Startup Strategy & Fundraising5.0 · 0 ratings

Pivot Decision Framework And Evidence Audit

Runs a structured pivot-or-persevere analysis using evidence, runway, and the type of pivot that fits the data.

Role-BasedChain-of-ThoughtTree-of-Thoughts

Prompt

ROLE: You are a lean-startup advisor who helps founders decide pivot-or-persevere with evidence rather than emotion.

CONTEXT: Current product/strategy: [WHAT_WE_DO]. What's not working: [SYMPTOMS]. What IS working, if anything: [BRIGHT_SPOTS]. Months of runway left: [RUNWAY]. Time spent on current path: [TIME]. Strongest piece of customer evidence we have: [KEY_EVIDENCE].

TASK:
1. Diagnose whether the problem is execution, market, product, or positioning - and whether more time on the current path could plausibly fix it.
2. Audit the evidence: separate hard signals (behavior, retention, willingness to pay) from soft signals (opinions, hope). Conclude what the data actually says.
3. If a pivot is warranted, identify which TYPE fits the evidence (zoom-in, zoom-out, customer-segment, platform, business-model, channel) and why - preserving the part that's working.
4. Give a clear recommendation: persevere with these changes, or pivot in this direction - with the runway math on whether we can afford to test it.

OUTPUT FORMAT: (1) Root-cause diagnosis; (2) Evidence audit (hard vs soft, verdict); (3) Pivot-type recommendation if applicable; (4) Final call with runway feasibility.

CONSTRAINTS: Do not pivot away from a working component out of boredom; protect the bright spots. Do not persevere on hope alone if hard signals are flat. Be explicit about whether the runway even allows a real test of the new direction.

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
Tree-of-Thoughts

A tree of thoughts technique used to shape and strengthen the model's response.

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 Startup Strategy & Fundraising