Claims Adjuster Copilot
Outcome
Help a claims adjuster reach a defensible coverage and reserve decision faster by unifying the first notice of loss, policy terms, damage evidence, and repair estimates with mandatory human sign-off on payments.
| Portfolio attribute | Value |
|---|---|
| Primary persona | Claims adjuster |
| Primary aggregate | ClaimFile |
| Cosmos DB containers | 1 |
| Grounding data | claims, policies, images, estimates, correspondence |
| 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 | Claim review cycle time | 8-14% reduction | (baseline median claim-review minutes - assisted median minutes) / baseline median minutes * 100 |
| Quality or risk | Reopened or corrected claims | 3-6% reduction | (baseline reopened or corrected claim 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: Claims, policies, images, estimates, and correspondence support faster evidence synthesis and recommendation preparation.
Pilot guardrail: Adjusters retain coverage, liability, reserve, and settlement authority with complete evidence lineage.
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 claim review cycle time and reopened or corrected claims 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. Intake first notice of loss | Insured or call agent | Loss report with date, cause, and parties → ClaimFile with structured loss facts | Policy controlled |
| 2. Bind policy terms in force at loss date | Policy service | Policy number and loss date → PolicySnapshot with limits and exclusions | Policy controlled |
| 3. Analyze damage evidence and estimates | Evidence analysis agent | Photos, inspection reports, shop estimates → Damage observations and estimate variance | Policy controlled |
| 4. Draft the coverage position and reserve | Coverage reasoning agent | Loss facts, policy clauses, evidence → CoverageAssessment with cited clauses | Policy controlled |
| 5. Approve payment or denial | Claims adjuster and supervisor | Coverage assessment and settlement figure → Authorized payment or issued denial letter | Human required |
Technical architecture

Cosmos DB data model
| Container | Hierarchical partition key | Documents | Search paths |
|---|---|---|---|
claimFiles | /tenantId, /claimId | ClaimFile, PolicySnapshot, DamageEvidence, RepairEstimate, CorrespondenceThread, CoverageAssessment | /endorsementTextVectorEmbedding, /observationVectorEmbedding, /bodyVectorEmbedding, /assessmentVectorEmbedding, /endorsementTextVector, /observationVector, /bodyVector, /assessmentVector |
Query contract
| Query | Container | Scope | Purpose |
|---|---|---|---|
| Claim file assembly | claimFiles | single-partition | Load the complete claim context in one partition read for the adjuster desktop. |
| Estimate variance review | claimFiles | single-partition | Highlight estimates that exceed the guideline schedule by more than the review tolerance. |
| Unanswered insured correspondence | claimFiles | cross-partition-bounded | Bounded cross-partition control-plane query: find inbound messages awaiting an adjuster response inside the service-level window. It cannot carry the second partition key because the service-level breach report covers every open claim in the unit, so it runs as a tenant-scoped scheduled sweep off the interactive path, bounded by inbound messages received inside the last seven days with no respondedUtc, executed with MaxItemCount paging and continuation tokens. |
| Aging severe claims | claimFiles | cross-partition-bounded | Bounded cross-partition control-plane query: surface open high-reserve claims that have not moved recently for supervisor review. It cannot carry the second partition key because supervisory oversight is by definition a portfolio view across claims, so it runs as a tenant-scoped scheduled sweep off the interactive path, bounded by open claims above the severity reserve threshold with no update for ten days, 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/insurance/claims-adjuster-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