Skip to main content
AER-03 · Aerospace & Defense

Engineering Change Impact Copilot

Outcome​

Let the configuration manager see the true blast radius of a proposed engineering change: which requirements, parts, effectivity ranges, qualification tests and publications it disturbs, so the change board decides with the affected artifacts enumerated rather than estimated.

Portfolio attributeValue
Primary personaConfiguration manager
Primary aggregateEngineeringChangeRequest
Cosmos DB containers2
Grounding datarequirements, BOM, tests, changes, manuals
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
ProductivityTask cycle time10-20% reduction(baseline median task minutes - assisted median task minutes) / baseline median task 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: Configuration managers can trace requirements, bills of material, tests, changes, and manuals more quickly while retaining formal approval.

Pilot guardrail: Surface missing or conflicting change-control evidence rather than resolving it through inference.

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 task 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. Change intake and classificationConfiguration managerChangeRequest → classifiedChangePolicy controlled
2. Requirement and BOM traceability expansionTraceability resolverclassifiedChange → affectedArtifactSetPolicy controlled
3. Requalification determinationEngineering change impact copilot with test engineeringQualificationTestLink → requalificationVerdictSetPolicy controlled
4. Publication impact scopingEngineering change impact copilotPublicationImpactChunk → publicationUpdateScopePolicy controlled
5. Change control board dispositionChange control boardImpactAssessment → boardDispositionHuman required

Technical architecture​

Technical architecture

Cosmos DB data model​

ContainerHierarchical partition keyDocumentsSearch paths
engineeringChangeRequests/tenantId, /changeRequestIdChangeRequest, RequirementLink, BomImpact, QualificationTestLink, ImpactAssessment/changeVectorEmbedding, /requirementVectorEmbedding, /changeVector, /requirementVector
technicalPublicationLibrary/tenantId, /ataChapterPublicationImpactChunk/chunkVectorEmbedding, /chunkVector

Query contract​

QueryContainerScopePurpose
InvalidatedVerificationsengineeringChangeRequestssingle-partitionList requirements whose verification the change invalidates and that therefore need reverification.
FieldedUnitExposureengineeringChangeRequestssingle-partitionQuantify how many fielded units and how much existing stock the effectivity change disturbs.
RequalificationCostDriversengineeringChangeRequestssingle-partitionRank qualification tests requiring repeat or delta qualification by cost and duration.
AffectedPublicationSectionstechnicalPublicationLibrarycross-partition-boundedFind publication sections whose effectivity or content the change invalidates so updates are scoped before release.

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/aerospace-defense/engineering-change-impact-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