Where search finds similar text, AiirGap classifies whether two statements can both be true and verifies every evidence quote against the source character by character.
It Shows Its Work
Source-verified evidence and per-token confidence for every finding
Air-Gapped by Design
Fully offline on one workstation. Your documents never touch the internet
Honest About Uncertainty
It says "look at this" rather than "this is broken" and filters false positives first
How It Works
Five stages turn a document set into verified, explainable conflict findings
Contradiction is not one phenomenon. Statements can clash in what they measure, mandate, mean and entail.
Each clash has its own logic. AiirGap brings a specialist reasoner to every fundamental form of disagreement.
See What the Model Was Thinking
Every verdict comes with a certainty card that shows how it was reached. No other contradiction tool puts the model's internals in front of the reviewer
Per-token confidence (hover the words)
Six calibrated internal axes
Where the verdict crystallized
"The model settled this verdict at layer 19 and never wavered."
Built for Your Compliance Review
Air-gapped by design, not by permission slip. Built for the questions a security review asks
Measured, Not Marketed
Every number below traces to a reproducible engineering record. On our held-out evaluation, AiirGap found every planted contradiction and raised zero false alarms.
The entire EU AI Act for a third of a phone charge
One MacBook Pro, 740 comparisons, five contradictions flagged, measured at match sensitivity 0.93. Among them: a deadline that runs four years in one article and seven in another. Each verdict used 37× less energy than a single chatbot prompt, by Google's and OpenAI's own numbers.
Per verdict, everything on
0.958s per comparison through the full production path, with quote verification, model internals and the Jacobian lens live
Of our training data rejected
An adversarial label audit condemned a third of our hand-authored pairs across 10 domains
Chatbot energy per Google (0.24 Wh, median Gemini text prompt) and OpenAI (0.34 Wh, average ChatGPT query); a full AiirGap verdict measured 6.5 mWh. Phone charge relative to the iPhone 16's 13.8 Wh battery. Run measured at match sensitivity 0.93; the shipped default of 0.90 pairs roughly twice as many comparisons and takes proportionally longer. Flagged findings are review queues for humans, not adjudicated errors in the Act.
Where Contradictions Cost the Most
Pharma
SOPs, batch records and GMP obligations that quietly disagree, found before the inspector's walkthrough
Medical Device
Design controls, device files and submissions kept saying one thing across every revision
Aerospace
Engineering specs, maintenance manuals and certification requirements that must never diverge
Energy & Process
Process safety procedures, permits and operating limits reconciled across sites and decades
Engineering & Construction
Specs, drawings and contract requirements aligned before they become claims and disputes
Financial Services
Policies, controls and regulator handbooks in agreement before the audit letter arrives
Legal & Law Enforcement
Contracts, statutes and procedure manuals where the clashing clause becomes opposing counsel's exhibit
Manufacturing
Work instructions, quality manuals and supplier specs that drift apart across revisions and plants