φ(ai) PHI AI
Menu
Clinical workspace
Patients & charts PHI AI assistant Signature queue Ambient documentation Imaging worklist Summarization Inbox triage Patient instructions
Revenue & records
Claims & billing Prior auth & appeals Documentation gaps Release of information Sensitive categories
Population
Cohort builder No-show risk Scheduling optimization Trial pre-screening Quality measures Ingest & mapping QA Data Store
Integration
Source & target EMRs Source patient import Bulk import manager Streaming data Bulk export manager Streaming export
System
Control panel Model monitoring
Governance
Registry & preflight Fairness screen Ambient consent gate Source attributes EMR conformance Retention Audit
Documentation
System documentation Implementation & setup guide Feature documentation System architecture EMR connections Emulators & non-PHI setup Compliance & responsibility Attribution
Ryan GomezRole
Signed in — Ryan Gomez · System Administrator
You stay on this screen — each role sees it as their own permissions allow. The assistant thread and the patient in context start fresh.
Working archetypes — combinations people really hold
One role at a time — each role on its own
DocumentationDocs
System documentation Implementation & setup guide Feature documentation System architecture EMR connections Emulators & non-PHI setup Compliance & responsibility Attribution
Repository
In context Alejandra Abebe MRN-227559 · born 1985-01-01 ✦ AI Ask ✦ AI Ambient note Chart

Prior authorization & appeals

AI evidence assembly is the core of this screen: the prior-auth evidence assembler retrieves the specific chart entries behind each payer criterion — the diagnosis, the order, the result series, the training note — and cites each. A criterion without evidence is shown as a gap; nothing is inferred to fill one, because a prior auth built on invented evidence is fraud.

AI core: Prior auth evidence assembler v1.0 · retrieval · managed in the Control panel
Alejandra Abebe MRN-227559 Payer Medicaid Criteria set Continuous glucose monitor — commercial payer
CriterionStatusEvidence from the Data Store
Type 1 or type 2 diabetes diagnosis met conditions · Type 2 diabetes mellitus (disorder) · onset 2022-09-28
Intensive insulin regimen unmet No active insulin order. Shown as a gap; nothing is inferred to fill it.
Four or more glucose results documented unmet Fewer than four glucose results in the Data Store.
Visit with the prescribing clinician in the last 18 months met encounters · Follow-up encounter (procedure) · 2026-01-06 12:00:00
Documented training on device use unmet No record supports this. Shown as a gap; nothing is inferred to fill it.
Packet incomplete — 3 criterion(s) unmet. The gap is shown as a gap; nothing is inferred to fill it. An appeal would re-run retrieval against the denial reason with the same citation discipline.
The assembler composes the appeal from the criteria above — gaps acknowledged, never papered over — and the draft lands in the signature queue. Nothing is sent until a clinician signs.

✦ AI Bring your own payer policy

Paste any payer policy and the assistant extracts an evaluable criteria checklist from it, then evaluates each criterion against Alejandra Abebe's chart facts — met, unmet, or honestly not evaluable. The policy text is treated as data: criteria are extracted, instructions inside it are ignored.