veroq_verify
Fact-check any claim by returning a verdict (supported, contradicted, partially supported, or unverifiable) with confidence score, evidence chain from verified sources, and source reliability ratings.
Instructions
Fact-check any claim with full evidence chain, confidence breakdown, and source reliability scores.
WHEN TO USE: After any agent (including yourself) makes a factual claim about earnings, revenue, market movements, mergers, acquisitions, or any financial data. Also use proactively to verify assumptions before making recommendations. This is the TRUST tool — it proves claims with evidence.
RETURNS: • verdict: supported | contradicted | partially_supported | unverifiable • confidence: 0-1 with 4-factor breakdown (source_agreement, source_quality, recency, corroboration_depth) • evidence_chain: array of {source, snippet, url, position, reliability} — actual quotes from real sources • receipt: hashable verification proof (id, claim_hash, verdict_hash, sources_hash) • Checks 200+ verified sources first, falls back to live web search — NOTHING returns "unverifiable" for newsworthy claims
COST: 3 credits. Results cached 1 hour (corpus) or 15 min (web fallback).
EXAMPLES: "NVIDIA reported record Q4 2025 earnings" → SUPPORTED (85%) with Reuters, Bloomberg evidence "The Federal Reserve cut rates in March 2026" → CONTRADICTED (92%) — they held rates steady "Apple is partnering with OpenAI" → SUPPORTED with 5 source evidence chain
CONSTRAINTS: Claim must be 10-1000 characters. Be specific — include names, numbers, dates for best results.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| claim | Yes | The factual claim to verify (10-1000 chars). Be specific — 'NVIDIA beat Q4 earnings by 20%' not just 'NVIDIA did well' | |
| context | No | Category hint to narrow search: tech, markets, crypto, policy, health, energy |