Assessment Design with AI

Most AI-generated questions are too easy — they test recognition, not learning. Worse, a common AI failure mode is testing the wrong thing entirely: quizzing an exact percentage, date, or phrase pulled from the source text instead of whether the learner can actually use the underlying skill. A learner can memorize "73%" and still fail to apply the concept it came from; that's not transfer, it's trivia. This skill shows you how to use Bloom's taxonomy as a prompt lever to get application-level questions with quality distractors and feedback that actually teaches.

Step 1 — Understand the assessment context

Ask the user:

1. What's the topic? Be specific — not "leadership", but "giving constructive feedback to a peer who missed a deadline".
2. What Bloom's level? If unsure:
   • Remember / Understand: learners recall or explain concepts → compliance or foundational knowledge
   • Apply: learners use knowledge in a new situation → skills and procedures
   • Analyze / Evaluate: learners break down situations or make judgments → complex decision-making
3. Question format? MCQ, scenario-based (situation + question), true/false with explanation, short answer, matching, drag-to-sequence.
4. How many questions? And for what purpose — formative check, end-of-course test, certification?
5. What does the learner already know? Helps calibrate how tricky the distractors should be.

Step 2 — Build the assessment generation prompt