Self-Directed Product · Career Agent · Case Study 05
Separating source facts, AI interpretation, and generated language
A bilingual EN/ZH career intelligence system combining evidence-grounded job evaluation, gap interviews, and referral intelligence while keeping generated conclusions and resume claims traceable to verified candidate evidence.
Semantic EvaluationProvenanceProvenance
90+Live Test Rounds
EN/ZHBilingual Evidence
0→1Solo Build
01 / Problem & Context
What had to become true
The challenge
A bilingual EN/ZH career intelligence system combining evidence-grounded job evaluation, gap interviews, and referral intelligence while keeping generated conclusions and resume claims traceable to verified candidate evidence.
My role
I owned the problem framing, system/product decisions, implementation direction, validation, and iteration represented in this case study. The emphasis is on the decisions that changed the system—not a feature inventory.
02 / Decisions & Tradeoffs
Architecture follows the constraint
Key decisions
- Separate source material, extracted facts, user-confirmed evidence, AI interpretation, and resume-ready wording.
- Replace brittle substring matching with semantic evidence evaluation.
- Make completion depend on persisted evidence and factuality verification, not only generation success.
- Preserve non-destructive version history and human override.
Working loop
PROBLEM → INVESTIGATE → ARCHITECT → BUILD → VALIDATE → ITERATE
The implementation was treated as a measured loop: diagnose the actual constraint, make the smallest architectural change that resolves it, then verify behavior and quality before moving forward.
03 / System Design & Build
What I built
- Canonical Evidence Library stores facts and provenance as structured data.
- Semantic evaluator judges requirement intent, evidence strength, transferability, and uncertainty across EN/ZH.
- Claim-level verification links generated wording back to supporting evidence.
- Independent ATS, recruiter, and hiring-manager review acts as a separate quality layer.
- Referral Intelligence discovers and ranks relevant people using relationship signals, referral lift, feasibility, role value, and offer viability.
- Referral Queue and outreach workflows support candidate prioritization, editable outreach, contact tracking, and follow-up state.
- FastAPI, Next.js/React, TypeScript, SQLModel/SQLite, OpenAI APIs, structured outputs, and persistent workflow state support the end-to-end system.
04 / Validation & Outcomes
Validation in practice
Validation
- 90+ logged end-to-end testing rounds against real application workflows.
- Testing exposed invisible wait states, incomplete bilingual output, evidence reconciliation failures, and decision-quality regressions that isolated tests missed.
- Architecture changed in response to production behavior rather than only prompt edits.
- Referral ranking evolved from simple contact relevance toward Offer Viability: probability, referral lift, feasibility, role value, and investment priority.
What changed
For high-stakes career decisions, provenance and referral intelligence work together: the system needs to know why a claim is supportable, who may improve access to the opportunity, and where outreach effort is most likely to improve offer viability.
05 / System Capabilities
Core capabilities
Knowledge Engineering · Semantic Evaluation · ProvenanceThis case sits inside a broader portfolio spanning AI systems and agents, full-stack products and revenue infrastructure, design engineering, and creative AI leadership.
Portfolio Map
Explore the full system of work
Each project focuses on a distinct product, engineering, or creative challenge. The current project is highlighted so the portfolio reads as one connected body of work rather than a collection of isolated case studies.
