Patient Navigation Assistant
Outcome
Guide a patient through the next steps of their care plan by combining appointments, referrals, benefits, and approved education content into plain-language instructions, escalating clinical questions to the care team.
| Portfolio attribute | Value |
|---|---|
| Primary persona | Patient |
| Primary aggregate | PatientJourney |
| Cosmos DB containers | 2 |
| Grounding data | appointments, care plans, benefits, education content |
| Development estimate | USD 60-220 monthly dev estimate |
| Runtime options | Python FastAPI and C# ASP.NET Core |
Productivity hypothesis
These measures reflect the workflow, evidence, decision boundary, and industry risk for this use case.
| Impact type | Measure | Conservative internal assumption | Customer measurement |
|---|---|---|---|
| Productivity | Request-to-approved-response time | 7-12% reduction | (baseline median request-to-response minutes - assisted median minutes) / baseline median minutes * 100 |
| Quality or risk | Corrected responses | 2-5% reduction | (baseline corrected or reopened response rate - assisted rate) / baseline rate * 100 |
Important: Conservative internal pilot assumptions only; not public benchmarks, commitments, or expected customer results. Validate against a comparable baseline or matched control cohort with mandatory human review.
Rationale: Appointments, care plans, benefits, and approved education content support faster patient-navigation responses.
Pilot guardrail: Do not diagnose, prescribe, or make autonomous care decisions; keep patient guidance cited.
Customer validation plan
- Baseline the current workflow with representative users and tasks.
- Run the accelerator on the same task mix with human review retained.
- Measure request-to-approved-response time and corrected responses with the documented formulas.
- Replace internal assumptions with customer-observed results before a business case.
Why Azure Cosmos DB
This AI solution needs an operational data plane, not only a vector index:
- Hybrid vector and full-text retrieval combines semantic recall with exact identifiers, codes, names, and domain language.
- Hierarchical partition keys and metadata predicates keep tenant and domain boundaries in the normal query path.
- Operational JSON, source chunks, workflow and agent state, feedback, and audit records remain together for low-latency reads and governed writes.
- Change feed reacts to source and operational updates without polling.
- Autoscale throughput, configurable consistency, and multi-region distribution support variable demand and enterprise availability.
Domain workflow

| Stage | Actor | Input → output | Approval |
|---|---|---|---|
| 1. Ask a question about the next care step | Patient | Plain-language question in the patient portal or SMS → Classified navigation intent | Policy controlled |
| 2. Resolve the active pathway and due steps | Care plan service | Patient identifier and pathway state → Ordered CarePlanStep list with due windows | Policy controlled |
| 3. Check coverage and preparation requirements | Benefits agent | Planned service and payer coverage facts → Cost and prior-authorization expectation | Policy controlled |
| 4. Explain the step in approved plain language | Navigation assistant | Care step, appointment, coverage facts, education content → Cited plain-language instruction at the patient's reading level | Policy controlled |
| 5. Escalate clinical or urgent concerns | Nurse navigator | Symptom report or clinical question → Triage decision and human response to the patient | Human required |
Technical architecture

Cosmos DB data model
| Container | Hierarchical partition key | Documents | Search paths |
|---|---|---|---|
patientJourneys | /tenantId, /patientId | PatientJourney, CarePlanStep, AppointmentSlot, BenefitCoverageFact, CareTeamEscalation | /patientMessageVectorEmbedding, /patientMessageVector |
patientEducationLibrary | /tenantId, /contentId | EducationContent | /bodyVectorEmbedding, /bodyVector |
Query contract
| Query | Container | Scope | Purpose |
|---|---|---|---|
| Next steps timeline | patientJourneys | single-partition | Assemble the patient's upcoming steps and appointments in one partition read. |
| Overdue care gap detection | patientJourneys | cross-partition-bounded | Bounded cross-partition control-plane query: find steps past their due window so the navigator can intervene. It cannot carry the second partition key because population health outreach is a panel-level view across patients, so it runs as a tenant-scoped scheduled sweep off the interactive path, bounded by steps whose due window closed inside the last 30 days, executed with MaxItemCount paging and continuation tokens. |
| Prior authorization exposure | patientJourneys | single-partition | Identify planned services that need payer approval before scheduling. |
| Open escalation queue | patientJourneys | cross-partition-bounded | Bounded cross-partition control-plane query: show the care team escalations still awaiting a human response by urgency. It cannot carry the second partition key because the nurse triage queue is shared across the panel rather than per patient, so it runs as a tenant-scoped scheduled sweep off the interactive path, bounded by escalations awaiting response inside the 24-hour response standard, executed with MaxItemCount paging and continuation tokens. |
Python and C# services route each document type to its declared container and hierarchical partition key. ETag-based writes protect mutable aggregates, while append-only records and bounded cross-partition queries preserve scale.
Azure deployment

Clone the source repository, authenticate with Azure, and run:
Set-Location accelerators/healthcare-providers/patient-navigation-assistant
az login
./Deploy.ps1 -Runtime python -Location eastus2
Change python to csharp to deploy the .NET implementation.
Explore the implementation
- Launch signed-in demo
- Implementation article
- Domain data model
- Workflow and API contract
- Python application
- C# application
- Domain container Bicep
- Platform Bicep
- Cost and configuration
- Source repository