ClinicalListed · screen comingClinical record

RareFind

Collectively not rare: 300 million people, years to a name.

Notify meJoin the early-access listHow pricing works →

What it is

A rare-disease flag is a rule family in the Rules engine — a set of rules evaluated together at one decision point over the findings the record holds, raising a flag for review — and that engine already exists as an API (POST /rules/definitions with a family, POST /rules/evaluate), with no screen of its own. No code was added for this idea, because the raising is already done. What is left of it is the part that needs data the product does not hold: the combinations of findings that should trigger the question are reference data nobody has supplied, so no rare-disease rule family is loaded, nothing matches a patient into a registry or a trial, and no registry link exists.

Who uses it: Built for: Every specialty
Reads: The patient record, through the Rules engine
Writes: Nothing
Never: It does not pronounce a diagnosis or suggest one — no phenotype criteria are typed here — and it does not match anyone to a registry or a trial: no such link exists in this product.
Access: Only people whose role includes it — the clinic owner decides who
Your data: Full PHI. Hosted in Boston, United States. On uninstall: Every record stays; only the workflow leaves.

How it works

The usual shape of a clinical record app. RareFind’s own steps are written from its screen when it ships.

Open the patientThe chart opens with allergies, medicines and recent results on screen.
Write itType, dictate or accept the AI draft — structured, not free text.
Sign itNothing is saved until you sign; safety checks run first.

Rules it keeps

What it does not do, by design. A listing with only benefits is an advertisement.

It does not pronounce a diagnosis or suggest one — no phenotype criteria are typed here — and it does not match anyone to a registry or a trial: no such link exists in this product.

AI in RareFind

AskQuestions about what is on screen — “What needs attention in RareFind today?” — answered with the records it read.

DraftSummaries and notes for the team, marked as drafts until a person signs.

Every answer shows its sources. Nothing AI writes is saved until a person accepts it.

Questions clinics ask

What does RareFind do?

Collectively not rare: 300 million people, years to a name. A rare-disease flag is a rule family in the Rules engine — a set of rules evaluated together at one decision point over the findings the record holds, raising a flag for review — and that engine already exists as an API (POST /rules/definitions with a family, POST /rules/evaluate), with no screen of its own. No code was added for this idea, because the raising is already done. What is left of it is the part that needs data the product does not hold: the combinations of findings that should trigger the question are reference data nobody has supplied, so no rare-disease rule family is loaded, nothing matches a patient into a registry or a trial, and no registry link exists.

What data does RareFind read and write?

RareFind reads the patient record, through the Rules engine and writes nothing. Its data class is Full PHI. Every app works on the same patient record — nothing is copied into a silo.

What does RareFind deliberately not do?

It does not pronounce a diagnosis or suggest one — no phenotype criteria are typed here — and it does not match anyone to a registry or a trial: no such link exists in this product.

What happens to our data if we uninstall RareFind?

Every record stays; only the workflow leaves.

Is RareFind available today?

RareFind is in design: the surface exists and the platform underneath is ready. Join the waitlist and it moves up the build order.

Want to see RareFind running on your own patients?

Tell us what you run and we will show you this app inside a practice shaped like yours — or answer the question the page above did not.

More in Clinical

All 434 →