Skip to main content
AUT-02 · Automotive & Mobility

Engineering Requirements Copilot

Outcome​

Keep automotive systems requirements traceable and testable by linking each requirement to design decisions, verification cases, and applicable regulations, with engineering review before a baseline is frozen.

Portfolio attributeValue
Primary personaSystems engineer
Primary aggregateRequirementBaseline
Cosmos DB containers2
Grounding datarequirements, designs, tests, regulations
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
ProductivityRequirements review cycle time8-15% reduction(baseline median review minutes - assisted median review minutes) / baseline median review minutes * 100
Quality or riskFirst-pass acceptance5-10 percentage-point improvementassisted percentage accepted without material rework - baseline percentage accepted without material rework

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: Systems engineers can accelerate traceability analysis while keeping change-sensitive engineering decisions under human control.

Pilot guardrail: Maintain strict traceability across requirements, designs, tests, and regulations with formal engineering review.

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 requirements review cycle time and first-pass acceptance 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. Author or import the requirementSystems engineerRequirement text with allocation and verification method → SystemRequirement in the working baselinePolicy controlled
2. Check quality, ambiguity, and duplicationRequirement quality agentRequirement text and existing baseline → Quality findings and near-duplicate candidatesPolicy controlled
3. Link regulations and design decisionsTraceability agentRequirement, regulation clauses, decision records → Bidirectional trace links with confidencePolicy controlled
4. Assess verification coverageVerification analytics serviceRequirements and verification cases → Coverage report with unverified requirementsPolicy controlled
5. Freeze the baselineChief engineer and systems authorityCoverage report and open change requests → Frozen baseline released to development partnersHuman required

Technical architecture​

Technical architecture

Cosmos DB data model​

ContainerHierarchical partition keyDocumentsSearch paths
requirementBaselines/tenantId, /vehicleProgramIdRequirementBaseline, SystemRequirement, DesignDecisionRecord, VerificationCase/requirementVectorEmbedding, /rationaleVectorEmbedding, /requirementVector, /rationaleVector
homologationRegulationLibrary/tenantId, /marketCodeRegulatoryRequirementClause/clauseVectorEmbedding, /clauseVector

Query contract​

QueryContainerScopePurpose
Requirement trace assemblyrequirementBaselinessingle-partitionRead a requirement with its decisions and verification cases in a single program partition query.
Unverified safety requirementsrequirementBaselinessingle-partitionFind high integrity level requirements without a passing verification case.
Market homologation gaphomologationRegulationLibrarysingle-partitionKnowledge-container query against homologationRegulationLibrary (partition-aligned to /tenantId + /marketCode): list regulation clauses in force for a target market, then diff them against the programme's linked requirements; the library stores one clause document per market so the market read is partition-aligned.
Failing verification runsrequirementBaselinessingle-partitionSurface verification cases that failed since the last baseline review.

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/engineering-requirements-copilot
az login
./Deploy.ps1 -Runtime python -Location eastus2

Change python to csharp to deploy the .NET implementation.

Explore the implementation​

Return to all accelerators