Case file 01 / Own Product
OptiTalent
Evidence-first recruiting workflows
A multi-tenant recruitment product that turns candidate search, evidence review, shortlist decisions, controlled sharing, and recruiter feedback into one coherent workflow.
- CLASSIFICATION
- Own Product
- PUBLIC STATUS
- REVIEWED
- CASE
- 01 / 06
The problem
Recruiting teams need to move quickly without turning matching into an opaque score or losing the evidence behind a decision.
My role
I defined the product boundaries, tenant model, evidence contracts, recruiter workflow, review gates, and release acceptance. AI agents produced most implementation code under those constraints.
Capabilities
- 01
Tenant-scoped candidate retrieval
- 02
Candidate evidence and explainable match signals
- 03
Draft and approved shortlist states
- 04
Controlled sharing and feedback
- 05
CLI, MCP, desktop, and web access paths
Product decisions
- 01
Prefer evidence-first retrieval and explicit unknowns over a single opaque LLM judgment.
- 02
Keep the policy and lifecycle authority behind stable contracts while interfaces render approved state.
- 03
Treat agent and human entry points as adapters over the same capabilities.
Evidence
- 01
Public product surface at app.optitalent.cc.
- 02
Implemented candidate search, candidate evidence, shortlist, and sharing contracts.
- 03
Tenant-scoped retrieval and explicit review states are present in the product runtime.
Honest limits
- !
Private candidate, customer, and tenant data is not shown.
- !
Internal benchmarks are not published without a reproducible public profile.
The design principle
Recruiting software often compresses a complex judgment into a rank. OptiTalent keeps the underlying evidence visible: what matched, what remains unknown, which records support the conclusion, and where a recruiter still needs to decide.
Capability shape
The product is organized around a recruiting project rather than a loose collection of AI features. A team can describe a role, inspect the structured project, search its private talent graph, build a draft shortlist, approve candidates, share a controlled view, and collect feedback.
The same capability boundaries support human and agent entry points. Search, candidate evidence, shortlist construction, and sharing are callable contracts, not logic hidden inside one page.
What I learned
The useful unit of AI product design is not a prompt. It is a capability with inputs, state, permissions, evidence, failure behavior, and a place for human judgment.