Cutting LLM API Costs: Prompt Caching, Batching and Smaller Models
An LLM bill grows faster than traffic. Here's how prompt caching, the Batch API and smaller models cut it, with real prices, tested Python c...
Nov 5, 2026
17 min
Claude Won't Talk to Minors, But Your App Can (If You Do the Work).
Anthropic locked minors out of Claude.ai and got the enforcement wrong more than once along the way. None of that applies to what you build ...
Sep 13, 2026
11 min
I Built a Tiny AI Agent From Scratch — Every Line Tested Before It Touched a Real API
AI agents are often overcomplicated. At their core, they’re just models that can call tools, use the results, and continue working. This tut...
Jun 14, 2026
8 min
Token Budgeting: The Engineering Skill Nobody Talks About
Most developers think token optimization means shorter prompts. In 2026, the biggest costs come from bloated chat history, unused tool schem...
Jun 18, 2026
10 min