Skip to main content
NON-01 · Nonprofit & Social Impact

Caseworker Program Copilot

Outcome​

Help the caseworker move a participant through a multi-program service plan by grounding eligibility, benefit interactions and referral options in current program rules and the participant's own consented record, so scarce caseworker time goes to the relationship rather than to rule lookup.

Portfolio attributeValue
Primary personaCaseworker
Primary aggregateParticipantServiceCase
Cosmos DB containers2
Grounding datacase notes, program rules, services, eligibility
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
ProductivityRules and participant-context discovery time15-25% reduction(baseline median evidence-search minutes - assisted median evidence-search minutes) / baseline median evidence-search minutes * 100
Quality or riskFirst-pass acceptance5-12 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: Program rules, eligibility, services, and participant context support faster preparation of reviewable case plans.

Pilot guardrail: Respect participant consent and require human approval for service plans, referrals, and eligibility decisions.

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 rules and participant-context discovery 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. Strengths and needs intake with consentCaseworker with participantparticipantConversation → ParticipantCaseHuman required
2. Program rule and eligibility groundingCaseworker program copilotParticipantCase → ProgramRuleChunkPolicy controlled
3. Benefit interaction analysisCaseworker program copilotProgramRuleChunk → BenefitInteractionFindingPolicy controlled
4. Service plan co-creationCaseworker with participantBenefitInteractionFinding → ServicePlanGoalHuman required
5. Referral with consent and capacity checkCaseworkerServicePlanGoal → ReferralRecordHuman required

Technical architecture​

Technical architecture

Cosmos DB data model​

ContainerHierarchical partition keyDocumentsSearch paths
participantServiceCases/tenantId, /caseIdParticipantCase, ServicePlanGoal, ReferralRecord, EncounterNote, BenefitInteractionFindingOperational fields only
programRuleLibrary/tenantId, /programCodeProgramRuleChunk/chunkVectorEmbedding, /chunkVector

Query contract​

QueryContainerScopePurpose
CaseloadByNextActionparticipantServiceCasescross-partition-boundedOrder the caseworker's caseload by the goals and referrals with the nearest due dates. Intentional cross-partition caseworker worklist: bounded by the tenantId prefix, the responsible caseworker and a due-date horizon.
EffectiveProgramRuleRetrievalprogramRuleLibrarycross-partition-boundedRetrieve only the program and funder rules in force for the participant's enrollment date.
OpenBenefitInteractionsparticipantServiceCasessingle-partitionSurface unresolved findings where one enrollment would harm another benefit.
ReferralOutcomeHistoryparticipantServiceCasessingle-partitionReview which partner referrals actually closed successfully to inform the next handoff.

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/nonprofit-social-impact/caseworker-program-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