Trace a weak AI output to a fixable cause using a Five Whys diagnostic.
The move: diagnose before you reprompt. Five Whys helps you move from symptom to cause. In AI work, the symptom is often emotional: 'This is bad,' 'This is generic,' or 'This missed the point.' Those statements do not tell you what to change. A why chain does. Start with the defect. Why is it weak? Why did that happen? Why did the prompt or workflow allow it? Stop when you find a fixable cause: missing source, vague audience, no success criteria, unbounded scope, no examples, or an impossible ask. Symptom The model wrote generic advice. Cause The prompt gave no…
Sign up free — one personalized lesson every day, matched to your role and goals.
Already have an account? Sign in