Multi-site provider groups
Consistent front-door help across locations without adding front-desk headcount.
AI Agent · Virtual Health Assistant
Virtual Health Assistant
A patient-facing conversational agent that answers routine questions, handles scheduling, refills, and directions, and pulls personalized context from the chart — with hard guardrails that escalate anything clinical to a human.
Human-in-the-loopHIPAA-ReadyAudit LoggedFHIR R4
Trusted by global innovators
Most patient questions never needed a clinician
Much inbound patient contact is logistics: appointment times, refills, parking, billing, is my result back yet. Each one still consumes front-desk and nurse time, and after hours becomes a morning callback backlog. The virtual health assistant handles that layer conversationally, around the clock: it answers routine and administrative questions, pulls personalized context from the EHR via FHIR, books and reschedules appointments, and starts refill requests — while a strict guardrail layer routes anything clinical, urgent, or emotional to the right human. It is deliberately not a diagnostic tool.
Conversation with a safety net
Reference architecture for how this agent connects to your EHR and data systems.
Key Capabilities
What the assistant handles for patients — and where it stops and hands off.
Conversational Q&A
Natural-language answers to appointment, billing, medication, prep, and location questions, grounded in your approved content, not open-web guesses.
Personalized context via FHIR
With patient authentication, it reads appointment, medication, and result data through FHIR R4 to answer 'my' questions accurately.
Scheduling & refills
Books, reschedules, and cancels appointments and initiates refill requests, handing structured actions to the EHR and scheduling system.
Clinical guardrails & hand-off
An intent classifier detects symptoms, advice requests, and distress, refuses to diagnose, and routes them to a nurse or emergency services — passing the full conversation so the patient never repeats themselves.
Who runs it
Deployment scenarios
Where a patient-facing assistant deflects load and improves access.
Digital health startups
A compliant conversational layer to scale patient support without scaling the team linearly.
Specialty clinics
Prep instructions, scheduling, and FAQs tailored to each specialty's patient journey.
After-hours coverage
Answer routine questions overnight and queue clinical items for the morning team.
What conversational self-service changes
Directional impact, validated per deployment rather than guaranteed.
24/7
Availability for routine patient questions
Every message
Classified before it is answered
0
Diagnoses given — clinical questions always escalate
Compliance-First Healthcare App Development Services Backed by Global Standards
15-Minute Scoping Call01
HIPAA
Health Insurance Portability and Accountability Act
Protect PHI with privacy-first architecture, encrypted storage and transmission, strict access controls, and traceable audit logs.
02
GDPR
General Data Protection Regulation
Implement lawful consent flows, data minimization, retention controls, and secure processing for sensitive health data.
03
FHIR
Fast Healthcare Interoperability Resources
Enable standardized health data exchange across apps, care teams, and systems through robust FHIR-ready APIs.
04
HL7
Health Level Seven International
Support enterprise-grade interoperability with HL7-based integrations for records, events, and clinical messaging workflows.
05
HITRUST
Health Information Trust Alliance
Align security programs to healthcare-specific control and risk management practices trusted by providers and ecosystem partners.
06
HITECH
Health Information Technology for Economic and Clinical Health Act
Design with breach notification readiness, digital record safeguards, and operational controls that support regulated care programs.
07
SaMD
FDA Software as a Medical Device
Plan software quality, traceability, and documentation pathways for products that may require SaMD review and submission.
08
MDR (EU)
Medical Device Regulation (European Union)
Prepare EU market-ready processes for risk classification, evidence tracking, and lifecycle governance under MDR expectations.
09
SAMHSA
Substance Abuse and Mental Health Services Administration
Apply confidentiality controls and consent-aware sharing models for behavioral and mental health data experiences.
Standards we build against
Compliance & interoperability standards
HIPAASOC 2FHIRHL7OAuth2WCAG
How It Works
From patient message to resolved or escalated
Understand the request, check it against guardrails, act on the safe ones, and hand the rest to a human with context.
1.
1 · Understand (capture)
The patient messages via app, web, or SMS; the agent authenticates them and interprets intent in BAA scope, pulling FHIR context only when authorized.
PHI in BAA scope
2.
2 · Classify & guard (model + guardrails)
Every message is classified administrative, clinical, or urgent; clinical-advice and distress signals trip a hard guardrail, so the agent never answers outside its safe scope.
Scope-limited, explainable
3.
3 · Act or escalate (human-in-the-loop)
Safe requests are resolved — an answer, a booking, a refill; anything clinical or urgent is handed to triage or staff with the full conversation attached.
Human-in-the-loop
4.
4 · System update
Bookings, refill requests, and interaction summaries write back to the EHR and scheduling systems, and the exchange is captured in an audit log.
Audit logged
Related proof
Read Case StudyLera Health: compliant women's health platform
Related delivery proof from our compliant, AI-assisted healthcare work — not this exact agent.
Compliance & Guardrails
A patient-facing agent you can defend
In healthcare, the guardrails matter as much as the capability.
PHI handling
Authenticated access, encryption in transit and at rest, and BAA-covered processing; personalized data is read via scoped FHIR access, never over-shared.
Human-in-the-loop
The assistant handles logistics; clinical questions and distress always reach a human. It never gives medical advice or a diagnosis.
Explainability
Answers are grounded in your approved knowledge base with sources, so responses are traceable and content stays under your control.
Audit logging
Every conversation, action, and escalation is logged with timestamps for quality review, safety monitoring, and compliance.
Frequently Asked Questions
Yes. Patient conversations and personalized data are processed in BAA-covered infrastructure with authentication, encryption in transit and at rest, scoped FHIR access, and full audit logging. We sign a BAA before any PHI.
Ready to give patients 24/7 help — safely?
Tell us your workflow and systems, and we'll return an architecture review and a phased rollout plan.
contact@agnotic.com
Partnerships
contact@agnotic.com