Answers you can prove.
Several AI models from different companies answer your question, check each other against your documents, and show you which statements are confirmed, which are disputed, and why.
No card needed · Your files are never used to train models
Question
Can the supplier share our confidential information with its affiliates without telling us?
Answer
Yes. Sharing with affiliates needs no prior notice, but only with affiliates bound by equally protective confidentiality terms. The agreement has no after-the-fact notice duty.
Checked statements
- 1Models agree
The supplier may share your confidential information with its affiliates without telling you first.
…may disclose Confidential Information to its Affiliates without prior notice to the Disclosing Party, provided that…Master Services Agreement, §7.2
- 2Models agree
Those affiliates must be bound by confidentiality terms at least as protective as this agreement.
…each Affiliate is bound by obligations no less protective than those set out herein.Master Services Agreement, §7.2(b)
- 3Disputed
The supplier must tell you within 30 days after sharing.
3 of 4 checks found no such clause in the agreement. Removed from the answer.
Use any top AI model for drafts. Use Danphe when a wrong answer is expensive.
How it works
How a question is checked
- Step 1
Reading sources
Your documents are read and the passages that matter to the question are found.
- Step 2
Models answer on their own
Models from different companies answer independently, without seeing each other's answers.
- Step 3
Cross-checking every statement
Each statement is checked by models from other companies against your sources, with quotes.
- Step 4
Writing the answer
An editor writes the answer from what held up, and marks what didn't.
Labels
Every statement gets a verdict
The answer is split into individual statements. Each one carries a label with an icon and a word, never colour alone.
- Confirmed
Checked and certified
Independent models checked this against your sources, and this workspace has a signed-off calibration, so the error rate of “Confirmed” statements is measured.
- Models agree
Backed by independent checks, with a quote (not certified)
Independent models checked this and it is backed by a quote from your sources. It is not marked “Confirmed” because this workspace has no signed-off calibration yet, so the error rate of these statements has not been measured. Check the quote if the decision matters.
- Not settled
Backed, but not certified
The independent checks were mixed, or the point is backed but without a quote from your sources. Check the source before relying on it.
- Not supported
No model could back this up
Independent checks found no support in your sources, or found evidence against it. It was removed from or flagged in the answer.
- Opinion
A judgement, not a checkable fact
Recommendations, interpretations and other judgements. They are shown for context but cannot be proven true or false from the sources.
“Confirmed” vs “Models agree”: a statement is only marked “Confirmed” in a workspace with a signed-off calibration, where the error rate of confirmed statements has been measured. Without one, the same evidence is labelled “Models agree”. No label is a guarantee that a statement is true.
Dissent
Disagreement is shown, not hidden
When models read your sources differently, you see both readings and the quotes behind them, instead of a confident average.
Do we pay a fee if we end the contract early?
Reading A · 2 models
The early-termination fee applies whenever you end the contract for convenience.
If Customer terminates for convenience, Customer shall pay the Early Termination Fee.Services Agreement, §12.3
Reading B · 2 models
The fee no longer applies after the first contract year.
Section 12.3 shall not apply after the first anniversary of the Effective Date.Services Agreement, §12.4
Use cases
Built for work that gets checked
- LegalContract and policy questions, with the clause quotedLearn more
- ResearchLiterature and paper questions, checked against the paperLearn more
- AuditCheck reports for errors and unsupported statementsLearn more
- EducationFair, specific feedback on student workLearn more
- FinanceQuestions about filings and financial documentsLearn more
Accuracy
Measured, not promised
We test on questions the system has never seen, with the rules written down before the run. On short closed questions Danphe matches the best single model; the gain is that every statement is checked and quoted.
- 85.1%Smart mode accuracy
- 95% CI 81.6–88.1%, on 483 unseen questions across five domains.
- Matchesthe best single model
- Claude Opus 5.5 alone: 83.4%. The difference is not significant (p = 0.13), so we don't claim to beat it.
- +4.1 ptsover GPT-6.1 Sol alone
- 81.0% for GPT-6.1 Sol alone. Significant (p = 0.002).
- $0.24average cost per question
- Smart mode, model costs only. One model alone costs about $0.01–$0.06.
Locked test, n = 483, run November 2026, preregistered on 5 November 2026 before any run. Exact McNemar tests, strict scoring, failures counted as wrong. How we measured
Evidence
An audit record for every answer
Download an evidence pack for any answer, as JSON for your systems or as a printable page for a reviewer. Records are hash-chained and anchored with a signing key, so a later change to a record can be detected.
Every model's answer
Who answered, in what order, with which settings.
Sources and quotes
The exact passages each statement relies on.
Every check
Each checker's verdict, including the ones that disagreed.
Hash chain
Tamper-evident links between records, verifiable offline.
Your documents stay yours
We hold no security certifications yet; SOC 2 is planned. Here is what is in place today.
Read the security overviewEncrypted per tenant
Encrypted in transit and at rest, with a separate key for each organisation.
Isolated by design
Database row-level security keeps every organisation's data apart.
Never used for training
Your files and questions are not used to train models.
Tamper-evident audit
Every answer's record is hash-chained and signed.
Pricing
Start free, upgrade when it matters
Every plan uses several models from different companies that check each other.
Free
Try the council
$0 / month
60 credits a month, no extra usage
Start free (Free plan)Pro
Most popularFlagship models, and every model and algorithm setting is yours
$49 / month
200 credits a month, then $0.26 per credit
Start with Pro (Pro plan)Pro Max
Your own councils and long documents
$199 / month
800 credits a month, then $0.24 per credit
Start with Pro Max (Pro Max plan)Ask your first question in two minutes.
Free plan, 60 credits a month, no card needed.