Write the test before you write the lesson 📝

There's a rule in teaching called backward design. You don't start with the lesson. You start with the assessment. Decide exactly how you'll know they learned it, then build backward to the activities that get them there. Sounds obvious. Almost nobody does it, because writing the test first is harder than diving straight into the fun part.

Same trap with AI builds. We open a chat and start barking the build before we can say what "done" actually looks like. Then we act surprised when done keeps moving.

The habit i borrowed from the classroom: if you can't write the check for "done," you're not ready to build. Not the feature, the check. One sentence you could prove true or false. "A new user gets from signup to first export without asking me a single question." Now every step has a target to aim at, and you'll know the moment you've hit it.

Writing that sentence first feels like bureaucracy. It's the opposite. It's the thing that stops you building three polished versions of the wrong feature.

And there's a bonus. If you can't write the sentence, you just found out the project isn't scoped yet. Better to learn that now, for free, than four hours in.

What's your one-sentence "done" for the thing you're building right now?

8 comments

Write the test before you write the lesson 📝