Blog
Page 17
12 articlesThe AI Incident Response Playbook: Diagnosing LLM Degradation in Production
Apr 1813 min
The AI Incident Runbook: When Your Agent Causes Real-World Harm
Apr 1811 min
The AI Output Copyright Trap: What Engineers Need to Know Before It's a Legal Problem
Apr 1811 min
The AI Taste Problem: Measuring Quality When There's No Ground Truth
Apr 1811 min
The Three Silent Clocks of AI Technical Debt
Apr 1810 min
The Annotation Economy: Why Every Label Source Has a Hidden Tax
Apr 189 min
Annotation-Free Evaluation: Measuring LLM Quality Before You Have Ground Truth
Apr 1812 min
The Feedback Loop You Never Closed: Turning User Behavior into AI Ground Truth
Apr 1810 min
Benchmark Contamination: Why That 90% MMLU Score Doesn't Mean What You Think
Apr 188 min
Why 'Fix the Prompt' Is a Root Cause Fallacy: Blameless Postmortems for AI Systems
Apr 189 min
Board-Level AI Governance: The Five Decisions Only Executives Can Make
Apr 189 min
Browser Agents in Production: The DOM Fragility Tax
Apr 1813 min
About Tian Pan
I'm Tian Pan, an engineer-founder focused on agentic engineering — building autonomous AI systems and scaling engineering teams. I write practical guides on system design, technical leadership, and shipping with AI agents. Previously an early engineer at Uber, Brex, and IoTeX.
