Mastodon

Verify AI answers before you act on them.

One AI can be confidently wrong. IamVera is a multi-model AI verification layer for professionals. Claude answers, GPT fact-checks, Grok challenges and Perplexity verifies live sources — helping surface potential hallucinations and unsupported claims before they enter professional work.

Powered by

Claude GPT Grok Perplexity via OpenRouter

Built in the EU · Designed for professional workflows

Detect potential AI hallucinations before they enter professional work

Generative AI can be fluent, confident and wrong. For professionals who act on AI output, undetected hallucinations, unsupported claims and missing sources create avoidable risk.

Confident
AI models are optimised to sound fluent and certain. That fluency does not track accuracy — on its own, a verified fact is indistinguishable from a confident guess.
Hours
spent manually cross-checking AI output across multiple tabs — the workflow Vera replaces with a single, transparent chain
"You wouldn't publish a single unverified source. Why would you publish a single unverified model?"

AI answer verification — what Vera is and what it isn't

Verification only earns trust if it's honest about its own limits.

What Vera is

An AI answer verification layer for professional work. Vera cross-checks one answer through independent models that audit facts, challenge reasoning and verify live sources, then shows every correction, disagreement and source behind the final answer.

What Vera is not

Not a single language model. Not a guarantee of truth. Not a replacement for professional judgement. Final responsibility for acting on an answer stays with you.

How multi-model AI verification cross-checks an answer

Every Vera answer passes through a configurable, auditable AI verification chain. No single model has the final word without independent factual review, adversarial challenge and source verification.

Claude creates the initial answer

Claude (Anthropic) formulates the initial answer using its full reasoning capability. This becomes the baseline that every subsequent model evaluates — not a final answer, but a starting point for structured verification.

Example output
The GDPR came into effect on 25 May 2018.

GPT performs a factual audit

GPT (OpenAI) receives Claude's answer and independently verifies each factual claim. Corrections, confirmations, and confidence levels are returned — not as a replacement answer, but as a structured audit of the first response.

GPT fact-check output
✓ Confirmed: GDPR enforcement date is 25 May 2018.
Regulation (EU) 2016/679 — no errors detected in this claim.

Grok performs an adversarial challenge

Grok (xAI) plays devil's advocate. It looks for missing context, ambiguous framing, and important distinctions that the first two models may have glossed over. Disagreement is a feature, not a bug.

Grok challenge output
⚠ Nuance: GDPR was adopted 27 Apr 2016 and entered into force 24 May 2016.
"25 May 2018" is the date of application. Entry into force ≠ application — the distinction matters in legal contexts.

Perplexity verifies live sources — Claude synthesises

Perplexity performs a live source check, grounding the answer in citable references. Claude then synthesises all model feedback into a final, consolidated answer — with every correction and source visible.

Final verified answer
GDPR adopted 27 Apr 2016, entered into force 24 May 2016, applicable since 25 May 2018.
Source: EUR-Lex, Regulation (EU) 2016/679

An auditable AI verification chain — not a black box

Every verification step is inspectable. You see the factual audit, adversarial challenge, AI source verification and final synthesis — including corrections, disagreements and supporting references.

Q: When did the GDPR come into effect, and what regulation number is it?
Vera — Verified answer
The GDPR was adopted on 27 April 2016, entered into force on 24 May 2016, and became applicable on 25 May 2018. It is formally known as Regulation (EU) 2016/679. (Source: EUR-Lex)
C
Claude — Initial answer
The GDPR came into effect on 25 May 2018.
G
GPT — Fact-check
✓ Enforcement date confirmed. Regulation number: EU 2016/679 — added for completeness.
X
Grok — Challenge
⚠ Distinction flagged: GDPR adopted 27 Apr 2016, entered into force 24 May 2016, applicable 25 May 2018. Entry into force ≠ application. Relevant in legal contexts.
P
Perplexity — Source check
EUR-Lex confirms: adopted 27 Apr 2016, entered into force 24 May 2016, applicable since 25 May 2018. Grok's distinction verified.

Published AI verification evidence — including failures

We publish behavioural tests of the multi-model AI verification chain, including factual traps, source-grounding checks, prompt-injection resistance, raw run data and the cases where the chain fell short.

Method

Tests for factual traps and potential hallucinations

False-premise traps, source grounding, prompt-injection resistance and adversarial pressure to guess — each run through the configured chain and scored by deterministic checks.

Honesty

Failures and disagreements are visible

Where a check fails or the models disagree, we show it. A benchmark that only ever passes proves little; the disagreements are where the chain earns its keep.

Raw data

Inspect the raw verification data

Every result links to the underlying JSON: model calls, corrections, costs and judge output. Nothing summarised away.

You decide how much verification each question deserves

Configure the chain per session. See tokens and cost per model call. Verification depth is your choice — and so is the bill.

Get early access — pricing announced at launch →
C
Claude
Answer
G
GPT
Fact-check
X
Grok
Challenge
P
Perplexity
Source check
Claude (answer)~$0.003
GPT (fact-check)~$0.002
Grok (challenge)~$0.001
Perplexity (sources)~$0.005
This verification~$0.011

AI for confidential documents

Vera supports privacy-preserving AI document analysis through the Semantic Privacy Shield. Before a document reaches any external AI model, detected sensitive values are replaced locally with synthetic, session-only equivalents. The approved synthetic context can then be analysed while the original values remain inside the protected Vera environment. This utility-preserving transformation retains relevant roles and relationships while reducing exposure of identifying data.

