Blog
Page 6
12 articlesYour Prompt Is a Liability with No Type System
Apr 1910 min
Prompt Versioning Done Right: Treating LLM Instructions as Production Software
Apr 198 min
Zero-Shot, Few-Shot, or Chain-of-Thought: A Production Decision Framework
Apr 1910 min
RAG Knowledge Base Freshness: The Staleness Problem Teams Solve Last
Apr 1911 min
RAG Position Bias: Why Chunk Order Changes Your Answers
Apr 198 min
Testing the Retrieval-Generation Seam: The Integration Test Gap in RAG Systems
Apr 1911 min
RBAC Is Not Enough for AI Agents: A Practical Authorization Model
Apr 1911 min
Reasoning Model Economics: When Chain-of-Thought Earns Its Cost
Apr 199 min
The Reranker Gap: Why Most RAG Pipelines Skip the Most Important Layer
Apr 198 min
Sequential Tool Call Waterfalls: The Hidden Latency Tax in Agent Loops
Apr 199 min
Shadow to Autopilot: A Readiness Framework for AI Feature Autonomy
Apr 1911 min
The Share-Nothing Agent: Designing AI Agents for Horizontal Scalability
Apr 1911 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.
