Blog
Page 22
12 articlesThe 90% Reliability Wall: Why AI Features Plateau and What to Do About It
Apr 189 min
On-Call for Stochastic Systems: Why Your AI Runbook Needs a Rewrite
Apr 1810 min
The On-Device LLM Problem Nobody Talks About: Model Update Propagation
Apr 1812 min
On-Device LLM Inference in Production: When Edge Models Are Right and What They Actually Cost
Apr 1810 min
The Orchestration Framework Trap: When LangChain Makes You Slower to Ship
Apr 188 min
The Over-Tooled Agent Problem: Why More Tools Make Your LLM Dumber
Apr 189 min
The PII Leak in Your RAG Pipeline: Why Your Chatbot Knows Things It Shouldn't
Apr 1810 min
The Privacy Architecture of Embeddings: What Your Vector Store Knows About Your Users
Apr 1810 min
Prompt Archaeology: Recovering Intent from Legacy Prompts Nobody Documented
Apr 1810 min
The Prompt Debt Spiral: How One-Line Patches Kill Production Prompts
Apr 189 min
The Prompt Governance Problem: Managing Business Logic That Lives Outside Your Codebase
Apr 189 min
Prompt Injection Is a Supply Chain Problem, Not an Input Validation Problem
Apr 189 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.
