Skip to main content
PRO-03 · Professional Services

Expertise Discovery Assistant

Outcome​

Let the staffing manager find the right consultant for a role by reasoning over verified skills, delivered project evidence, certifications and real availability rather than self-reported profiles, while respecting rate bands, location constraints and development goals.

Portfolio attributeValue
Primary personaStaffing manager
Primary aggregateConsultantCapabilityProfile
Cosmos DB containers1
Grounding dataskills, CVs, projects, availability, knowledge assets
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
ProductivityExpert discovery time20-30% reduction(baseline median expert-search minutes - assisted median expert-search minutes) / baseline median expert-search minutes * 100
Quality or riskAccepted staffing recommendations5-10 percentage-point improvementassisted percentage of staffing recommendations accepted - 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: Search and ranking across expertise records can materially reduce staffing discovery effort.

Pilot guardrail: Validate skills, CV, project, location, and availability freshness; managers retain staffing authority.

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 expert discovery time and accepted staffing recommendations 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. Role demand intakeStaffing managerroleRequest → normalizedRoleProfilePolicy controlled
2. Evidenced capability matchingExpertise discovery assistantnormalizedRoleProfile → candidateShortlistPolicy controlled
3. Availability and rate reconciliationCapacity reconcilercandidateShortlist → feasibleShortlistPolicy controlled
4. Manager and consultant consultationStaffing manager with people managerfeasibleShortlist → agreedCandidateHuman required
5. Soft book and confirmationStaffing manageragreedCandidate → AvailabilityWindowHuman required

Technical architecture​

Technical architecture

Cosmos DB data model​

ContainerHierarchical partition keyDocumentsSearch paths
consultantCapabilityProfiles/tenantId, /consultantIdConsultant, SkillAssertion, ProjectExperience, AvailabilityWindow, KnowledgeContribution, StaffingRecommendation/experienceVectorEmbedding, /chunkVectorEmbedding, /experienceVector, /chunkVector

Query contract​

QueryContainerScopePurpose
VerifiedSkillCandidatesconsultantCapabilityProfilescross-partition-boundedFind consultants with verified, recently used proficiency in the skills the role demands. Intentional cross-partition talent discovery: finding people the requester cannot name is the purpose, so the scan is bounded by the tenantId prefix, the required skill codes, verified assertions and a recency cutoff.
OpenCapacityInWindowconsultantCapabilityProfilessingle-partitionCheck genuine open hours across the engagement's staffing window to avoid double booking.
DeliveredExperienceSearchconsultantCapabilityProfilescross-partition-boundedFind consultants whose delivered engagement outcomes, not just skill tags, match the role context. Intentional cross-partition experience search: bounded by the tenantId prefix, one client industry and a topK vector limit.
ThoughtLeadershipDepthconsultantCapabilityProfilescross-partition-boundedSurface authored assets that evidence depth beyond the skills taxonomy for niche roles. Intentional cross-partition contribution search: bounded by the tenantId prefix, one topic tag and a topK vector limit.

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/professional-services/expertise-discovery-assistant
az login
./Deploy.ps1 -Runtime python -Location eastus2

Change python to csharp to deploy the .NET implementation.

Explore the implementation​

Return to all accelerators