STEP 1
You send a document
A PDF, or plain text. Nothing is written to disk and nothing about what it says is logged. We do not keep your manuscript.
Provenance means the record of where something came from. Some documents carry one. We read it, check the signature, and hand you a result you can keep and show to someone else. When a document carries nothing, we say so plainly instead of guessing.
We are not an AI detector. We do not score how AI-sounding your writing is, and we never accuse anyone.
A PDF, or plain text. Nothing is written to disk and nothing about what it says is logged. We do not keep your manuscript.
Some files carry a signed record of how they were made, and some AI writing carries a hidden marker. We look for both, and we check the signature is genuine and has not been altered.
A plain answer, the evidence behind it, and a certificate anyone can re-check later. If we found nothing, it says so.
Most of this industry describes what it intends to do. We publish a table of what actually happens when you send us a document, including the checks that are not available to us yet. We would rather lose a sale than have you find that out later.
Signed records attached to a file. We read them and verify the signature.
Only where the keys are known to us. Not Google’s production watermark.
Detection is private preview. We have not been granted access.
Bring your own. Weighted by how often it is wrong, never an accusation.
Plug in your own commercial detector API, alongside our native provenance signals, or on their own. Your key, your account, your data terms. We add the evidence a detector can't see, and we tell you how much to trust the score you're paying for, measured against our own held-out human text, not the vendor's advertised figure.
Provenance-first: watermarks, C2PA, and our own calibrated signals. No third party required.
Your detector subscriptions, run through one report, each one calibrated to its real false-positive rate.
Native provenance and your detectors, combined, with disagreement surfaced, never averaged away.
Every third-party detector stays a calibrated, capped input, it can never, on its own, produce an accusation.
Provenote is on the trust side. We verify provenance and calibrate uncertainty. We do not strip, weaken, or evade watermarks or detectors.
Provenote answers one question, how was this content made?, for the people on both sides of it: those who must decide whether to trust a document, and those who must defend one they wrote.
When you submit work and your authorship may be questioned.
A tamper-evident record of how your draft actually came together, built as you write, plus a signed certificate anyone can re-check. If a detector flags you, you answer with evidence instead of your word.
When an essay you genuinely wrote gets flagged.
A verifiable writing record you build while you work, so a challenge is answered with evidence rather than argument. We never issue an accusation, and we tell institutions plainly that a detector score, on its own, does not establish that someone used AI.
When you must make a decision that affects a student’s record.
Provenance-first evidence, plus each detector’s measured false-positive rate rather than its marketing number, so a case rests on something checkable and due process is documented.
When a submission arrives and you must decide what to trust.
An auditable provenance report per manuscript: content credentials and provider watermarks read for you, uncertainty stated plainly, and a record you keep.
When authorship or content origin is contested.
A signed, tamper-evident record with a documented method and stated uncertainty. We provide a technical record, not an expert opinion, a forensic report, or legal advice. Whether it is admissible is for the court and your jurisdiction to decide.
When you publish, procure, or carry disclosure duties.
Verification at scale through an API, plus exports you can use as part of your own EU AI Act Article 50 evidence, and support for your own detector keys. Compliance-supporting, not legal advice, confirm your position with counsel.
We serve the university and the student, the journal and the author. That is deliberate. A verification layer that only ever works for one side is not neutral, and neutrality is the entire product.
One thing we will not do for anyone: tell you a human wrote something. Nobody can do that reliably. We prove provenance when it is there, and we are honest about uncertainty when it is not.
Provenote produces technical evidence and stated uncertainty. It does not render verdicts about people, and nothing here is legal advice.
Because verification isn’t for the person making the claim, it’s for everyone who has to trust it.
A self-declaration can’t be checked, doesn’t say which parts or how much, and binds no one. It’s a claim.
Provenote confirms how content was made from signals a third party can verify, a watermark, a credential, a signed record, without taking anyone’s word for it.
The value is for whoever must trust or comply, a journal, university, platform, or court, and for an honest writer defending against a false accusation.
Just disclosing on a low-stakes personal post? You may not need us, and we’ll say so. Read the FAQ →
Join the private beta. Tell us where you feel the cost of getting provenance wrong.