| What it does | An API that verifies each RAG response against its sources
| AI verification layer for professionals to check AI answers for facts, reasoning and sources
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | FR
| NL
|
|---|
| Pricing model | Contact for pricing
| Not given
|
|---|
| Pricing | Not given
| Starter (Free): 10 checked questions/month; Essential €79/month (€66/month yearly): 50 questions/month; Professional €199/month (€166/month yearly): 300 questions/month, 5 users; Compliance €399/month (€333/month yearly): 1,000 questions/month, 25 users. Evidence Engine module €250/month (€209/month
|
|---|
| Key features | - Response verification against source documents
- Confidence levels: certain, probable, or I don't know
- Nightly automatic improvements with proof
- REST API with coming Python and TypeScript SDKs
- LangChain and LlamaIndex integration support
- MCP server integration option
- Data hosted in Paris, Europe
- Full verification in French and English
- Graceful degradation if API fails
- User data never used for AI training
| - Multi-model fact checking with independent verification by different AI models
- Critical counter-reading to identify weak assumptions and missing arguments
- Source verification with current citations for claims
- Visible verification trail showing every step and model disagreement
- Semantic Privacy Shield for pseudonymisation of sensitive data
- Vera Office for document analysis and editing with automatic checks
- Vera X-Ray for local data discovery before sending to Vera
- Transparent cost tracking per verification step
- API integration for connecting to custom software
|
|---|
| What makes it different | - Honest "I don't know" instead of hallucinated answers
- Proven improvements: 31 out of 32 correct on sealed test set
- Drops in after your existing RAG: one API call only
| - Uses multiple independent AI models to check each answer, preventing any single model from having the final word
- Shows all model disagreements and corrections visibly rather than hiding them behind a confidence score
- Transparent about limitations and does not claim to eliminate hallucinations
- Built in the EU with data processing in customer-isolated environments
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | 28 ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 20 |
|---|
| Citation Flow (Majestic) | 0 | 35 |
|---|
| Referring domains (Majestic) | 0 | 135 |
|---|
WYRLO
I am Vera