Grant Development Studio
Outcome
Let the fundraising team move from a grant call to a submission-ready proposal faster by matching funder priorities against the organization's evidence base, reusing approved language and outcome data, and exposing every eligibility or budget condition that would disqualify the application.
| Portfolio attribute | Value |
|---|---|
| Primary persona | Fundraising team |
| Primary aggregate | GrantOpportunity |
| Cosmos DB containers | 2 |
| Grounding data | grant calls, evidence, budgets, outcomes, proposals |
| 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 | Proposal readiness time | 12-22% reduction | (baseline median proposal-readiness minutes - assisted median minutes) / baseline median minutes * 100 |
| Quality or risk | Evidence discovery time | 20-35% 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: Grant requirements, organizational evidence, budgets, and prior materials can be assembled faster into compliant drafts.
Pilot guardrail: Use verified evidence and require named reviewers for proposal, budget, and organizational commitments.
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 proposal readiness time and evidence discovery time 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. Opportunity intake and requirement extraction | Grant development studio | notionOfFundingOpportunity → FunderRequirementChunk | Policy controlled |
| 2. Eligibility and fit screening | Grant development studio | FunderRequirementChunk → EligibilityFinding | Policy controlled |
| 3. Go or no-go decision | Development director | EligibilityFinding → goNoGoDecision | Human required |
| 4. Narrative and budget drafting | Grant development studio with grant writer | EvidenceAsset → NarrativeSection | Policy controlled |
| 5. Finance and executive approval before submission | Finance director and executive director | BudgetLine → submittedProposal | Human required |
Technical architecture

Cosmos DB data model
| Container | Hierarchical partition key | Documents | Search paths |
|---|---|---|---|
grantOpportunities | /tenantId, /opportunityId | GrantOpportunity, FunderRequirementChunk, NarrativeSection, BudgetLine, EligibilityFinding | /opportunityVectorEmbedding, /chunkVectorEmbedding, /sectionVectorEmbedding, /opportunityVector, /chunkVector, /sectionVector |
outcomeEvidenceLibrary | /tenantId, /programCode | EvidenceAsset | /assetVectorEmbedding, /assetVector |
Query contract
| Query | Container | Scope | Purpose |
|---|---|---|---|
| EliminatingRequirementsUnmet | grantOpportunities | single-partition | Surface funder conditions that would disqualify the application if unresolved. |
| VerifiedEvidenceRetrieval | outcomeEvidenceLibrary | cross-partition-bounded | Match a narrative requirement to outcome evidence that is verified and inside its measurement currency window. |
| HighWeightScoringCriteria | grantOpportunities | single-partition | Prioritize drafting effort on the funder's most heavily scored criteria. |
| BudgetLinesWithRestrictions | grantOpportunities | single-partition | List budget lines carrying unresolved allowability or indirect-rate findings before finance approval. |
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/nonprofit-social-impact/grant-development-studio
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