Truth Discovery Engine + AI Reliability

Your data
disagrees.
We resolve it.

Two engines, one API. Reconcile conflicting data from multiple sources. Score AI model reliability and detect hallucinations.

500 free resolutionsNo credit cardOpen-source core
333K+ evidence reconciled7 algorithms
Engine 1

Data Consensus

5 sources disagree on a price. Which is right? Moresq finds the truth using academic algorithms.

01

Match

Group records that refer to the same entity. 5-level dedup.

02

Clean

Filter placeholders, normalize units, currencies, country codes.

03

Resolve

CATD truth discovery finds consensus with confidence scores.

04

Validate

Cross-field coherence checks catch impossible combinations.

Full pipeline in one call

Placeholders filtered. Currencies converted. Consensus computed. Coherence validated.

19,756

fields reconciled

8,992

junk filtered

<2ms

per resolution

const result = await moresq.pipeline({
  entity_id: 'asset_001',
  evidence: [
    { field: 'price', source: 'source_a', value: '$285,000' },
    { field: 'price', source: 'source_b', value: '€262,000' },
    { field: 'price', source: 'source_c', value: '$290,000' },
    { field: 'year',  source: 'source_a', value: 1967 },
    { field: 'color', source: 'source_c', value: 'Unknown' },
  ]
})
// → { price: 267000, year: 1967, color: filtered }
// → coherence.score: 1.0

Entity Matching

5-level: exact ID, name, phonetic, composite, fuzzy. Presets for vessel, vehicle, product, property, company.

Geo Consensus

GPS from multiple sources → geometric median. Weiszfeld algorithm + DBSCAN outlier detection.

Multi-Currency

$15M, €14.2M, £12.5M → auto-converts then reconciles. Handles every format and symbol.

CSV & Database

Upload CSV or connect Supabase/Postgres. Reconcile in background. Download results as CSV or branded PDF.

Engine 2

AI Reliability

Score AI models. Route questions to the best model. Detect hallucinations. All from response data — no LLM inside.

POST /v1/ai/score

Score

Send 5 AI responses to the same question. Get weighted consensus, agreement score, and per-model reliability.

POST /v1/ai/route

Route

Which model for this question? Based on historical reliability per domain. Save tokens, get better answers.

GET /v1/ai/reliability

Detect

If 4 models agree and 1 says something different → hallucination flagged. No external lookup needed.

Score AI responses

const score = await moresq.ai.score({
  question: 'Average rent in Paris?',
  domain: 'real_estate',
  responses: [
    { model: 'claude',     extracted_value: 1200 },
    { model: 'gpt-4o',     extracted_value: 1350 },
    { model: 'gemini',     extracted_value: 1280 },
    { model: 'perplexity', extracted_value: 1320, has_source: true },
  ]
})
// → consensus: 1291, confidence: 0.80
// → hallucinations: []
// → perplexity weighted higher (has_source)

Intelligent routing

const route = await moresq.ai.route({ domain: 'legal' })
// → { recommended: 'claude', reliability: 0.92,
//    fallback: 'mistral', skip: ['gemini'] }

After 100 queries, Moresq knows:

Claudelegal
0.92
GPT-4ocode
0.88
Geminiscience
0.90
Perplexitynews
0.95
Mistralfrench
0.87

Built for any domain

Data Pipelines

Scrape 5 APIs, reconcile in one call. Replace your custom if/else code.

Multi-LLM Apps

Score model responses, route to the best, flag hallucinations.

E-commerce

Product feeds from 10 suppliers — which price, name, description is correct?

Real Estate

Listings from 17 agencies — reconcile prices, surfaces, locations.

IoT & Sensors

Noisy sensor data → clean consensus. Incremental O(1) updates.

Fintech

Market data from multiple providers — which quote is right?

Replaces

Informatica MDM

$200K/year, 6 months setup

Custom code

300 lines of fragile if/else that breaks at 3am

Great Expectations

Validates rules you define — doesn't discover truth

Tamr / Senzing

Entity matching only — no field-level consensus

No AI scoring tool exists

Moresq is the first

Pricing

Simple. Transparent.

All features included. Both engines. Pay for volume.

Choose your credit

All features. Both engines. Never expires.

10

5,000 resolutions

€5€20

Free

€0

500 resolutions

  • All features
  • All algorithms
  • Data + AI engines
  • No credit card
Get started

Packs

Popular
€29or €79

14,500 or 39,500 resolutions

  • Everything included
  • Data + AI engines
  • Pipeline + matching
  • CSV, database, PDF
Buy credits

Business

€149/mo

500,000 resolutions/month

  • Everything included
  • Priority support
  • Highest volume
  • Predictable billing
Subscribe

Stop guessing.

Two engines. One API. Truth from data.