14 min · up to 75 XP

Iterate and refine

Prompting is a loop, not a lottery. Build your refinement instincts.

Module finale. Priya's brief was textbook, everything this module taught: context, a direct ask, a named role, an exact format. The draft that came back is… a 6 out of 10. Right facts, wrong weight, and the one number the board cares about is buried in paragraph three.

Ben slumps: "So even a perfect prompt is a lottery." Priya doesn't re-roll. She's about to do the thing that separates people who use AI from people who just demo it. Which is what, exactly?

Check your intuition

The prompt was already good, and the draft is still only 6/10. What's Priya's next move?

The first reply isn't the verdict on your prompt, it's a draft, and the conversation that produced it is now primed to improve it.

Three follow-up moves do most of the lifting. Tighten fixes the weight: "halve it, keep the numbers." Redirect fixes the aim: "wrong audience, rewrite for the board." Interrogate exposes the guesswork: "what did you assume?" You drilled all three in Module 2; now watch them run as one loop, then drive it yourself.

This lesson is part of the full course

The free lessons are just the opening chapter. Unlock the rest of AI at Work to keep going.

Every AI at Work lesson, as it ships
New interactive lessons added monthly
Founding-member pricing, locked in
Learn at your own pace, forever

or keep browsing the free lessons