Resource
Executive Summary Prompt
Summary, Why It Matters, What Happens Next — the executive summary contract for readers who will never open the source.
Product Validation Decision Framework Prompt
Weigh the evidence against the target and decide — a synthesis that renders a hit / partial / miss verdict and turns it into an iterate, pivot, or scale recommendation, with the reasoning that holds it up.
Overview
Collected evidence decides nothing until someone weighs it against the bar and commits to a call. This prompt synthesizes the categorized behavior and feedback signals against the success metric, renders a clear hit / partial / miss verdict, and converts that into the decision that matters — iterate, pivot, or scale — with the reasoning and the open risks that could change it. It keeps the recommendation tied to the supplied evidence, so the call is auditable rather than a gut read dressed up in data.
How to use this resource
-
Bring the metric in with the evidence
Supply the success metric and target alongside the categorized signals — the verdict is meaningless without the bar it is measured against.
-
Force one verdict and one decision
Hold it to a single hit/partial/miss and a single iterate/pivot/scale — a hedged verdict is how teams avoid deciding.
-
Read the Open Risks before acting
Thin evidence or an unaddressed confounder in that section means the call is provisional — treat it as such.
Why This Works
- Weighing signals against an explicit target keeps the verdict evidence-driven, not vibe-driven
- Forcing exactly one verdict and one decision stops the analysis from dodging the call
- The Open Risks section keeps a confident recommendation honest about what could change it
Best for
- Deciding what to do after a product-validation measurement
- Making the iterate/pivot/scale call defensible to stakeholders
- Separating the verdict from the wishful reading of it
Not for
- Categorizing the raw feedback into signals — that is the Data Classification Prompt
- Planning what to measure — that is the Product Validation Measurement Plan Prompt
- Verifying code or AI-output correctness — that is Testing and Agent Evaluation
Use cases
- Turning categorized launch evidence into a hit/partial/miss verdict
- Converting a validation result into an iterate, pivot, or scale call
- Keeping a go/no-go recommendation tied to the evidence behind it
FAQ
What inputs does the product validation decision framework prompt need before it can give a verdict?
It needs the success metric — its definition and numeric target — plus your already-categorized behavior and feedback signals. The prompt works only from what you supply and won't invent evidence or pull outside benchmarks, so a verdict without the metric and target is meaningless. Categorize the raw feedback into signals first, as a separate step; this framework synthesizes those signals against the bar, it doesn't gather them.
What does the product validation decision framework prompt output look like — what sections does it produce?
The output is Markdown with five fixed sections in order: Signal vs Target (each decisive signal beside the number it must hit), Verdict, Decision, Reasoning, and Open Risks. Each section runs two to five sentences and preserves your numbers, thresholds, and dates exactly as given. There's no preamble or closing commentary — just the synthesis, so you can drop it straight into a decision doc.
Why does the framework force exactly one hit/partial/miss verdict and one iterate/pivot/scale decision?
Forcing one verdict — hit, partial, or miss — and one decision — iterate, pivot, or scale — keeps the review from hiding behind a hedged "it's promising" that never commits. It also binds the two: a miss won't recommend scale and a hit won't recommend pivot unless the evidence explicitly justifies it, so the decision has to follow from the verdict rather than from what you were hoping for.
How do I use the Open Risks section — does a hit verdict mean it is safe to scale?
Read Open Risks before acting: it names the thin evidence, confounders, and unresolved questions that could flip the call. A hit verdict is a structured read of the supplied signals against your target — not a guarantee that scaling is safe — and a populated Open Risks section means the recommendation is provisional. You own the business decision; the prompt structures it, it doesn't make it for you.
More resources from Structured Summary Prompt
Resource
Structured Summary Prompt — the Anatomy
The blocks a reliable summary prompt needs: source guidance, a fixed section skeleton, length budgets, fidelity rules, and quote handling.
Resource
Stop AI Summaries from Making Things Up
The fidelity ladder: Balanced, High, Strict — and the six-rule battery that keeps a summary inside its source.
Resources that pair well
Resource
Markdown Output Prompt — Lock the Document Structure
The contract that stops AI documents from restructuring themselves: a pinned section skeleton, forced tables, and strict consistency rules.
Resource
Extract Data From Text with AI
Free text in, named fields out. The extraction prompt pattern that turns any unstructured text into consistent, parseable records.
Resource
Fix a Vague Prompt
'Make it good', 'be detailed', 'keep it interesting' — vague prompts get vague output. The fix is mechanical: replace every fuzzy word with a checkable instruction.
Related tools
Tool
Structured Summary Prompt
Build summary prompts with fixed sections, length caps, and no-invention fidelity rules.
Workflows that use this resource
Workflow
AI Product Validation Workflow
Find out whether the thing you shipped actually worked — define the success metric, plan the measurement, classify the real evidence, then render a verdict and an iterate / pivot / scale decision.
Guides for this resource
Guide
How to Make AI Say What Would Change Its Answer
AI hands back a clean "yes" with no sign of what it's resting on or what would flip it. Here's how to make the model show its load-bearing assumptions and the specific changes that would flip, narrow, or defer its recommendation — so you see how fragile the answer really is.
Guide
Tell Reversible From Irreversible Decisions With AI
Before asking AI which option to pick, have it classify the decision's reversal cost — reversible, hard-to-reverse, or irreversible — so you move fast on the easy calls and slow down on the one-way doors. A candidate reading you confirm, not a verdict it issues.
Guide
Build a Decision Matrix With AI
Ask AI "which option is best?" and it returns a one-line pick with the criteria hidden and unknowns scored like facts. Here's how to build a decision matrix with AI: options against weighted criteria you approve, a reason per score, unknowns kept separate, and a sensitivity check.
Guide
Decide When to Defer a Decision With AI
You ask AI which option to pick and it hands back a confident call — even when the real answer is that the decision isn't ready to make yet. Here's how to make AI weigh cost of delay against cost of being wrong and choose decide-now, a reversible step, or a dated deferral.