Technical editorial

Build the argument, not just the answer.

Practical, source-backed writing about automation, productivity, and AI agents.

Recently published

Latest articles

Local AI

Choosing a Cache-Aware Prompt Accounting Boundary for Ollama

A practical recording boundary for Ollama usage: keep requested context, observed prompt tokens, cache-read tokens, and prompt-evaluation time in separate fields, and collect streaming usage only from the terminal chunk.

Browse by subject

Explore topics