Decision owner
Staffing manager with people manager
The named role remains accountable for the consequential decision.
Professional Services
Designed for Staffing manager
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.
Contract PRO-03 · primary aggregate ConsultantCapabilityProfile · mode loading
Decision brief
This brief starts with the decision, evidence, and accountable owner. The guided workflow then shows how the recommendation was produced.
The evidence and control points that shape this recommendation.
Decision owner
Staffing manager with people manager
The named role remains accountable for the consequential decision.
Governed evidence
6 record types
Structured records and cited text ground the recommendation.
Workflow
5 controlled stages
Each transition records its input, output, status, and audit context.
Human controls
2 approval gates
Approval gates prevent the copilot from making consequential decisions.
A staffing manager needs a lead data architect for a 16-week regulated-industry program starting in five weeks, capped at rate band 4 and requiring onsite presence in Chicago two days a week.
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.
AvailabilityWindow gives Staffing manager the evidence needed to begin the final governed business outcome, with the decision trail retained for review.
Step 1 of 5
| Field | Value |
|---|
| Field | Value |
|---|
The output appears here immediately. More technical evidence remains available below.
The demonstration keeps deterministic controls, AI assistance, and approval separate.
Source systems enforce identity, workflow order, policy filters, and record updates.
Retrieval and generation assemble relevant evidence into a cited recommendation or draft.
Staffing manager with people manager verifies material claims and approves the consequential action.
Run the stages in order before using the Copilot. Every stage explains what happens, why it matters, the evidence it uses, and the complete API request and response.
Automated stage
What happens: Staffing manager performs role demand intake using roleRequest and produces normalizedRoleProfile. The transition is deterministic and does not require autonomous model approval.
Why it matters: normalizedRoleProfile gives Expertise discovery assistant the evidence needed to begin Evidenced capability matching, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/role-demand-intake
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Automated stage
What happens: Expertise discovery assistant performs evidenced capability matching using normalizedRoleProfile and produces candidateShortlist. The transition is deterministic and does not require autonomous model approval.
Why it matters: candidateShortlist gives Capacity reconciler the evidence needed to begin Availability and rate reconciliation, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/evidenced-capability-matching
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Automated stage
What happens: Capacity reconciler performs availability and rate reconciliation using candidateShortlist and produces feasibleShortlist. The transition is deterministic and does not require autonomous model approval.
Why it matters: feasibleShortlist gives Staffing manager with people manager the evidence needed to begin Manager and consultant consultation, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/availability-and-rate-reconciliation
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Human approval required
What happens: Staffing manager with people manager performs manager and consultant consultation using feasibleShortlist and produces agreedCandidate. A named human approver must review the evidence before the transition completes.
Why it matters: agreedCandidate gives Staffing manager the evidence needed to begin Soft book and confirmation, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/manager-and-consultant-consultation
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Human approval required
What happens: Staffing manager performs soft book and confirmation using agreedCandidate and produces AvailabilityWindow. A named human approver must review the evidence before the transition completes.
Why it matters: AvailabilityWindow gives Staffing manager the evidence needed to begin the final governed business outcome, with the decision trail retained for review.
Loading relevant sample records.
Ready to run.
POST /api/domain/workflow/soft-book-and-confirmation
Run this API to see its formatted outcome.
| Field | Value |
|---|
| Field | Value |
|---|
Run a stage to see its explanation, evidence, full request, and full response.
Ask a question and receive an answer grounded in retrieved ConsultantCapabilityProfile evidence.
Select a starter question or enter your own.
Loaded live from /api/config, /api/domain/model, and
/api/domain/sample.
consultantCapabilityProfiles/tenantId + /consultantIdA staffing manager needs a lead data architect for a 16-week regulated-industry program starting in five weeks, capped at rate band 4 and requiring onsite presence in Chicago two days a week. The assistant ranks candidates by verified rather than self-claimed skills, surfacing a consultant whose Snowflake proficiency is evidenced by two delivered engagements and an internal accelerator they authored, over a higher-graded peer whose claim is unverified and last used three years ago. It flags that the top candidate is soft booked by a competing pursuit for weeks 3 through 6. The manager resolves the conflict with the other pursuit lead, confirms the staffing, and the soft book converts to committed hours.
| Container | Role | Hierarchical partition key | Document types |
|---|---|---|---|
consultantCapabilityProfiles |
Primary | /tenantId + /consultantId |
Consultant, SkillAssertion, ProjectExperience, AvailabilityWindow, KnowledgeContribution, StaffingRecommendation |
| Type | Container | Partition key | Identifier pattern | Embedding fields |
|---|---|---|---|---|
Consultant |
consultantCapabilityProfiles |
/tenantId + /consultantId |
consultant::{consultantId} |
None |
SkillAssertion |
consultantCapabilityProfiles |
/tenantId + /consultantId |
consultant::{consultantId}::skill::{skillCode}::{evidenceBasis} |
None |
ProjectExperience |
consultantCapabilityProfiles |
/tenantId + /consultantId |
consultant::{consultantId}::experience::{engagementRef} |
experienceVector |
AvailabilityWindow |
consultantCapabilityProfiles |
/tenantId + /consultantId |
consultant::{consultantId}::availability::{weekStartUtc} |
None |
KnowledgeContribution |
consultantCapabilityProfiles |
/tenantId + /consultantId |
consultant::{consultantId}::contribution::{assetId}::{chunkOrdinal} |
chunkVector |
StaffingRecommendation |
consultantCapabilityProfiles |
/tenantId + /consultantId |
consultant::{consultantId}::recommendation::{roleRequestId} |
None |
Find consultants with verified, recently used proficiency in the skills the role demands. Application-side partition-key fan-out 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.
consultantCapabilityProfiles
partition-key-fan-out
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.type = 'SkillAssertion' AND ARRAY_CONTAINS(@requiredSkillCodes, c.skillCode) AND c.verificationState = 'verified' AND c.proficiencyLevel >= @minimumProficiency AND c.lastUsedUtc >= @recencyCutoffUtc ORDER BY c.decayAdjustedScore DESC
Check genuine open hours across the engagement's staffing window to avoid double booking.
consultantCapabilityProfiles
single-partition
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.consultantId = @consultantId AND c.type = 'AvailabilityWindow' AND c.weekStartUtc BETWEEN @staffingStartUtc AND @staffingEndUtc AND c.openHours >= @weeklyHoursNeeded ORDER BY c.weekStartUtc ASC
Find consultants whose delivered engagement outcomes, not just skill tags, match the role context. Application-side partition-key fan-out experience search: bounded by the tenantId prefix, one client industry and a topK vector limit.
consultantCapabilityProfiles
partition-key-fan-out
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.type = 'ProjectExperience' AND c.clientIndustry = @targetIndustry ORDER BY RANK RRF(VectorDistance(c.experienceVector, @roleVector), FullTextScore(c.outcomeSummary, @queryTerms))
Surface authored assets that evidence depth beyond the skills taxonomy for niche roles. Application-side partition-key fan-out contribution search: bounded by the tenantId prefix, one topic tag and a topK vector limit.
consultantCapabilityProfiles
partition-key-fan-out
SELECT * FROM c WHERE c.tenantId = @tenantId AND c.type = 'KnowledgeContribution' AND ARRAY_CONTAINS(c.topicTags, @topicTag) ORDER BY RANK RRF(VectorDistance(c.chunkVector, @queryVector), FullTextScore(c.chunkText, @queryTerms))