AI drafts it.
A licensed physician signs or declines.

Your AI writes the clinical document. A licensed physician in the matching specialty signs it or declines it in writing, and you get a receipt anyone can check.

Physicians: apply to review or check a draft before you sign.

Caring for a parent? Get a plan in six questions, no account.

SYNTHETIC SAMPLECare assessment
AI output

Meets criteria for skilled home nursing 3×/week. Fall risk 4/5.

Flag: the needs listed read as companion care, a different benefit.
The physician’s decision
Decision receiptSample · not anchored
DecisionREVISE
ReviewerMD · independent · specialty-matched
SHA-256 · made in your browsercomputed when a decision is made
Madeon your device
Verify a real demo anchor on the public ledger →

Same flat fee whichever you tap. Once cases go live, each decision is anchored to hashcare.com and countersigned into Bitcoin daily; this sample is not.

VALIDATIONNPI-verified reviewers NEUTRALITYFlat fee — same for yes and no PRIVACYHash-only receipts · no PHI FINALITYCountersigned into Bitcoin daily
This is the whole job

A review is one card. Swipe it.

Read the AI's draft, look for what's wrong or missing, and decide. Drag the card — right to approve, left to reject, up to revise — or tap. Three sample cases, synthetic.

ClinicalSwipe
3 in queue
Every decision is signed under your NPI and audit-trailed. You're attesting documents, not treating patients.

These cards show the flag. The review drill hides it: five cases, your call, then the reference answer and its source.
The proof layer

Every decision ends in a receipt.

Signed is good; provable is better. Each determination — yes or no — is fingerprinted and anchored to a public ledger, countersigned into Bitcoin daily. An auditor verifies it in one click, without trusting ClinicalSwipe. Read the whole ledger →

Attested decision receipt

Demo specimen
DeterminationQUALIFY
ReviewerMD · independent · specialty-matched
SHA-2563978a3160bbe1d04f55b47893fdec48bb03977159573b208633da4cced99f78f
Anchored2026-08-20 20:17:36 UTC
Verify on the public ledger → How to check it yourself

A real ledger anchor from the 2026-08-20 demo — synthetic case, real anchor; the fingerprint contains no name, no diagnosis, no PHI.

The whole thing, animated

ClinicalSwipe in 15 seconds

Text version:
  1. The AI called it skilled nursing. The notes say meals, reminders and supervision: companion care.
  2. A review is one card. Swipe it. Right to approve, left to reject, up to revise. Only in your specialty.
  3. Yes or no, it becomes a receipt. A fingerprint, no patient data, on a ledger anyone can check.
  4. Try three sample cards. Then apply. Synthetic cases today. Your NPI is checked against NPPES.
  5. ClinicalSwipe. The accountability layer for healthcare AI. clinicalswipe.com
Honest state
Where this is today

A pre-go-live pilot. The review loop, the specialty gate and the receipts run today, on synthetic or de-identified cases only until the physician goes live; our vendor BAA with Google Cloud is in place (a customer BAA with each company comes before any of its PHI), and reviewer malpractice coverage must be bound before the first real case. Review coverage is family medicine and primary care; the specialty gate holds anything else rather than let whoever is available sign it. The qualifying conditions are in the protocol.

Four worked cases

What the physician did with the draft.

Each case below is illustrative, not a real case. They show the kinds of decision the review loop records. Real cases will replace them as they are signed or declined, with their receipts.

Illustrative, not a real caseDeclined

A gym plan written up as medical care.

The AI drafted
A letter of medical necessity for a general fitness membership, for someone who wanted to lose weight.
The physician
Declined, with the reason in writing.
Why
The packet named no diagnosed condition the program treats. Exercise for general health is not medical care under the IRS rule, so there was nothing to certify.
The receipt records
The decline, the reason, the physician's role, the AI model that drafted the letter, and a fingerprint of the decision. No name, no diagnosis.
Illustrative, not a real caseRevised

Skilled nursing, where the notes say companion care.

The AI drafted
A home-care determination calling for skilled nursing.
The physician
Sent it back with changes: the category is companion care.
Why
The notes describe meals, reminders and someone nearby, not nursing tasks. The draft put the need in the wrong benefit category.
The receipt records
That changes were requested, what they were, who asked for them by role, and the model that drafted the first version. The revised draft comes back as a new version for a new decision.
Illustrative, not a real caseSigned

Strength training for diagnosed low bone density.

The AI drafted
A letter of medical necessity for a supervised strength program, citing a bone density report.
The physician
Opened the report, checked the draft against it and against the protocol criteria, and signed.
Why
The diagnosis was in the source document, the condition is on the protocol’s list, and the program treats it.
The receipt records
The signature, a fingerprint covering the letter and the report it relied on, the signer's role, and the model and version that drafted it.
Illustrative, not a real caseSigned

It looked wrong. It was right.

The AI drafted
A letter for resistance training that read, at first glance, like a fitness plan.
The physician
Recorded a first read of “decline” before seeing the draft, then opened the source: a diagnosed loss of muscle linked to a weight-loss medicine, a condition on the protocol’s list. Signed as drafted.
Why
The source document, not the first impression, decides. The draft matched it.
The receipt records
Both the first read and the decision, so anyone can see the physician changed their mind and why, plus the model that drafted the letter.

The ledger lists every decision in one table. Every real decision, signed, revised or declined, goes on the public ledger as a fingerprint with no patient data. Check a receipt yourself.