Skip to main content
NON-03 · Nonprofit & Social Impact

Impact Reporting Copilot

Outcome​

Let the program director produce an impact report that ties indicator results to the program's logic model, reconciles outcome data with financial spend, and pairs quantitative results with consented participant stories, without overstating attribution.

Portfolio attributeValue
Primary personaProgram director
Primary aggregateProgramImpactPeriod
Cosmos DB containers2
Grounding dataoutcomes, surveys, financials, stories, indicators
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
ProductivityReporting rework6-14% reduction(baseline corrected or repeated reporting-task rate - assisted rate) / baseline rate * 100
Quality or riskEvidence discovery time15-30% reduction(baseline median evidence-search minutes - assisted median evidence-search minutes) / baseline median evidence-search minutes * 100
Business outcomeApproved funder-report turnaround5-10% reduction(baseline median report days - assisted median report days) / baseline median report days * 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: Program, survey, partner, and finance evidence can reduce report corrections and modestly shorten approval turnaround.

Pilot guardrail: Preserve measurement caveats, attribution limits, participant-story consent, and source evidence.

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 reporting rework 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. Indicator data consolidation and quality ratingData connectors with data stewardIndicatorResult → ratedIndicatorSetPolicy controlled
2. Financial reconciliation to general ledgerFinance analystFinancialAllocation → reconciledSpendHuman required
3. Story selection under consent scopeImpact reporting copilotParticipantStory → eligibleStorySetPolicy controlled
4. Report synthesis with attribution caveatsImpact reporting copilotEvaluationChunk → ImpactReportDraftPolicy controlled
5. Program director and funder-variant approvalProgram directorImpactReportDraft → approvedImpactReportHuman required

Technical architecture​

Technical architecture

Cosmos DB data model​

ContainerHierarchical partition keyDocumentsSearch paths
programImpactPeriods/tenantId, /programIdProgram, IndicatorResult, FinancialAllocation, ParticipantStory, ImpactReportDraft/storyVectorEmbedding, /storyVector
evaluationLiteratureArchive/tenantId, /evalDocIdEvaluationChunk/chunkVectorEmbedding, /chunkVector

Query contract​

QueryContainerScopePurpose
IndicatorPerformanceVersusTargetprogramImpactPeriodssingle-partitionCompare actuals to targets across the logic model for the reporting period.
RestrictedFundSpendReconciliationprogramImpactPeriodssingle-partitionReport spend by funding source with restriction class for funder-specific variants.
ConsentEligibleStoriesprogramImpactPeriodssingle-partitionSelect only stories whose consent scope permits the intended publication channel.
AttributionCaveatRetrievalevaluationLiteratureArchivecross-partition-boundedRetrieve evaluation methodology text that bounds what the program may claim to have caused. Intentional cross-partition fan-out across the evaluationLiteratureArchive reference container, bounded by the tenant prefix, the comparison-group flag and a publication lookback window, returning only the top-ranked evaluation chunks.

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/impact-reporting-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