Clinical Documentation Copilot
Outcome
Reduce clinician documentation burden by turning an ambient or dictated encounter into a structured, coded clinical note grounded in the patient chart, with clinician attestation required before anything enters the medical record.
| Portfolio attribute | Value |
|---|---|
| Primary persona | Clinician |
| Primary aggregate | EncounterDocumentation |
| Cosmos DB containers | 1 |
| Grounding data | encounters, EHR context, templates, terminology |
| 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 | Encounter-to-note approval time | 7-12% reduction | (baseline median encounter-to-note minutes - assisted median minutes) / baseline median minutes * 100 |
| Quality or risk | Corrected note sections | 2-5% reduction | (baseline corrected note-section 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: Encounter context, templates, and terminology can modestly reduce documentation preparation in a safety-sensitive workflow.
Pilot guardrail: Clinicians remain responsible for clinical accuracy, documentation approval, and all care decisions.
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 encounter-to-note approval time and corrected note sections 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. Capture the encounter conversation | Clinician | Ambient audio or dictation with patient consent → Diarized TranscriptSegment stream | Policy controlled |
| 2. Assemble relevant chart context | Chart context service | Patient identifier and encounter reason → ChartContextSnapshot of problems, meds, allergies, results | Policy controlled |
| 3. Draft the structured clinical note | Documentation agent | Transcript segments and chart snapshot → NoteDraft with per-statement evidence links | Policy controlled |
| 4. Suggest diagnosis and procedure coding | Coding agent | Note assessment and plan sections → CodingSuggestion set with specificity warnings | Policy controlled |
| 5. Attest and file to the medical record | Clinician | Edited note and accepted codes → Signed note written to the EHR encounter | Human required |
Technical architecture

Cosmos DB data model
| Container | Hierarchical partition key | Documents | Search paths |
|---|---|---|---|
encounterDocumentations | /tenantId, /encounterId | EncounterDocumentation, TranscriptSegment, ChartContextSnapshot, NoteDraft, CodingSuggestion | /segmentVectorEmbedding, /noteVectorEmbedding, /segmentVector, /noteVector |
Query contract
| Query | Container | Scope | Purpose |
|---|---|---|---|
| Encounter documentation assembly | encounterDocumentations | single-partition | Load transcript, chart snapshot, and current draft for the note editor in one partition read. |
| Unattested note backlog | encounterDocumentations | cross-partition-bounded | Bounded cross-partition control-plane query: show the clinician every draft still awaiting signature within the compliance window. It cannot carry the second partition key because a clinician's backlog spans all of the encounters they saw, so it runs as a tenant-scoped scheduled sweep off the interactive path, bounded by one clinicianId and the 24-hour attestation compliance window, executed with MaxItemCount paging and continuation tokens. |
| Unsupported statement review | encounterDocumentations | single-partition | Highlight generated sentences that lack a transcript or chart evidence link. |
| Coding specificity queue | encounterDocumentations | cross-partition-bounded | Bounded cross-partition control-plane query: list suggested codes flagged for insufficient specificity before claim submission. It cannot carry the second partition key because the coding integrity queue is owned by the health information management team across encounters, so it runs as a tenant-scoped scheduled sweep off the interactive path, bounded by proposed codes on encounters inside the 72-hour pre-bill window, 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/clinical-documentation-copilot
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