Page 28
12 articlesThinking Budgets: When Extended Reasoning Models Actually Make Economic Sense
Extended reasoning models can inflate inference costs 5–30x — or deliver genuine quality jumps on hard tasks. The difference comes down to routing: which queries actually warrant thinking tokens, how to set budget ceilings, and how to catch over-thinking before it hits your invoice.
Timeout-Aware Agent Design: How to Deliver Partial Results Instead of Silent Failure
Most AI agents fail completely when they hit a deadline. Here's how to design agents that surface the best available result instead of returning nothing.
Token Economics for AI-Powered API Products: Pricing What You Cannot Predict
Per-seat and per-query pricing both collapse under variable LLM costs. Here's how to think about hybrid pricing, token budgets, and margin math for AI-powered API products.
Tool Discovery at Scale: Why Embedding-Only Retrieval Fails Past 20 Tools
Flat embedding retrieval breaks as AI agent tool inventories grow past 20. Here's why it fails, what structured capability metadata looks like, and how hierarchical routers solve the problem that better descriptions cannot.
Tool Output Schema Design: How Your Tool Responses Shape Agent Reasoning
Poor tool output schemas cause agent reasoning failures that look like model problems. A practical guide to field naming, nullability, verbosity, error design, and output contract testing for LLM tool interfaces.
The Two-Sided Cost of AI Content Filters: Why Over-Refusal Is a Business Problem Too
AI content filters are routinely tuned to minimize false negatives while ignoring false positives — but blocking legitimate users has measurable business costs too. Here's how to calibrate both error types properly.
Vector DB Sharding: Why HNSW Breaks at Partition Boundaries and What to Do About It
HNSW graphs resist partitioning in ways that cause silent recall degradation at scale. Here's why it breaks, what the quality loss looks like in practice, and the operational patterns teams use to recover accuracy when they've outgrown a single node.
The Accountability Transfer Problem: Why AI Gets Blamed for Decisions It Was Never Designed to Make Alone
When AI-assisted decisions go wrong, organizations often blame 'the AI' — but the AI approved nothing. Here's why accountability transfer happens in production systems and the design patterns that prevent it.
Why AI Coding Tools Amplify Juniors and Plateau Seniors
AI coding tools deliver 27–39% productivity gains for junior engineers while slowing experienced developers by 19% on complex tasks. Here's why the gap exists and what senior engineers need to do differently.
Your Prompts Are Configuration: Treating AI Settings as Production Infrastructure
Most teams track every environment variable in production but let prompts, sampling parameters, and tool schemas drift unversioned. Here's why AI configuration is more fragile than env vars — and how to manage it with the same rigor.
AI Content Drift: When Your Documentation Corpus Starts Contradicting Itself
AI-generated documentation quietly contradicts itself over time as models update, prompts evolve, and corpus grows. Here's how drift accumulates, why users catch it before editors do, and how to build consistency auditing that actually scales.
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.
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.
