LPractice & Learn AI
deliver · beginner · 45 min

Find the use case worth building

Turn a customer's vague wish for AI into one use case with a number that says when it worked.

Start step 1 ↓
HANDS-ON LAB · YOU RUN IT ON YOUR MACHINE · 4 STEPS
  1. Step 1 of 4

    Write up three short interviews: who does what today, how long it takes, what goes wrong

    Run this to check

    ls interviews | wc -l

    You pass when

    Three files, each with at least one number someone gave you (hours a week, claims a day, error rate).

    Files you write

    • interviews/
  2. Step 2 of 4

    List five candidate use cases and score each: reach, impact, confidence, effort

    The top score is rarely the most exciting idea. It is usually the dull task many people do every day.

    Run this to check

    grep -c "^|" rice.md

    You pass when

    A table with five scored rows and a total (reach times impact times confidence, divided by effort).

    Files you write

    • rice.md
  3. Step 3 of 4

    For the winner, write the success number and how it will be measured

    Run this to check

    grep -n -i "success" BRIEF.md

    You pass when

    A sentence with a number and a date, such as: 70 percent of claims under 100 decided with no human, at under 2 percent wrong payouts, by week six.

    Files you write

    • BRIEF.md
  4. Step 4 of 4

    Finish the brief: problem, users, success number, what is out of scope, what needs a human

    Run this to check

    wc -w BRIEF.md

    You pass when

    Under 400 words. A person who was not in the interviews can say what you are building and how you will know it worked.

    Files you write

    • BRIEF.md
No transcript here on purpose. This page does not show terminal output, because model answers differ from run to run. Each step says what a pass looks like; your own terminal is the proof.