Testing and Evaluating Copilot Agents
Schema-first evaluation, test sets, release gates, and human review for Copilot-style agents.
Read articleCase Studies
A curated path through applied AI, evaluation, data product, product systems, and focus-tool work for hiring managers, collaborators, and applied AI/product audiences.
How to read these
How to read these
Each case-study path highlights a different kind of judgment: production AI reliability, data product design, workflow measurement, product value, or focused user experience.
What they show
What they show
The common thread is practical systems thinking: define the user, constrain the workflow, make outputs inspectable, design for review, and connect technical work to adoption.
For collaborators
For collaborators
Start with AI evaluation if you care about shipping reliable agents, data products if you care about decision systems, and Focus Room if you want to see product interaction craft.
Topic hub
Case-study writing and artifacts
The case-study path is meant for readers who want evidence of applied judgment: how a problem was framed, what system boundaries mattered, how quality was evaluated, and which product constraints shaped the final implementation.
These links are intentionally not duplicate case-study pages. They point to canonical posts, artifacts, or project pages that show different slices of the same work: AI evaluation, analytics, product strategy, experiment infrastructure, and focused user experience design.
This section follows the starter-blog pattern of metadata-driven topic pages: each card shows a canonical article link, summary, date, reading time, and tags. The page is a hub, not a duplicate post archive.
AI Agent Evaluation Checklist
A practical checklist for launch readiness, regression thinking, and production review.
Read articleHealthcare AI Analytics
Applied AI and analytics framing for healthcare operations and decision support.
Read articleA/B Test Engineering Guide
Feature gates, experiments, reliable launch measurement, and experimentation infrastructure.
Read articleAI Agent Evaluation Is More Important Than Prompting
Why production AI agents need custom eval sets, trajectory checks, calibrated judges, regression tests, and business-ready metrics.
Read articleFor future notes on applied AI systems, evaluation, data products, and product workflows, subscribe to Yangming Li's Newsletter.
Subscribe for updates