Scriba
Scriba is nexmin's observation engine: the clinical notary. It turns an hour of audio or transcript into a structured clinical note (SOAP, GIRP, free format) without inferring anything that has not been said. Precision without interpretation — that is the rule.
Scriba listens to the session and produces the record. Its job is deliberately bounded: it extracts what was said, organises it in the clinical format the therapist has chosen, and pulls metrics straight from natural language (frequencies, repetitions, presence of affect). It never adds context that was not in the audio, never fills gaps with plausible guesses, never interprets. That restriction is precisely why Scriba exists as an independent engine. A generalist model that writes the note while also opining on the case contaminates the data with premature hypotheses. If those hypotheses later turn out to be wrong, the clinician can no longer separate what the client said from what the model believed it heard. Scriba protects that boundary. What Scriba does well: it reduces 60 minutes of session to the note the therapist would sign as their own — in their format, in their style — leaving room for the clinician to edit before closing the record. Interpretation of the captured material lives in another engine — Pensa.
Inside nexmin
Scriba is invoked when a session is closed in nexmin (in-person, telehealth or by uploading audio). The draft lands in the clinician's inbox; they edit and approve it before it enters the chart — the Trust Loop pattern. The validated note is the source over which Pensa later reasons.
Related terms
Last updated: 2026-06-11