Skip to content

Decision Making

Weighted Decision Matrix

AI Tools:
ChatGPT + 3 moreWorks with ChatGPT, Claude, Gemini, Perplexity
Category: Problem Solving

Turn unranked priorities into weighted criteria, scored options, a sensitivity check, and a three-sentence recommendation.

Prompt Quality - 100/100 · Strong

The Prompt

weighted-decision-matrix.md

You are a decision-analysis consultant. Build a weighted decision matrix.

DECISION TO MAKE:
{{decision}}

OPTIONS:
{{options}}

MY PRIORITIES (in my own words, unranked):
{{priorities}}

INSTRUCTIONS:
1. From my stated priorities, derive 5 - 8 evaluation criteria. Merge overlapping ones; name each clearly.
2. Propose a weight (out of 100, summing to 100) for each criterion. One-line reasoning per weight.
3. Score every option against every criterion on a 1 - 10 scale. Justify each score in a short phrase - no unexplained numbers.
4. Calculate weighted totals and rank the options.
5. Sensitivity check: which 1 - 2 criteria, if weighted differently, would flip the ranking? What would have to change for a different option to win?
6. Separately list irreversible risks per option.
7. Final recommendation in 3 sentences: the pick, the main reason, and the condition under which you'd choose differently.

OUTPUT FORMAT:
- Derived criteria + weights (table, with one-line rationale per weight)
- Scoring matrix (table with justification per cell)
- Weighted totals + rank
- Sensitivity check
- Irreversible risks per option
- Final recommendation (3 sentences)

CONSTRAINTS:
- Do not silently invent criteria I didn't imply - if you add one, flag it as [inferred] and explain why.
- If two options are within 5% of each other, say so and treat it as a tie needing a qualitative tiebreaker, not a clean win.
- Sanity-check the math before presenting it.

Negative prompt

Included when you copy the prompt

Do not invent options or criteria that were not implied. Do not let one criterion dominate unless the weights genuinely justify it. Do not hide a near-tie as a decisive win. Do not skip the sensitivity check or irreversible risks.

The PromptUTF-8

Fill in your details below - this prompt updates as you type, then copy it.

Fill in your details

0 of 3 filled. Preview updates as you type - then copy the finished prompt (negative prompt included when present).

The choice you need to make.

Option A, B, C - add or remove as needed.

What matters to you, unranked.

weighted-decision-matrix.md

Prompt preview

You are a decision-analysis consultant. Build a weighted decision matrix.

DECISION TO MAKE:
{{decision}}

OPTIONS:
{{options}}

MY PRIORITIES (in my own words, unranked):
{{priorities}}

INSTRUCTIONS:
1. From my stated priorities, derive 5 - 8 evaluation criteria. Merge overlapping ones; name each clearly.
2. Propose a weight (out of 100, summing to 100) for each criterion. One-line reasoning per weight.
3. Score every option against every criterion on a 1 - 10 scale. Justify each score in a short phrase - no unexplained numbers.
4. Calculate weighted totals and rank the options.
5. Sensitivity check: which 1 - 2 criteria, if weighted differently, would flip the ranking? What would have to change for a different option to win?
6. Separately list irreversible risks per option.
7. Final recommendation in 3 sentences: the pick, the main reason, and the condition under which you'd choose differently.

OUTPUT FORMAT:
- Derived criteria + weights (table, with one-line rationale per weight)
- Scoring matrix (table with justification per cell)
- Weighted totals + rank
- Sensitivity check
- Irreversible risks per option
- Final recommendation (3 sentences)

CONSTRAINTS:
- Do not silently invent criteria I didn't imply - if you add one, flag it as [inferred] and explain why.
- If two options are within 5% of each other, say so and treat it as a tie needing a qualitative tiebreaker, not a clean win.
- Sanity-check the math before presenting it.
0 / 3 filledPreview

Examples

Example input

Decision: Pick a helpdesk for a 14-person SaaS support team. Options: Zendesk, Intercom, Freshdesk. Priorities: Agents should not live in five tabs. We need a decent knowledge base. Price under ~$80/agent. We already use Slack. Don't want a six-month rollout.

What you should get

Criteria (weights): Time-to-live (22), Slack + existing stack fit (18), Knowledge base quality (16), Price (16), Agent UX / fewer tabs (14), Reporting (8), Migration risk (6). [inferred] Reporting flagged because ticket volume was implied. Scores (illustrative): Intercom leads on UX and Slack; Zendesk on KB and reporting; Freshdesk on price. Weighted totals within 5% between Intercom and Zendesk → treat as a tie. Sensitivity: If Price jumps to 28, Freshdesk wins. If Slack fit drops, Zendesk wins. Recommendation: Intercom if we value agent UX and Slack; Zendesk if the knowledge base and reporting matter more than a shorter rollout. Revisit if we cannot keep price under $80/agent.

When to use this prompt

Use it when

  • You need help with managers.
  • You need help with engineers.
  • You need help with operators.
  • You need help with founders.

Skip it when

  • You only need a one-line ask with no constraints, format, or context.
  • You cannot supply the fill-in details the template asks for.
  • A different category or tool-specific workflow fits the job better.

How to get a good result

Done when

Criteria (weights): Time-to-live (22), Slack + existing stack fit (18), Knowledge base quality (16), Price (16), Agent UX / fewer tabs (14), Reporting (8), Migration risk (6). [inferred] Reporting flagged because ticket volume was implied. Scores (illustrative): Intercom leads on UX and Slack; Zendesk on KB and reporting; Freshdesk on price. Weighted totals within 5% between Intercom and Zendesk → treat as a tie. Sensitivity: If Price jumps to 28, Freshdesk wins. If Slack fit drops, Zendesk wins. Recommendation: Intercom if we value agent UX and Slack; Zendesk if the knowledge base and reporting matter more than a shorter rollout. Revisit if we cannot keep price under $80/agent.

Common mistakes

  • Leaving decision, options, priorities vague - the model then invents placeholders.
  • Asking ChatGPT, Claude, Gemini, or Perplexity for a shorter answer after a long structured prompt - that throws away the format rules.
  • Stopping when the first draft appears instead of checking it against the success criteria below.

FAQ

What do I fill in before I copy this prompt?
Replace these placeholders with your details: decision, options, priorities. Required fields are marked on the page. The prompt text updates as you type.
Which AI tools is this prompt written for?
It works best with ChatGPT, Claude, Gemini, Perplexity. Copy the filled prompt and paste it into the tool you already use.
What should a good result look like?
Criteria (weights): Time-to-live (22), Slack + existing stack fit (18), Knowledge base quality (16), Price (16), Agent UX / fewer tabs (14), Reporting (8), Migration risk (6). [inferred] Reporting flagged because ticket volume was implied. Scores (illustrative): Intercom leads on UX and Slack; Zendesk on KB and reporting; Freshdesk on price. Weighted totals within 5% between Intercom and Zendesk → treat as a tie. Sensitivity: If Price jumps to 28, Freshdesk wins. If Slack fit drops, Zendesk…
What are common mistakes with this prompt?
Leaving decision, options, priorities vague - the model then invents placeholders. Asking ChatGPT, Claude, Gemini, or Perplexity for a shorter answer after a long structured prompt - that throws away the format rules. Stopping when the first draft appears instead of checking it against the success criteria below.

Best for

  • Managers
  • Engineers
  • Operators
  • Founders

More prompts like this — same topic and style.