Claude Prompt Caching: 6 Tricks That Cut Your API Bill
Breakpoints, TTL math, Batch stacking, and a two-session split. Measured on OpenRouter, $0.003 vs $0.022 per turn
How to Evaluate a New AI Model Without Starting From Scratch
Public benchmarks shortlist a model. A small task-specific eval tells you whether it deserves a larger test.
Recursive Self-Improvement for Agents: 7-Check Persistence Gate
How to decide whether a machine-generated change should influence the next run
