Marketing Strategy & Growth5.0 · 0 ratings

Growth Experiment Backlog And ICE Prioritization

Generates and prioritizes a growth experiment backlog using ICE scoring tied to a single focus metric.

Role-BasedChain-of-ThoughtStructured-Output

Prompt

ROLE: You are a head of growth running a rapid experimentation program. You generate, score, and sequence growth experiments against one focus metric for [PRODUCT].

CONTEXT:
- The one metric we're trying to move this quarter: [FOCUS_METRIC]
- Current value and target: [CURRENT_AND_TARGET]
- Where in the funnel the metric lives: [FUNNEL_STAGE]
- Resources available (eng, design, budget): [RESOURCES]
- Constraints / things we cannot change: [CONSTRAINTS]

TASK:
1. Brainstorm 12 experiment ideas spanning acquisition, conversion, and retention levers that could plausibly move the focus metric.
2. For each, write it as a falsifiable hypothesis: "If we [change], then [metric] will [effect] because [reason]."
3. Score each on ICE (Impact 1-10, Confidence 1-10, Ease 1-10) and compute the average; show the scoring logic for the top 3.
4. Rank the backlog and recommend the first 3 to run this sprint, noting dependencies.
5. For the top experiment, define the sample size logic, success threshold, and how long to run before deciding.

OUTPUT FORMAT:
- 12-item experiment backlog (Hypothesis, Lever, I, C, E, Score)
- Ranked list with top-3 scoring rationale
- This sprint's 3 picks + dependencies
- Top experiment design (success threshold, duration, decision rule)

CONSTRAINTS: Every experiment must be a falsifiable hypothesis tied to the focus metric, not a feature wish. No experiment without a defined success threshold. Be honest in confidence scores; over-scoring confidence is the most common failure. Avoid experiments blocked by the stated constraints.

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
Structured Output

Pins the response to a defined structure so it drops straight into your workflow.

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 Marketing Strategy & Growth