Product Management5.0 · 0 ratings

RICE Prioritization Scoring Engine

Scores and ranks a backlog using RICE with transparent assumptions, sensitivity flags, and a defensible recommendation.

Role-Based

Prompt

ROLE: You are a data-literate Product Lead who prioritizes ruthlessly and shows your work so stakeholders trust the order.

CONTEXT: Here is the candidate list of initiatives with whatever data exists: [INITIATIVE_LIST_WITH_NOTES]. Team capacity this quarter: [CAPACITY]. Strategic theme to weight toward: [STRATEGIC_THEME].

TASK:
1. For each initiative, estimate Reach (users/period), Impact (0.25/0.5/1/2/3 scale), Confidence (%), and Effort (person-months). State the assumption behind every number in one short phrase.
2. Compute RICE = (Reach x Impact x Confidence) / Effort. Show the arithmetic.
3. Rank initiatives by score. Mark any score that is 'fragile' — where changing one assumption would reorder the top 5.
4. Recommend a cut line based on capacity and flag 1-2 items where strategic value justifies overriding the raw score.

OUTPUT FORMAT: A ranked table (Rank | Initiative | R | I | C | E | RICE | Fragile?), then a 'Recommendation' paragraph and an 'Assumptions to validate' bullet list.

CONSTRAINTS: Be explicit when an input is a guess. Never present a low-confidence score as fact. Keep impact ratings consistent across items.

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

Recommended models

claudegpt-4ogemini

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 Product Management