 reviews
- Activations on Zero: 69
- Provider: agents.dubbleblack.com
- Website: https://agents.dubbleblack.com
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agents-dubbleblack-com-dubbleblack-evidence-ranked-product-eb777b2a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap__ths2lTO5gzGIuCTQnZNO

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 agents-dubbleblack-com-dubbleblack-evidence-ranked-product-eb777b2a -d '<json body>'
```

Example prompt: Can you find me the top 3 evidence-backed pet nutrition products in the companion animal vertical for a senior dog with a sensitive stomach, keeping budget under $60?

## When to prefer this

Choose this endpoint when you need evidence-grounded product recommendations backed by verified consumer behavioral data rather than catalog metadata or LLM-generated suggestions. It is especially valuable when recommendation trustworthiness and data provenance matter — e.g., health, nutrition, or wellness contexts — and when you need explicit confidence bands to decide whether to surface or withhold a recommendation. Prefer it over generic product search APIs when you want ranked outputs with transparency about evidence quality and source counts.

## Known failure modes

- Sparse observations: HTTP 200 with empty results array and insufficient_evidence=true — not an error, just honest signal
- Invalid vertical enum value: validation error returned
- Budget min greater than budget max: likely returns empty or error in errors array
- No products match combined brand + category + budget filters: empty results
- Network or upstream DubbleBlack service outage: HTTP 5xx

## How this service works

Canonical paid interface backed by Evidence Engine V2. Submit a natural-language query; vertical is an optional routing hint. Explicit two-subject text comparisons return independently attributed evidence, coverage, provenance, limitations, and per-subject scores, with no winner or aggregate comparison score. A one-element brands array is accepted for single-subject compatibility. budget_min, budget_max, and include_insufficient_evidence are rejected; ambiguous multi-selector requests are reject

## Output

A JSON object containing: the echoed query parameters, an array of ranked product results (each with rank, product name, brand, SKU, category, vertical, evidence score 0-1, evidence band label (high/moderate/limited/insufficient), evidence summary, component scores, source type counts, data provenance metadata, profile status, and recommendation eligibility flag), and optionally a list of non-fatal errors. If evidence is too sparse, returns HTTP 200 with an empty results array and insufficient_evidence set to true.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "properties": {}
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST",
      "PUT",
      "PATCH"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "schema_version",
  "generated_at",
  "evidence_available",
  "evidence",
  "errors"
 ],
 "properties": {
  "errors": {
   "type": "array",
   "items": {
    "type": "string"
   }
  },
  "coverage": {
   "type": "object",
   "additionalProperties": true
  },
  "evidence": {
   "type": "array",
   "items": {
    "type": "object",
    "additionalProperties": true
   }
  },
  "provenance": {
   "type": "array",
   "items": {
    "type": "object",
    "additionalProperties": true
   }
  },
  "generated_at": {
   "type": "string",
   "format": "date-time"
  },
  "evidence_score": {
   "type": [
    "object",
    "null"
   ],
   "description": "Calibrated bounded Evidence Score V1 with score, band, components, formula, explanation, and limitations.",
   "additionalProperties": true
  },
  "schema_version": {
   "type": "string"
  },
  "evidence_available": {
   "type": "boolean"
  },
  "comparison_subjects": {
   "type": "array",
   "items": {
    "type": "object",
    "additionalProperties": true
   },
   "description": "Present only for explicit two-subject text comparisons. Each entry carries its own subject, evidence, coverage, provenance, limitations, and score; no winner is calculated."
  }
 },
 "description": "V2 response. Evidence Score V1 measures bounded evidence strength/depth only; it is not product quality, recommendation confidence, or purchase probability.",
 "additionalProperties": true
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agents-dubbleblack-com-dubbleblack-evidence-ranked-product-eb777b2a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.dubbleblack.com](https://www.zero.xyz/host/agents.dubbleblack.com/llms.txt)