Tian Pan
Software Engineer
AI Fallback Design Is an Architecture Problem, Not an Afterthought
Most AI features are designed for the happy path. Fallback design gets bolted on after the first production incident — if at all. Here's how to fix that before you write your first prompt.
AI Documentation Debt: How Stochastic Systems Break Your Technical Knowledge Base
AI feature docs rot faster than any other technical debt — and in ways teams rarely see coming. Here's why deterministic documentation patterns fail for probabilistic systems, and what to write instead.
The Coverage Illusion: Why AI-Generated Tests Inherit Your Code's Blind Spots
When AI generates both your code and your tests, it creates a closed loop: the same blind spots appear in both. High line coverage becomes a false signal, and the test suite becomes an artifact that reinforces bugs rather than catching them.
The Overcorrection Trap: Why Removing Your AI Feature After a Public Failure Makes Recovery Slower
When your AI feature fails publicly, the instinct to remove it or pile on guardrails extends recovery by months. Here's why cold-start trust repair works differently than software bug fixes — and what to do instead.
AI System Design Advisor: What It Gets Right, What It Gets Confidently Wrong, and How to Tell the Difference
AI gives genuinely useful input on textbook architecture tradeoffs and pattern exploration — and dangerously overconfident advice when your actual constraints are the ones that matter.
Behavioral Cloning for System Prompts: Preserving Expert Judgment Before It Walks Out the Door
When the engineer who built your production system prompt leaves, so does the reasoning behind every rule in it. A structured behavioral cloning approach captures the 'why' before it's gone.
The Budget Inversion Trap: Why Your Most Valuable AI Features Get the Cheapest Inference
Cost pressure in AI systems routinely routes complex, high-value workflows to the cheapest models—while low-stakes queries run on frontier tiers. Here's how to audit and fix the inversion.
Chain-of-Thought Has Two Failure Modes Nobody Talks About
Visible reasoning chains are supposed to make AI more transparent — but research shows they anchor users to wrong conclusions, bury the final answer in verbosity, and produce false audit trails that mislead compliance reviewers.
The Co-Evolution Trap: How Your AI Feature's Success Is Quietly Destroying Its Evaluations
When users adapt to your AI feature, they change the distribution it was evaluated on. Here's how to detect user-induced distribution shift and build evaluations that stay honest over time.
Continuous Production Eval: Statistical Quality Monitoring for Live LLM Traffic
Pre-deployment evals catch about 40% of production failures. A continuous monitoring stack using reference-free signals, SPC control charts, and SLO burn rate alerting catches the rest before users do.
The Co-Pilot Trap: Why Full Autopilot Ships Faster but Fails Harder
Full automation ships fast but fails systematically. A decision framework for placing each AI feature on the automation spectrum—and why 'just make it an agent' is the wrong default.
The Copy-Paste Contagion: How AI-Assisted Development Spreads Architectural Anti-Patterns
AI coding tools generate locally coherent but globally inconsistent code. When developers accept suggestions and copy-paste them, architectural anti-patterns spread at machine speed with no authorship accountability.