ThinkWithPrompt by SynotticThinkWithPrompt

Prepare SME interview questions to capture expert know-how

A structured interview plan that pulls the real decisions, mistakes, and shortcuts out of a subject matter expert, not just theory.

Learning & TeachingFew-ShotStandardAnalyzePlanFill-in Template

The prompt

Help me prepare to interview a subject matter expert (SME) so I can build training from what they know. Topic or task: [WHAT THE TRAINING COVERS] SME's role: [e.g. "senior claims adjuster, 12 years"] Learners: [WHO WILL TAKE THE TRAINING and their experience level] Time I have with the SME: [e.g. "two 45-minute sessions"] What I already have: [existing docs, slides, SOPs, or "nothing"] Build an interview plan that: - Focuses on what people must DO, not everything the SME knows. - Uses cognitive task analysis techniques: walk me through a real recent case, critical decision points, cues they notice, what a novice would miss. - Surfaces the most common and most costly mistakes, and why people make them. - Separates "must know" from "nice to know" and "can look up". - Captures real stories and examples I can turn into scenarios. Return: 1. A one-paragraph pre-interview note to send the SME (purpose, time, what to bring). 2. Interview questions grouped by phase: warm-up, task walkthrough, decisions and judgment, mistakes and edge cases, wrap-up. Mark the 8 must-ask questions. 3. Follow-up probes for when answers are vague ("It depends" - on what?). 4. A note-taking template: Task step | Decision or cue | Common error | Example or story | Must/Should/Could know. 5. Tips for keeping a talkative SME on track and for validating content afterward.

Highlighted [brackets] are blanks to replace with your own details.

Fill in the blanks and use this promptMore Learning & Teaching prompts

What to fill in

  • WHAT THE TRAINING COVERS
  • e.g. "senior claims adjuster, 12 years"
  • WHO WILL TAKE THE TRAINING and their experience level
  • e.g. "two 45-minute sessions"
  • existing docs, slides, SOPs, or "nothing"

How this prompt is built

This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.

Related prompts

Find more prompts like this