Blog
Page 19
12 articlesYour Team's Benchmarks Are Lying to Each Other: Shared Eval Infrastructure Contamination
Apr 1610 min
The Sparse Reward Trap: Why Long-Horizon Agents Look Great in Demos and Break in Production
Apr 1612 min
Specification Gaming in Production AI Agents: When Your Agent Optimizes the Wrong Thing
Apr 169 min
Speculative Decoding in Production: Free Tokens and Hidden Traps
Apr 169 min
The Three Hidden Debts Killing Your AI System
Apr 1610 min
Testing the Untestable: Integration Contracts for LLM-Powered APIs
Apr 1610 min
The Testing Pyramid Inverts for AI: Why Unit Tests Are the Wrong Investment for LLM Features
Apr 1610 min
Tokens Are a Finite Resource: A Budget Allocation Framework for Complex Agents
Apr 1610 min
Vector Store Access Control: The Row-Level Security Problem Most RAG Teams Skip
Apr 1611 min
When Your Agent Framework Becomes the Bug
Apr 168 min
Zero-Shot vs. Few-Shot in Production: When Examples Help and When They Hurt
Apr 1610 min
Agent Fleet Observability: Monitoring 1,000 Concurrent Agent Runs Without Dashboard Blindness
Apr 1512 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.
