Skip to main content
ENE-01 · Energy & Utilities

Field Service Grid Copilot

Outcome​

Equip a field technician at the pole or substation with the right asset record, switching procedure, and outage context to complete the work order safely, with a control-room switching authorization before any energized operation.

Portfolio attributeValue
Primary personaField technician
Primary aggregateFieldWorkOrder
Cosmos DB containers2
Grounding dataasset registry, GIS, manuals, outages, work orders
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
ProductivityField task cycle time8-15% reduction(baseline median field-task minutes - assisted median minutes) / baseline median minutes * 100
Quality or riskReopened work orders3-6% reduction(baseline reopened work-order 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: Asset registry, GIS, manuals, outages, and work orders support faster field preparation with tight safety controls.

Pilot guardrail: Safety procedures, asset-system truth, and technician verification take precedence over generated guidance.

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 field task cycle time and reopened work orders 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. Accept the work order in the fieldField technicianDispatched job with asset and location → FieldWorkOrder accepted with crew identityPolicy controlled
2. Load asset, connectivity, and outage contextNetwork context serviceAsset identifiers and feeder topology → Asset record with upstream devices and active outagesPolicy controlled
3. Retrieve the applicable procedureRetrieval agentJob type, asset class, and voltage class → Ordered switching steps with safety precautionsPolicy controlled
4. Guide the field task with citationsField copilotProcedure steps and asset specifics → Step-by-step guidance with manual citationsPolicy controlled
5. Authorize switching and energizationControl-room operatorRequested switching operation and grounding state → Issued switching authorization and permit recordHuman required

Technical architecture​

Technical architecture

Cosmos DB data model​

ContainerHierarchical partition keyDocumentsSearch paths
fieldWorkOrders/tenantId, /serviceTerritoryIdFieldWorkOrder, GridAssetRecord, OutageIncidentOperational fields only
gridProcedureLibrary/tenantId, /documentIdSwitchingProcedure, TechnicalManualChunk/stepVectorEmbedding, /bodyVectorEmbedding, /stepVector, /bodyVector

Query contract​

QueryContainerScopePurpose
Job context assemblyfieldWorkOrderssingle-partitionRead work order, target assets, and active outages for the territory in one partition query.
Voltage-correct procedure retrievalgridProcedureLibrarysingle-partitionKnowledge-container query against gridProcedureLibrary (partition-aligned to /tenantId + /documentId): return only the switching steps valid for the asset class and voltage the crew is working on, read as a single partition query on the procedure document.
Active outage impactfieldWorkOrderssingle-partitionShow open outages on the feeder the crew is about to work on.
Overdue asset inspectionsfieldWorkOrderssingle-partitionIdentify assets in the territory past their inspection interval for opportunistic work.

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/energy-utilities/field-service-grid-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