Blog
Page 34
12 articlesPost-Training Alignment for Product Engineers: What RLHF, DPO, and RLAIF Actually Mean for You
Apr 1611 min
The Pretraining Shadow: The Hidden Constraint Your Fine-Tuning Plan Ignores
Apr 169 min
Pricing AI Features: The Unit Economics Framework Engineering Teams Always Skip
Apr 1611 min
Prompt Cache Break-Even: The Exact Math on When Provider-Side Prefix Caching Actually Pays Off
Apr 169 min
Prompt Canaries: The Deployment Primitive Your AI Team Is Missing
Apr 1610 min
Prompt Injection Detection at 100,000 Requests Per Day: Why Simple Defenses Break and What Actually Works
Apr 1611 min
The Prompt-Model Coupling Trap: Why Your Prompts Only Speak One Model's Dialect
Apr 1610 min
Property-Based Testing for LLM Outputs: Finding the Bugs Your Eval Set Never Imagined
Apr 1611 min
Poisoned at the Source: RAG Corpus Decay and Data Governance for Vector Stores
Apr 1611 min
The RAG Eval Antipattern That Hides Retriever Bugs
Apr 1610 min
Schema-First AI Development: Define Output Contracts Before You Write Prompts
Apr 169 min
The Schema Problem: Taming LLM Output in Production
Apr 169 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.
