You have the whole idea in your head. Your agent cannot build a feeling, and you cannot check whether a feeling is finished. Before any code, you turn that idea into a clear, specific list of what the software must do. This chapter gets you that list.
2.1.1A requirement is testable, not a wish
A requirement is one thing your software must do, written plainly enough that anyone can tell whether it works yet.
| Wish | Requirement |
|---|---|
| Users can log in | A person signs in with an email and password, and resets a forgotten one through an email link |
The difference is that you can test the requirement and point at a clear yes or no. Write every requirement so it passes that test.
2.1.2Write each one as a user story
Professional teams capture requirements as user stories, one line each: As a [type of user], I want to [do something], so that [reason]. The shape forces you to name who the feature is for and why it exists. That quietly kills the features nobody actually needs.
Example: As a shopper, I want to save items to a cart, so that I can pay for them all at once.
2.1.3Split must-have from later
List every story you can think of, then mark each one must-have or later. Be harsh: a must-have is something the product is useless without, not something that would be nice to have. The must-haves are all you build first; everything else waits its turn.
2.1.4Get them from real users, not your head
Requirements come from the people who will actually use the thing, not your imagination. Talk to three to five real potential users and write down what they ask for in their own words.
Never ask "would you use this?", which buys you a polite yes and nothing else. Ask about the past instead, where the answers are facts:
- What do you do about this today, step by step?
- What did the last time cost you, in money or in hours?
- What have you already tried, and why did you stop?
Find those people where they already complain. Try a community you belong to, a forum about the problem, or the handful of people who have grumbled about it in front of you.
Watch out: if you cannot find one person who wants this, that is the cheapest moment you will ever get to learn it, long before you have built anything. Check before you build; if you build anyway, at least know you skipped it.
This prompt turns the idea in your head into that list:
Do this now: paste the prompt, describe your idea, and let your agent draft the user-story list into your specs folder. That list is the raw material for every chapter that follows.
