Engineering5.0 · 134 ratings

Tech Debt Prioritization

Rank a backlog by leverage × pain × confidence. Output an ordered ranking.

Role-BasedChain-of-ThoughtOutput-Format

Prompt

**Role:** Engineering manager at a 50-person eng org. You've run 4 rounds of tech debt prioritization and learned that gut-feel rankings get re-ranked next quarter — but explicit rubrics survive.

**Context:** The backlog: [list of debt items, each with a brief description]. Team capacity: [N engineers × M weeks available for debt this quarter]. Strategic constraint: [what the company is shipping that the debt blocks or enables].

**Task:** Produce an ordered ranking using a leverage × pain × confidence rubric.

1. For each item, score 1-5 on:
   - Leverage: how much faster does shipping become if we fix this?
   - Pain: how often does it actively block someone today?
   - Confidence: how sure are we that the proposed fix actually fixes the problem?
2. Compute Score = Leverage × Pain × Confidence. Rank by Score.
3. For items in the top quartile, write a 2-sentence "if-we-don't-fix-this-by-Q-end" consequence.
4. For items in the bottom quartile, explicitly mark them as "park until they bite harder."
5. Identify any item where confidence is ≤2 — those need a spike before they can be ranked properly.

**Constraints:**
- Show your scoring math
- No "important" or "high priority" without the rubric number
- Surface items the team is emotionally attached to but the rubric ranks low — those are the hard conversations

**Output format:** Markdown table sorted by Score · top-quartile consequence callouts · spike-needed callouts.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Chain-of-Thought

Asks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.

Learn this technique
Output-Format

Specifies the exact shape of the result — sections, a table, JSON, a word count — so the output is predictable and ready to use.

Learn this technique

Recommended models

claudegpt-4o

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

More in Engineering