Blog
Page 4
12 articlesThe Prompt Made Sense Last Year: Institutional Knowledge Decay in AI Systems
Apr 1910 min
When Vector Search Fails: Why Knowledge Graphs Handle Queries Embeddings Can't
Apr 199 min
The Last-Mile Reliability Problem: Why 95% Accuracy Often Means 0% Usable
Apr 199 min
The Latency Perception Gap: Why a 3-Second Stream Feels Faster Than a 1-Second Batch
Apr 1911 min
Why Your LLM Alerting Is Always Two Weeks Late
Apr 1910 min
Your Model Is Most Wrong When It Sounds Most Sure: LLM Calibration in Production
Apr 199 min
LLM Cost Forecasting Before You Ship: The Estimation Problem Most Teams Skip
Apr 199 min
LLM-Powered Data Migrations: What Actually Works at Scale
Apr 1910 min
LLMs as Data Engineers: The Silent Failures in AI-Driven ETL
Apr 1911 min
What Model Cards Don't Tell You: The Production Gap Between Published Benchmarks and Real Workloads
Apr 199 min
Model Deprecation Is a Systems Migration: How to Survive Provider Model Retirements
Apr 1911 min
The Model Portability Tax: How to Architect AI Systems You Can Actually Migrate
Apr 199 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.
