Blog
Page 15
12 articlesEval Coverage as a Production Metric: Is Your Test Suite Actually Testing What Users Do?
Apr 169 min
Event-Driven Agent Scheduling: Why Cron + REST Calls Fail for Recurring AI Workloads
Apr 1611 min
Why Your AI Model Is Always 6 Months Behind: Closing the Feedback Loop
Apr 1610 min
The Feedback Loop Trap: Why AI Features Degrade When Users Adapt to Them
Apr 1610 min
Feedback Surfaces That Actually Train Your Model
Apr 1610 min
Fleet Health for AI Agents: What Single-Agent Observability Gets Wrong at Scale
Apr 169 min
GraphRAG vs. Vector RAG: When Knowledge Graphs Beat Embeddings
Apr 169 min
Where to Put the Human: Placement Theory for AI Approval Gates
Apr 1612 min
When Embeddings Aren't Enough: A Decision Framework for Hybrid Retrieval Architecture
Apr 1611 min
The Insider Threat You Created When You Deployed Enterprise AI
Apr 169 min
The Instruction Complexity Cliff: Why LLMs Follow 5 Rules Reliably but Not 15
Apr 1610 min
The Jagged Frontier: Why AI Fails at Easy Things and What It Means for Your Product
Apr 1610 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.
