Store Associate Knowledge Copilot
Outcome
Answer a store associate's floor question in seconds from current policy, planogram, inventory, and service bulletins, so the customer is served without leaving the aisle or escalating to a manager.
| Portfolio attribute | Value |
|---|---|
| Primary persona | Store associate |
| Primary aggregate | AssociateAssist |
| Cosmos DB containers | 2 |
| Grounding data | manuals, policies, inventory, service bulletins |
| Development estimate | USD 60-220 monthly dev estimate |
| Runtime options | Python FastAPI and C# ASP.NET Core |
Productivity hypothesis
These measures reflect the workflow, evidence, decision boundary, and industry risk for this use case.
| Impact type | Measure | Conservative internal assumption | Customer measurement |
|---|---|---|---|
| Productivity | Associate answer time | 20-35% reduction | (baseline median answer-preparation minutes - assisted median minutes) / baseline median minutes * 100 |
| Quality or risk | Accepted answers | 5-10 percentage-point improvement | assisted percentage of answers accepted as correct and useful - baseline percentage |
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: Manuals, policies, inventory, and service bulletins support faster point-of-service answers.
Pilot guardrail: Require staff authority for returns, exceptions, safety matters, and inventory or account changes.
Customer validation plan
- Baseline the current workflow with representative users and tasks.
- Run the accelerator on the same task mix with human review retained.
- Measure associate answer time and accepted answers with the documented formulas.
- 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

| Stage | Actor | Input → output | Approval |
|---|---|---|---|
| 1. Ask a floor question on the handheld | Store associate | Spoken or typed question with scanned SKU → Normalized question bound to store context | Policy controlled |
| 2. Retrieve policy, bulletins, and stock | Retrieval agent | Question, storeId, and region scope → Ranked evidence with effective-date filter | Policy controlled |
| 3. Resolve bulletin override against standing policy | Policy reasoning agent | Conflicting policy and bulletin evidence → Single authoritative instruction with precedence note | Policy controlled |
| 4. Deliver a step-by-step floor answer | Associate copilot | Authoritative instruction and stock location → Cited answer with aisle and backroom location | Policy controlled |
| 5. Escalate exception to the manager on duty | Manager on duty | Proposed exception such as an out-of-policy return → Approved or denied exception with reason | Human required |
Technical architecture

Cosmos DB data model
| Container | Hierarchical partition key | Documents | Search paths |
|---|---|---|---|
associateAssists | /tenantId, /storeId | AssociateAssist, StoreInventorySnapshot, TaskHandoff | Operational fields only |
storeOperationsKnowledge | /tenantId, /documentId | PolicyArticle, ServiceBulletin | /bodyVectorEmbedding, /instructionVectorEmbedding, /bodyVector, /instructionVector |
Query contract
| Query | Container | Scope | Purpose |
|---|---|---|---|
| Active bulletin check for a SKU | storeOperationsKnowledge | cross-partition-bounded | Knowledge-container query against storeOperationsKnowledge (bounded fan-out across the /tenantId + /documentId partitions named by the shortlist): confirm whether an unexpired recall or correction bulletin overrides standing policy for the scanned SKU, over the bounded bulletin id set returned by the SKU-to-bulletin index. |
| In-store stock and location | associateAssists | single-partition | Tell the associate where the item sits on the floor or in the backroom. |
| Region-scoped policy retrieval | storeOperationsKnowledge | cross-partition-bounded | Knowledge-container query against storeOperationsKnowledge (bounded fan-out across the /tenantId + /documentId partitions named by the shortlist): pull the in-force chunks of the policy documents shortlisted by vector search, narrowed to the store's region so a Texas associate never sees a California-only rule, as a bounded fan-out across the at most ten policy document ids returned by vector shortlisting. |
| Open store task board | associateAssists | single-partition | Show tasks created from assists that are still open for this store. |
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

Clone the source repository, authenticate with Azure, and run:
Set-Location accelerators/retail-e-commerce/store-associate-knowledge-copilot
az login
./Deploy.ps1 -Runtime python -Location eastus2
Change python to csharp to deploy the .NET implementation.
Explore the implementation
- Launch signed-in demo
- Implementation article
- Domain data model
- Workflow and API contract
- Python application
- C# application
- Domain container Bicep
- Platform Bicep
- Cost and configuration
- Source repository