Customer Success Intelligence
Outcome
Give the customer success manager a defensible account health picture that ties product usage against entitlement, support burden, contract commitments and stakeholder sentiment into a specific renewal or expansion play grounded in the account's own evidence.
| Portfolio attribute | Value |
|---|---|
| Primary persona | Customer success manager |
| Primary aggregate | CustomerAccountHealth |
| Cosmos DB containers | 1 |
| Grounding data | CRM, usage, support, contracts, calls |
| 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 | Account evidence discovery time | 15-25% reduction | (baseline median account-evidence search minutes - assisted median minutes) / baseline median minutes * 100 |
| Quality or risk | Evidence-complete risk and action narratives | 5-10 percentage-point improvement | assisted percentage meeting the account-evidence completeness rubric - 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: CRM, usage, support, contracts, and calls support faster preparation of grounded customer-success narratives.
Pilot guardrail: Humans approve renewal, escalation, commercial, and customer-commitment actions.
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 account evidence discovery time and evidence-complete risk and action narratives 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. Signal consolidation across systems | Account data connectors | UsageFact → consolidatedSignalSet | Policy controlled |
| 2. Health scoring with driver attribution | Customer success intelligence | consolidatedSignalSet → healthScoreWithDrivers | Policy controlled |
| 3. Commitment and objection retrieval | Retrieval orchestrator | InteractionChunk → evidenceBundle | Policy controlled |
| 4. Play recommendation | Customer success intelligence | evidenceBundle → AccountPlay | Policy controlled |
| 5. CSM and manager commitment to the play | Customer success manager and CS leader | AccountPlay → committedPlay | Human required |
Technical architecture

Cosmos DB data model
| Container | Hierarchical partition key | Documents | Search paths |
|---|---|---|---|
customerAccountHealths | /tenantId, /accountId | Account, UsageFact, SupportSignal, StakeholderRecord, InteractionChunk, AccountPlay | /chunkVectorEmbedding, /rationaleVectorEmbedding, /chunkVector, /rationaleVector |
Query contract
| Query | Container | Scope | Purpose |
|---|---|---|---|
| RenewalsAtRiskInWindow | customerAccountHealths | cross-partition-bounded | List accounts renewing inside the horizon whose health score sits in a risk band. Intentional cross-partition book-of-business view: bounded by the tenantId prefix, one CSM's assignment, a renewal horizon and the elevated churn-risk bands. |
| EntitlementUtilizationGap | customerAccountHealths | single-partition | Expose features where consumption is far under or over entitlement, driving recovery or expansion. |
| ChampionDepartureRisk | customerAccountHealths | single-partition | Surface influential champions with no meaningful engagement inside their expected cadence. |
| CommitmentEvidenceRetrieval | customerAccountHealths | single-partition | Retrieve the call or contract passage where a success criterion or commitment was made. |
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/technology-software/customer-success-intelligence
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