Draft page

This page is an outline. It describes what will be covered and is not yet complete technical documentation.

Prompt engineering has a poor reputation earned by folklore, but the underlying practice is ordinary engineering: change one thing, measure the effect on a fixed evaluation set, keep what works.

This page focuses on techniques that survive that treatment, and on the evaluation discipline that makes the difference.

What you will learn

  • Which prompt structures reliably improve task performance.
  • How to build an evaluation set before tuning prompts.
  • How prompt length interacts with latency and cost.
  • Why prompts should be versioned like any other production artifact.

This page is an outline. The subsections below are the planned structure; they are filled in as the handbook is written.

Prompt structure

Draft

Instructions, examples and context

Draft

Evaluation before iteration

Draft

Prompt length, latency and cost

Draft

Versioning prompts

Draft

Techniques that do not generalise

Draft