The model layer
Six models. One clinical record.
A named, versioned model layer, not one prompt behind a chat box. Each model does one job. Together they make up the agents.
The six
Each one does a job you can name.
Speech becomes a note, the note becomes code, and the code becomes a score, an answer and a proposed action.
01: Language to code
IASORA Lex
A note only becomes clinical data when something can name the code and defend it.
SNOMED CT · ICD-10 · LOINC · RxNorm · CPT
Conditions, medications, allergies, procedures, observations
Abbreviations, negation, disambiguation, specialty context, confidence thresholds
Scribe notes, referral letters, uploaded documents
02: Speech to note
IASORA Scribe
The consultation is the richest record in medicine, and the one we most reliably lose.
In the room, on a video call, streaming or batch
50 languages, 72 regional variants
SOAP · progress note · discharge summary · consult letter
DocumentReference, conditions, medications, allergies, provenance
03: Speech to speech
IASORA Voice
Most of a practice's work is conversation. Voice writes it to the chart.
Real-time speech to speech, inbound and outbound
Enquiries · booking · reminders · recall
Against live availability
Communication, Appointment, Task
04: Record to risk
IASORA Risk
A risk score nobody can take apart is a rumour.
Four weighted risk areas, 34 factors, a 0-100 composite, five tiers
NEWS2 · CHA₂DS₂-VASc · CKD-EPI 2021 · Charlson · Elixhauser · HHS-HCC · LACE · NHS eFrailty
Every point traces to a factor, a weight and its source
Deterministic baseline, accuracy and fairness gates, reversible in one step
05: Question to answer
IASORA QL
The people with the hardest questions rarely write SQL.
Count · list · trend · compare · breakdown · distribution
Analytical SQL, written against the FHIR schema
Every query validated before it runs, and workspace-scoped
Analytics Studio, the metrics builder, cohort definitions
06: Evidence to judgement
IASORA Reason
Reason prepares the thinking. The clinician decides.
Deep, standard and fast
Differential reasoning, summarisation, structuring, decision support
The agent workforce
Your approval gate: nothing reaches the chart unapproved
The agent workforce
Each agent works next to a person.
An agent chains these models for one job. It prepares the work; the person beside it decides. Any model can also be licensed on its own.
Patient
AI Call Operator
Answers and makes patient calls, and books against live availability.
Care coordinator
Care Gap Closure
Finds who is overdue for care, and reaches out to them.
Practice manager
No-Show Prevention
Reminds patients before the visit, so fewer appointments are missed.
Clinician
Medication Reconciliation
Checks the medication list against what was said and prescribed.
Clinical director
Risk Stratification
Stratifies the panel and measures the outcome.
Leadership
Ask Your Data
Answers questions about your patients and performance in plain language.
Whichever agent runs, the run is the same six steps
Every step is one authorised, metered and logged call against your workspace.
How they run
Every call is authorised, metered and logged.
The model layer sits behind one gateway: one place where access, cost, residency and audit are decided.
On or off, per workspace
Switch each model on for a workspace at a tier, or leave it off. A clinic that wants only the scribe gets only the scribe.
Metered to the action
Every call is priced and counted where it happened, so each AI action has a cost next to the work it did.
Logged, every request
Which model, workspace and user, what it was asked and what it returned. Written whether or not anyone is looking.
Inference stays in region
Kept inside your jurisdiction, on private cloud or on-premise including air-gapped, for health systems that cannot send data out.
Bring your own keys
Run the layer on your own model credentials, and keep the routing, metering and audit.
Versioned, and reversible
Weights, thresholds and rules change under an audit diff. A change that does not hold up rolls back in one step.
Where the models show up in the product
Scribe and Voice in the consultation and at the front desk, Lex on every document, Risk across the panel, QL in Analytics Studio, and Reason inside every agent.
Get started
Run one model, or the whole layer.
Use the scribe on your own consultations, or talk to us about the model layer inside your own estate.