Getting good answers

Prompts, examples, thinking budgets, tools and schemas: the controls that decide whether a model hands you something usable or something merely plausible.

10 concepts, about 60 minutes of reading at roughly six minutes each. 5 of them are free to read with no account; the rest need a paid plan.

What is in this track

1. Prompt engineering is a real skill — The same model answers the same question differently depending on how you ask. That gap is the whole job. (free)
2. Zero-shot, few-shot, in-context learning — Showing a model three examples of the output you want usually beats describing it in a paragraph. (free)
3. Chain of thought — Making a model write out its steps changes the answer, because the steps are where the computation actually happens. (free)
4. Self-consistency — Ask the same question five times, keep the answer that shows up most often, and accuracy goes up. (free)
5. Thinking tokens you pay for and never see — Hidden reasoning is billed at output rates, so a short answer can carry a bill many times larger than it looks. (free)
6. Test-time compute — Spending more computation when the question arrives, rather than only back when the model was trained.
7. The effort dial — The reasoning control became a qualitative level, from low to max, but the old token budget did not disappear.
8. Structured output — Constrained decoding makes invalid JSON impossible to generate, which retires the retry loop everyone still writes.
9. Function calling and tool use — The model never runs anything. It writes down what it would like called, and your code decides what happens next.
10. Multimodal input — Images, audio and video are converted into tokens before the model sees them, and tokens are what you are billed for.

Before this: Turning the dials

After this: Memory and truth

Every track · Pricing · Claims we checked and could not stand behind