1 · Detect and pseudonymise locally

Names, dates, minors, diagnoses, criminal-law context, case numbers — replaced locally with realistic synthetic values. Roles and relationships stay intact, so the AI still understands the file.

2 · Verify the outbound context

A local check confirms no detected real values remain in the prepared text. If it is not clean, nothing is sent. Fail closed — no exceptions.

3 · Restore original values locally

The verified answer is restored locally with the original values. You get a normal, usable answer — the public AI never saw the real data.

// Sent to the AI chain — fictional example
Mrs. Dylan Knoers [[DOC001_ADULT_PERSON_001]] states that her ex-partner Mr. Tobias Evers [[DOC001_ADULT_PERSON_002]] became aggressive on 06-01-2026 [[DOC001_DATE_001]] during the handover of her minor daughter [[DOC001_MINOR_CHILD_001]].

Built for professionals bound by confidentiality — lawyers, notaries, judges, physicians, occupational health physicians, psychiatrists, investigative journalists.

Secure AI document analysis and controlled editing

Vera Office combines privacy-preserving AI document analysis, multi-model verification and controlled AI document editing inside a browser-based DOCX workspace. Open a document and ask, for example:

"Summarise this document."

"Rewrite this paragraph more formally."

"Replace this phrasing throughout the document."

Privacy Shield before external AI processing

Vera processes the document content through the Semantic Privacy Shield. Sensitive values are replaced locally before the selected AI models analyse the document. Afterwards, the necessary values are restored locally.

Validated document changes

For edits, Vera first builds a controlled action plan. Only validated changes are executed and saved — a model never gets unrestricted access to your file.

Discover Vera Office

Document analysis, multi-model verification and controlled document editing in one secured working environment.

Designed for data control. No hidden flows.

A verification tool that obscures its own data handling would undermine the very thing it promises. So we don't.

PDF files not permanently stored

Documents are processed temporarily in memory for the active chat run. Only metadata is retained for session history. Files are not written to disk.

Transparent model routing

Model calls — including document content in the context — are sent to the configured AI providers via OpenRouter. This is stated clearly, not buried in a privacy policy.

Built in the EU

Vera is built and operated within the EU. We are working toward full GDPR processor documentation. We will only claim compliance when the documentation is complete.

Built for professionals who cannot rely on one unchecked model

Vera is designed for work where AI output is acted upon — not just read.

Legal

Legal research & compliance

A compliance officer uses Vera to verify regulatory summaries before they become internal policy. Every claim is traceable to a source — or flagged as unverified.

Full case study — coming soon
Journalism

Investigative journalism

A journalist uses Vera to fact-check background research before publication. Grok surfaces the contested claim; Perplexity finds the primary source.

Full case study — coming soon
Research

Academic & policy research

A researcher uses Vera to cross-check AI-generated literature summaries. The chain catches outdated statistics before they enter a published report.

Full case study — coming soon

AI answer verification: common questions

Direct answers about multi-model AI verification, potential hallucinations, source checking and confidential documents.

Use independent checks for factual claims, reasoning and sources rather than relying on the original model alone. Vera automates this by routing the answer through a configurable multi-model AI verification chain and exposing each correction, disagreement and source. The result remains subject to professional judgement.

Vera does not claim to identify every hallucination. It reduces the risk of undetected errors by having independent models audit factual claims, challenge assumptions and verify live sources. Conflicts are surfaced rather than hidden, so unsupported claims and missing evidence are easier to inspect.

A single model produces and judges its own answer. Vera separates roles across independent models: one formulates, another audits facts, another challenges the reasoning and another verifies sources. No single model has the final word without review.

Yes. Vera runs every model selected for the session in its configured role and records the resulting findings, corrections, sources, token usage and cost. The exact models can be configured per session.

When source verification is selected, Perplexity checks current public sources and returns references for the claims under review. Claude then incorporates justified findings into the final answer. The sources and model steps remain visible for inspection.

No. It means the answer passed through independent factual audit, adversarial challenge and live source verification, with corrections, disagreements and sources shown. Vera does not guarantee truth; it makes the verification behind each answer inspectable.

Vera's Semantic Privacy Shield transforms detected sensitive values inside the customer-isolated Vera environment before approved context is released to external models. A local privacy gate checks the outbound text and blocks transmission if verification fails. This reduces exposure but does not guarantee that every indirect identifier can be detected.

Vera surfaces disagreement rather than collapsing it into a false consensus. The final synthesis can incorporate justified corrections, preserve unresolved uncertainty and show which model raised each issue. You can inspect the evidence and remain responsible for the decision.

PDF files are not permanently stored by Vera. They are processed temporarily in memory for the active chat run; only metadata is retained for session history. Model calls, including document content in the context, are sent to the configured AI providers via OpenRouter.

Yes. You configure the verification chain per session. You can choose which models participate, see the tokens and cost per model call, and decide how much verification depth each question deserves.

Stop trusting one model. Start verifying.

Vera replaces blind trust with structured verification. Every step visible. Every source traceable.

No credit card required · One email when your access is ready · Built in the EU