Skip to main content
AUT-01 · Automotive & Mobility

Vehicle Owner Companion

Outcome​

Answer a vehicle owner's questions about their exact VIN configuration, warning lights, and service needs using the owner manual, build configuration, and connected telemetry, with dealer confirmation before any booking or remote command.

Portfolio attributeValue
Primary personaVehicle owner
Primary aggregateVehicleOwnership
Cosmos DB containers2
Grounding datamanuals, VIN configuration, telemetry, service history
Development estimateUSD 60-220 monthly dev estimate
Runtime optionsPython FastAPI and C# ASP.NET Core

Productivity hypothesis​

These measures reflect the workflow, evidence, decision boundary, and industry risk for this use case.

Impact typeMeasureConservative internal assumptionCustomer measurement
ProductivityResponse cycle time10-20% reduction(baseline median response minutes - assisted median response minutes) / baseline median response minutes * 100
Quality or riskEvidence discovery time15-25% reduction(baseline median evidence-search minutes - assisted median evidence-search minutes) / baseline median evidence-search minutes * 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: Vehicle-owner support can reduce manual lookup across manuals and service data without replacing professional diagnosis.

Pilot guardrail: Keep guidance within the evidence for the specific VIN, configuration, telemetry, and service history.

Customer validation plan​

  1. Baseline the current workflow with representative users and tasks.
  2. Run the accelerator on the same task mix with human review retained.
  3. Measure response cycle time and evidence discovery time with the documented formulas.
  4. 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​

Domain workflow

StageActorInput → outputApproval
1. Ask a vehicle question in the appVehicle ownerQuestion, warning light photo, or voice prompt → Intent bound to the owner's VINPolicy controlled
2. Resolve VIN configuration and entitlementsVehicle identity serviceVIN and ownership record → BuildConfiguration and entitlement scopePolicy controlled
3. Retrieve trim-valid manual and campaign contentRetrieval agentQuestion plus option codes and model year → Applicable manual sections and open campaignsPolicy controlled
4. Interpret telemetry and explain the conditionVehicle companionLatest telemetry and diagnostic codes → Plain-language explanation with urgency and cited manual textPolicy controlled
5. Confirm service booking or remote commandOwner with dealer confirmationProposed appointment or remote action → Confirmed booking or executed command with audit recordHuman required

Technical architecture​

Technical architecture

Cosmos DB data model​

ContainerHierarchical partition keyDocumentsSearch paths
vehicleOwnerships/tenantId, /vehicleVinVehicleOwnership, BuildConfiguration, TelemetrySnapshot, ServiceHistoryEntry, CampaignNoticeOperational fields only
vehicleManualLibrary/tenantId, /manualIdOwnerManualSection/bodyVectorEmbedding, /bodyVector

Query contract​

QueryContainerScopePurpose
Vehicle context loadvehicleOwnershipssingle-partitionRead configuration, latest telemetry, and service history for the VIN in one partition query.
Trim-applicable manual retrievalvehicleManualLibrarysingle-partitionKnowledge-container query against vehicleManualLibrary (partition-aligned to /tenantId + /manualId): return only manual chunks valid for this VIN's option codes and model year, using the manualId resolved from the build configuration so the read is a single partition query.
Open safety campaignsvehicleOwnershipssingle-partitionSurface unresolved recalls for the VIN with remedy availability.
Service due projectionvehicleOwnershipssingle-partitionCompare current odometer with the next service interval to propose a booking window.

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​

Azure deployment

Clone the source repository, authenticate with Azure, and run:

Set-Location accelerators/automotive-mobility/vehicle-owner-companion
az login
./Deploy.ps1 -Runtime python -Location eastus2

Change python to csharp to deploy the .NET implementation.

Explore the implementation​

Return to all accelerators