Module 02 / 08
Prompting
Learn how to turn vague intent into reliable model behavior.
The point
Prompting is the first control surface. Good prompts make later systems easier to evaluate, debug, and operate.
Start with
Read next
Understanding check
You should be able to…
- write task prompts with clear inputs, outputs, and constraints
- use few-shot examples when behavior is hard to describe
- separate instruction quality from model capability
- know when prompting is no longer enough
Practice with an agent
Turn one job into a bounded specification
beginner · codex or claude, markdown, one real workflow
Make
a reusable task specification with a named user, input, output, constraints, examples, and stop conditions
You know it works when
run the same specification three times and explain which differences are acceptable and which violate the contract
Go deeper by building
Build a prompt pack for one workflow
beginner · claude, chatgpt, or any model playground
Make
five reusable prompts for a real workflow, each with inputs, expected output, and examples
You know it works when
include before/after outputs and explain which prompt changes improved reliability