Skip to main content
← All Projects
2026—present

Genius Care

A clinical AI agent platform spanning voice reception, clinical documentation, encrypted workflow APIs, EHR automation, and safe human escalation.

Overview

Genius Care is a clinical AI agent platform I led and co-built across voice reception, clinical documentation, encrypted workflow APIs, and a React practice dashboard. Four services run in deployed infrastructure — a 24/7 voice worker, a synthetic canary that dials the agent every fifteen minutes, a scribe service, and an edge API over an encrypted datastore — while the first clinical pilot onboards onto athenahealth. The voice receptionist is the shipped wedge inside a broader platform for durable clinical and administrative workflows, not the definition of the product.

Constraint

Clinical teams lose time and revenue to fragmented front-desk, documentation, scheduling, and EHR workflows. Automating that work safely requires more than a conversational demo: protected data, auditable actions, reliable writes, integration fallbacks, evaluation gates, and clear escalation to people.

Contribution

Built LiveKit voice reception and clinical-scribe workflows over an encrypted edge API: field-level AES-256-GCM whose ciphertext is bound to its own row so records cannot be transplanted, an append-only access log that records column names and row ids but never plaintext, idempotency enforced at the API boundary, and rollback paths. Emergency escalation runs on deterministic tripwires that fire before the model round-trip and lock out every other tool for the rest of the call. The athenahealth integration is built through a shadow-to-failsafe-to-primary ladder, staged behind a flag ahead of pilot cut-over. Python and TypeScript services deploy through Fly.io, Cloudflare, and Vercel behind nine CI workflows and a nightly agent evaluation.

Architecture

Input

Inbound patient callEncounter audioInbound SMS

System

Voice agent · LiveKitClinical scribe · SOAP pipelineWorker API · D1 + PHI encryption

Outcome

athenahealth writeSigned SOAP noteEscalation to staff

Walkthrough

  1. 01 — New encounter

    A note opens against a provider, with the patient left optional — a walk-in does not need a record to exist first.

  2. 02 — Audio staged

    Consultation audio is attached and queued for transcription. Recording in the app and uploading a file both land here.

  3. 03 — Structured note

    The transcript is drafted into separate clinical sections with an ICD-10 code on the assessment. A section the encounter never covered is left explicitly empty rather than filled in.

  4. 04 — Signed

    Signing moves the note to the signed list with its provider, encounter time, and code — and clears it out of the drafts queue.

Capabilities

Scheduling & bookingAvailability checks, booking, rescheduling, cancellation, and waitlist placement, each reconciled against the practice calendar.
Patient identity & lookupRecord lookup by identifier or name, plus registration for callers with no existing record.
Caller verificationDate-of-birth confirmation and a send-then-confirm one-time code before any record is disclosed.
Emergency escalation & handoffTiered escalation on deterministic tripwires, transfer to staff, and call termination — each writing one append-only audit row.
Patient self-serviceUpcoming appointments for a verified caller, and practice details that need no verification.
Consent capturePer-recipient SMS confirmation consent, captured and recorded at the point the caller grants it.

Stack

PythonTypeScriptLiveKitReactathenahealthFly.ioCloudflare · Vercel

Next

Want something like it built for your team?

Start a conversation→

More work

Toolshed
Agent capability and operations layer with a library of skills spanning research, commerce, prediction, browser, voice, infrastructure, and content, plus executable services, scheduled workflows, and multi-host deployment
Nvidia Jetson Toolkit
Open-source JetPack 6.2 camera-driver toolkit for the Arducam IMX708 on Jetson Orin Nano
Catalyst Edge MCP
Two query-only MCP tools that return source-linked catalyst evidence and paginated claim provenance for public-company tickers