When an AI produces a clinical output, a licensed, specialty-matched physician reviews it and signs — or declines. The decision becomes a hash-anchored receipt on a public ledger: a record anyone can verify, without trusting us.
ClinicalSwipe is a working system in a pre-go-live pilot, and we would rather you read that here than discover it later. The review loop, the specialty gate, the receipts and the public ledger anchoring all run today. What is not yet in force: no BAA is signed, so every case runs on synthetic or de-identified data; the qualifying-condition criteria await the Medical Director’s sign-off; and reviewer malpractice, AI-liability and cyber coverage is arranged but not bound until before the first real case.
“Specialty-matched” is enforced in code and it fails closed: a reviewer is shown only cases inside their own specialty, and an output with no matching reviewer is held, never quietly signed by whoever is available. The honest consequence is that our live coverage is narrow — family medicine and primary care today. If your output sits outside that, the gate will hold it rather than pretend.
We publish this because the product is accountability. A service that overstates its own readiness has already failed the thing it sells. What a company gets today →
A clinical output that needs a licensed human behind it — a determination, an assessment, a letter.
An NPI-verified, licensed physician evaluates it in their own specialty and signs, revises, or declines — with a documented rationale. No rubber stamps.
Signed, timestamped, and fingerprinted — a SHA-256 anchor on a public ledger that survives audit, staff turnover, and us.
Read the AI's draft, catch what's wrong or missing, and decide. Drag the card — right to approve, left to reject, up to revise — or tap. Three real cases.
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 →
A real ledger anchor from the 2026-08-20 demo — synthetic case, real anchor; the fingerprint contains no name, no diagnosis, no PHI.
Every determination is owned by a real, specialty-matched physician — not an algorithm, and not a stranger to the field.
A physician who can decline is what makes the "yes" mean something. The decline is a feature, not a failure.
Reviewers earn the same flat fee whether they sign or decline — and we take no percentage of any claim, sale, or savings. Economics that keep the no honest.
Signed, timestamped, anchored, and retained — a record built to survive review, not just to look official.
That headline above used to be a design opinion. Two things happened this year that make it a requirement somebody else writes down.
The ACCESS Model — Advancing Chronic Care with Effective, Scalable Solutions, live since 5 July 2026 and running ten years — requires participating organisations to designate a physician Clinical Director responsible for clinical oversight and compliance. Not a nice-to-have. A condition of participating at all.
ARPA-H’s ADVOCATE programme — $62.7M over four years — separates the acting agent from a second, independent supervisory agent, with an outside laboratory evaluating both. Faced with making clinical AI trustworthy at national scale, nobody proposed a bigger review committee.
In that architecture the named human sits at escalation and accountability, not at accuracy. Which is exactly the split this product was built on: cheap deterministic checks catch what is checkable, and a licensed human owns what carries judgement.
A human in the loop buys accountability, not accuracy. The evidence does not support “reviewed, therefore more accurate,” and we will not claim it. Design the human for ownership; use checkers for correctness.
Sources are the CMS and ARPA-H programme pages, read 10 September 2026. ⛔ Nothing in ADVOCATE is FDA-authorised — authorisation is that programme’s stated goal. The full derivation is at solvinghealth.com/model.
Exercise therapy, nutrition, sleep, recovery, aging at home — and the care a family gives a parent. One independent physician's determination, written honestly, decides whether it counts. An honest no costs the same flat review fee as a yes.
Review AI-generated clinical outputs in your own specialty, on your own time. NPI-verified, clear scope, no shifts and no minimums.
Apply with your NPI →Give your AI outputs a licensed, accountable physician signature and an audit-ready, ledger-anchored record — without building a clinician network yourself. Or try the sandbox first.
Start a conversation →Coaches, gyms, wellness brands: an independent physician reviews each customer's case and signs a Letter of Medical Necessity — or declines honestly. One flat fee per determination, paid by you — never by your customer; receipts for everyone.
See the partner motion →