ThinkWithPrompt by SynotticThinkWithPrompt

Turn expert know-how into a decision tree

Converts how an expert makes a recurring decision into a clear yes/no decision tree others can follow, with escalation points.

Thinking & DecisionsFew-ShotAdvancedFill-in Template

The prompt

Turn the expert knowledge below into a decision tree that others can follow. The decision: [e.g. "whether to approve a refund", "which support tier handles a ticket", "how to classify an incident"] Expert's explanation: [PASTE interview notes, emails, examples of past decisions, or the expert's own words] Who will use the tree: [e.g. "new team members", "frontline staff"] Rules or limits that always apply: [policy, approval limits, legal or safety constraints] Build: 1. Starting point - the trigger that starts the decision. 2. The tree - questions that can be answered yes/no or with a short set of options, ordered so the most decisive and safety-critical questions come first. Each branch ends in a clear outcome or action. 3. Text version as a numbered outline (e.g. 1 > 1a > 1a-i) so it works in Word or a wiki. 4. Diagram code in Mermaid flowchart syntax that I can paste into a diagram tool. 5. Escalation points - where the tree should send the case to a person instead of deciding. 6. Test cases - 5 realistic scenarios with the path each takes and the outcome, including at least 2 edge cases. 7. Gaps - situations the expert's input doesn't cover, marked [ASK EXPERT]. Rules: - Reflect how the expert actually decides; don't add criteria they didn't mention without labeling them (suggested). - Every path must end in an outcome; no dead ends or loops. - For decisions with legal, financial, safety, or HR consequences, the tree supports judgment; it doesn't replace the accountable person's sign-off.

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

Fill in the blanks and use this promptMore Thinking & Decisions prompts

What to fill in

  • e.g. "new team members", "frontline staff"
  • policy, approval limits, legal or safety constraints
  • ASK EXPERT

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