Proposal and Pursuit Studio
Outcome
Compress the pursuit team's response cycle by decomposing an RFP into scored requirements, assembling compliant answers from vetted credentials, case studies and CVs, and flagging every requirement the firm cannot evidence before the bid or no-bid decision is made.
| Portfolio attribute | Value |
|---|---|
| Primary persona | Pursuit team |
| Primary aggregate | PursuitResponse |
| Cosmos DB containers | 3 |
| Grounding data | RFPs, credentials, case studies, CVs, brand content |
| 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 | Pursuit draft cycle time | 12-20% reduction | (baseline median pursuit-draft minutes - assisted median minutes) / baseline median minutes * 100 |
| Quality or risk | Rework rate | 5-12% reduction | (baseline corrected or repeated pursuit-task rate - assisted rate) / baseline rate * 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: RFPs, credentials, case studies, CVs, and brand content support faster pursuit-draft assembly.
Pilot guardrail: Prohibit unsupported claims and require approval for credentials, pricing, commitments, and proposal language.
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 pursuit draft cycle time and rework rate 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. Solicitation decomposition | Proposal and pursuit studio | solicitationDocument → RfpRequirement | Policy controlled |
| 2. Credential and personnel matching | Proposal and pursuit studio | RfpRequirement → credentialMatchSet | Policy controlled |
| 3. Gap identification and bid or no-bid framing | Pursuit lead | GapFinding → bidDecision | Human required |
| 4. Response section drafting | Proposal and pursuit studio with writers | credentialMatchSet → ResponseSection | Policy controlled |
| 5. Compliance review and submission | Proposal manager and partner | ResponseSection → submittedProposal | Human required |
Technical architecture

Cosmos DB data model
| Container | Hierarchical partition key | Documents | Search paths |
|---|---|---|---|
pursuitResponses | /tenantId, /pursuitId | Pursuit, RfpRequirement, ResponseSection, GapFinding | /requirementVectorEmbedding, /sectionVectorEmbedding, /requirementVector, /sectionVector |
firmCredentialLibrary | /tenantId, /credentialId | CredentialAsset | /assetVectorEmbedding, /assetVector |
personnelMasterProfiles | /tenantId, /personnelId | PersonnelProfile | /cvVectorEmbedding, /cvVector |
Query contract
| Query | Container | Scope | Purpose |
|---|---|---|---|
| UncoveredMandatoryRequirements | pursuitResponses | single-partition | List mandatory requirements with no drafted, compliant answer as the submission deadline approaches. |
| ConsentedCredentialRetrieval | firmCredentialLibrary | cross-partition-bounded | Match a requirement to case studies and references that are approved, consented and unexpired. Intentional cross-partition fan-out across the firmCredentialLibrary reference container, bounded by the tenant prefix, approval and client consent state and the submission deadline, returning only the top-ranked credential assets. |
| QualifiedPersonnelForRole | personnelMasterProfiles | cross-partition-bounded | Find proposal-ready personnel meeting the clearance, certification and availability the solicitation demands. Intentional cross-partition fan-out across the personnelMasterProfiles reference container, bounded by the tenant prefix, the required clearance rank, the required certification and availability, returning a shortlist of candidate profiles. |
| OpenGapsBySeverity | pursuitResponses | single-partition | Surface unresolved evidence gaps that should shape the bid or no-bid and teaming decision. |
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/professional-services/proposal-and-pursuit-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