LLM Mechanics for Agent Builders — No Math Required

The five facts about how LLMs actually work that every agent engineer runs into within a week: tokens are the meter, the context window is the whole world, the model remembers nothing between calls, temperature 0 is not determinism, and non-determinism compounds until testing becomes statistics.

Content current as of 2026-09.

Lessons

1. Tokens: the meter everything runs on
2. The context window — and the amnesia behind it
3. Sampling and temperature: where the dice live
4. Non-determinism compounds: why agent testing is statistical
5. Latency and cost: the two meters that gate every design