Skip to main content
Category: Clinical Operations  ·  Voice agent: Intake (agent type.INTAKE)  ·  Voice ID: Medera voice
The Patient Intake Agent runs the first contact a patient has with the practice. It is voice-first, orchestrated via Medera Voice with Medera STT nova-2-medical transcription and an Medera voice, and follows a documented 7-state conversation state machine.

Conversation state machine

medera/intake-state.svg7-state conversationIntake conversation state machineGREETINGIDENTITY_VERIFICATIONGATHERING_INFOMENTAL_HEALTH_SCREENINGAPPOINTMENT_SCHEDULINGSUMMARY_CONFIRMATIONCLOSINGCOMPLETEDESCALATED (any state → terminal)

Task types (TaskType enum)

IDENTITY_VERIFICATION, INSURANCE_VERIFICATION, APPOINTMENT_SCHEDULING, REFERRAL_PROCESSING, PRE_AUTHORIZATION, PRESCRIPTION_REFILL, BILLING_CALCULATION, SYMPTOM_DOCUMENTATION, CHIEF_COMPLAINT, URGENT_CARE_TRIAGE.

The Intake Agent’s 4 function calls

Workflow modules

System prompt structure

INTAKE_SYSTEM_PROMPT_TEMPLATE is composed of 13 sections, including: 1. Patient context (name, DOB, provider, conditions, meds, allergies) 2. Call scenario (type + scenario details) 3. Conversation guidelines (tone, opening, AI / recording disclosure — mandatory, identity verification, info gathering, sensitive topics, urgent situations, closing)

Configuration

Composable experts

Compliance guarantees

  • Verbal recording + AI disclosure is mandatory before any clinical questions. - Identity verification requires 2-of-3 confirmation. - Crisis-language detection bypasses agent gating and triggers escalate_urgent immediately. - Every claim in the summary is anchored to a quoted span in the transcript.

Quickstart

Deploy the Intake Agent in 15 minutes.

Medera Voice Webhooks

Webhook schema.

Intake API

REST surface.

Care Orchestrator

Multi-agent runtime.