Skip to main content
CON-03 · Consumer Packaged Goods

Sales Execution Copilot

Outcome​

Prepare the field sales representative for each retail account call with a grounded pre-call plan: what the account bought and stopped buying, which planogram gaps and promotion compliance issues exist, and what the trade terms permit them to offer, all cited to the account record and the trade playbook.

Portfolio attributeValue
Primary personaField sales representative
Primary aggregateRetailAccountCallPlan
Cosmos DB containers2
Grounding dataretailer history, assortment, promotions, playbooks
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
ProductivityAccount preparation time10-20% reduction(baseline median preparation minutes - assisted median preparation minutes) / baseline median preparation 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: Field-sales teams can prepare accounts faster from retailer history, assortment, promotions, and execution guidance.

Pilot guardrail: Keep proposed actions within approved retailer policy, trade terms, promotions, and playbooks.

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 account preparation 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. Account performance analysisSales execution copilotOrderHistoryFact → performanceGapSetPolicy controlled
2. Distribution void and compliance detectionAssortment analyzerAssortmentPosition → voidAndComplianceFindingsPolicy controlled
3. Trade terms groundingRetrieval orchestratorvoidAndComplianceFindings → TradePlaybookChunkPolicy controlled
4. Pre-call plan generationSales execution copilotTradePlaybookChunk → CallPlanPolicy controlled
5. Representative call execution and commitment captureField sales representativeCallPlan → CallOutcomeHuman required

Technical architecture​

Technical architecture

Cosmos DB data model​

ContainerHierarchical partition keyDocumentsSearch paths
retailAccountCallPlans/tenantId, /accountIdRetailAccount, AssortmentPosition, OrderHistoryFact, CallPlan, CallOutcome/planVectorEmbedding, /planVector
tradePlaybookLibrary/tenantId, /termsTierTradePlaybookChunk/chunkVectorEmbedding, /chunkVector

Query contract​

QueryContainerScopePurpose
DistributionVoidsForAccountretailAccountCallPlanssingle-partitionList authorized SKUs that are not on shelf so the representative can open the call with a specific gap.
DecliningSkuTrendretailAccountCallPlanssingle-partitionFind SKUs whose ordered cases fell materially across the trailing periods for this account.
PermittedOfferRetrievaltradePlaybookLibrarysingle-partitionRetrieve only the trade terms and promotion rules that apply to this account's terms tier and the topic at hand.
OpenFollowUpsByTerritoryretailAccountCallPlanscross-partition-boundedShow commitments and follow-ups owed across the representative's route. Intentional cross-partition rep worklist: bounded by the tenantId prefix, one representative and a due-date horizon.

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/consumer-packaged-goods/sales-execution-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