ThinkWithPrompt by SynotticThinkWithPrompt

Break a big work problem into smaller, solvable parts (MECE)

Splits a messy problem into a clean MECE issue tree, so you know which pieces to tackle, in what order, and who owns each.

Thinking & DecisionsFew-ShotStandardFill-in Template

The prompt

Help me break a big problem into smaller parts I can actually work on. The problem, in my words: [DESCRIBE IT - e.g. "our team keeps missing delivery dates"] Context: [team, product, or process involved; what has changed recently] What I already know or suspect: [FACTS, DATA, THEORIES] Constraints: [time, budget, people, what I can and can't change] Steps: 1. Restate the problem as one clear question I am trying to answer. 2. Split it into 3-5 parts that are MECE: mutually exclusive (no overlaps) and collectively exhaustive (nothing missing). Name the logic of the split (e.g. process stages, internal vs. external, volume vs. rate, people / process / tools). 3. Break each part one level further where it helps, so every bottom-level piece is small enough for one person to investigate in a week or less. 4. Check the tree: point out any overlaps or gaps and fix them. If another way of splitting would be more useful, show it briefly and say why. 5. Prioritize the pieces by likely impact and ease of checking. Return: 1. The key question. 2. The issue tree as an indented list. 3. A table: Sub-problem | Why it might matter | How to check it | Data or person needed | Priority (H/M/L). 4. The 2-3 pieces to start on this week. Rules: keep the pieces specific to my situation, not generic categories. Don't state causes as facts; mark them as possibilities to check.

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

  • DESCRIBE IT - e.g. "our team keeps missing delivery dates"
  • team, product, or process involved; what has changed recently
  • FACTS, DATA, THEORIES
  • time, budget, people, what I can and can't change

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