Blog
Page 23
12 articlesPrompt Localization Debt: The Silent Quality Tiers Hiding in Your Multilingual AI Product
Apr 189 min
Red-Teaming Consumer LLM Features: Finding Injection Surfaces Before Your Users Do
Apr 189 min
Retrieval Monoculture: Why Your RAG System Has Systematic Blind Spots
Apr 1810 min
Sandboxing Agents That Can Write Code: Least Privilege Is Not Optional
Apr 1812 min
Serving AI at the Edge: A Decision Framework for Moving Inference Out of the Cloud
Apr 1810 min
Shadow Traffic for AI Systems: The Safest Way to Validate Model Changes Before They Ship
Apr 1810 min
The Shared Prompt Service Problem: Multi-Team LLM Platforms and the Dependency Nightmare
Apr 1810 min
The Skill Atrophy Trap: How AI Assistance Silently Erodes the Engineers Who Use It Most
Apr 1810 min
SLOs for Non-Deterministic AI Features: Setting Error Budgets When Wrong Is Probabilistic
Apr 1810 min
Specification Gaming in Production LLM Systems: When Your AI Does Exactly What You Asked
Apr 1810 min
SRE for AI Agents: What Actually Breaks at 3am
Apr 1810 min
SSE vs WebSockets vs gRPC Streaming for LLM Apps: The Protocol Decision That Bites You Later
Apr 1811 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.
