# ProspectIntel Deep Verify

> ProspectIntel Deep Verify is a paid API for AI agents from claim-grounding.prospectintel.workers.dev, paid per call via x402, $0.75/call, status unknown (last checked 2026-10-16).

Asynchronously fact-checks a claim against Wikipedia and Google News, returning a verdict with evidence for and against plus citations

## Facts

- Endpoint: POST https://claim-grounding.prospectintel.workers.dev/v1/deep_verify?utm_source=zero.xyz
- Price: $0.75/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/prospectintel-deep-verify-b233f552
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_xf9cTzsVR4rLnO7Z8_CR-

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 prospectintel-deep-verify-b233f552 -d '<json body>'
```

Example prompt: Can you do a deep verify on the claim 'The Eiffel Tower is taller than the Empire State Building' — check it against Wikipedia and recent news and tell me if any sources contradict it, with citations?

## When to prefer this

Choose this endpoint when you need deep, multi-source fact-checking with citations rather than a fast lightweight grounding check. It is best when accuracy and evidence trails matter more than speed — for example, verifying AI-generated content, checking contested claims before publication, or detecting misinformation. Prefer the sibling fast-grounding endpoints when you only need a quick confidence signal without waiting for async processing.

## Known failure modes

- Claim text missing or empty — returns 400 validation error
- Job polling returns pending status until processing completes — agent must retry
- Verdict may be inconclusive if sources are ambiguous or sparse
- Wikipedia/Google News sources unavailable — may result in incomplete evidence sets
- Payment of $2.00 USDC not processed — request rejected before job creation
- Job ID not found on poll — may have expired or be invalid

## How this service works

Deep verify. Checks a claim against Wikipedia, Google News titles, Europe PMC reviews and trials (health and science claims), FRED data (US economic indicators), Wikidata structured facts (dates, quantities, offices held) and SEC EDGAR filings (US public companies: financials, listing status, former names), and flags a contradiction when sources disagree. Async: returns a job_id; poll GET /v1/jobs/{id} (free) for verdict, evidence for and against, citations and receipt. $0.75 USDC.

## Output

Returns a job_id immediately. Polling GET /v1/jobs/{id} (free) yields a structured result containing: a verdict (supported/contradicted/inconclusive), evidence in favor of the claim, evidence against the claim, source citations from Wikipedia and Google News, and a payment receipt.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string"
  },
  "claim": {
   "anyOf": [
    {
     "type": "string",
     "minLength": 1
    },
    {
     "type": "object",
     "required": [
      "text"
     ],
     "properties": {
      "text": {
       "type": "string",
       "minLength": 1
      }
     }
    }
   ],
   "description": "The claim to check. Object {\"text\": \"...\"} or a plain string."
  },
  "answer": {
   "type": "string"
  },
  "sources": {
   "type": "array",
   "items": {
    "type": "object",
    "anyOf": [
     {
      "required": [
       "url"
      ]
     },
     {
      "required": [
       "text"
      ]
     }
    ],
    "properties": {
     "url": {
      "type": "string",
      "format": "uri",
      "maxLength": 2048,
      "description": "Public https URL. Fetched with a 3.5 s timeout and a 512 KB cap; http, file and other schemes, private / loopback / link-local / metadata addresses, IP-literal hosts, custom ports and URLs with credentials are rejected (HTTP 400, not charged). With text, it is only the citation link."
     },
     "text": {
      "type": "string",
      "maxLength": 20000,
      "minLength": 1,
      "description": "Source text to check the claim against (up to 20,000 characters). When given, no fetch is made."
     },
     "title": {
      "type": "string",
      "maxLength": 200,
      "description": "Optional title shown in citations."
     }
    },
    "description": "One source: {url} for a public https page we fetch, or {text, title?, url?} for text you already have.",
    "additionalProperties": false
   },
   "maxItems": 10,
   "description": "Optional. Up to 10 sources of your own, used as extra evidence next to the public sources and cited with provider and source_type \"caller\". The response lists what was used in sources_used."
  },
  "sources_only": {
   "type": "boolean",
   "default": false,
   "description": "Optional. true = judge the claim only against your sources (no public-source lookups). Needs a non-empty sources array."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "mode": "deep",
  "poll": "GET /v1/jobs/job_8c1d2e3f4a5b6c7d (free)",
  "claims": [],
  "job_id": "job_8c1d2e3f4a5b6c7d",
  "status": "queued",
  "receipt": {
   "claims": [
    {
     "text": "Paris is the capital of France",
     "claim_id": "clm_3f9a1c2b4d5e6f70",
     "grounding_required": true
    }
   ],
   "job_id": "job_8c1d2e3f4a5b6c7d",
   "created_at": "2026-10-10T12:00:00.000Z",
   "priced_usd": 0.75
  },
  "next_actions": []
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/prospectintel-deep-verify-b233f552/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from claim-grounding.prospectintel.workers.dev](https://www.zero.xyz/host/claim-grounding.prospectintel.workers.dev/llms.txt)