# Case studies

Deep dives into how the work actually happened.

- [Making an Enterprise Design System Reliable for AI Agents](https://mattwhalley.com/case-studies/enterprise-design-system) — 1.6M+ Figma instances, no reliable way to know what mapped to real code. I built the infrastructure to measure, classify, and distribute that truth.

- [Shipping an Agentic Provider Search Into Production](https://mattwhalley.com/case-studies/ai-search) — Natural-language search over a regulated healthcare directory — without exposing a single record. The agent writes the query; SQL produces the answer.

- [Building an AI Code Reviewer Engineers Would Actually Trust](https://mattwhalley.com/case-studies/ai-code-review) — An automated code reviewer has one currency: whether engineers believe it. A parallel multi-agent review system built to spend every design decision on credibility, not coverage.