Design your big bet’s smallest real-world test.
Before committing to a big idea, find the smallest test that would answer an important question about whether it can work.
Try it now
Copy the prompt into your AI tool of choice, then answer its questions as they come.
Paste it into any AI chat to start. For most people, this is all you need.
Everything on this page in one paste: the prompt plus the full plan, every step and what to check. Use it for longer moves, to plan ahead, to share with a colleague, or if your AI can't open links.
How it goes
What the AI will do
- Investigate your initiative and identify uncertainties whose answers could change the larger decision.
- Compare small real-world tests and recommend one based on what it teaches, time, cost, and effort.
- Write the full game plan and essential test materials, including how to interpret the result and when to stop and review it.
What to have ready
- Documents or a spoken account of the idea and the commitment you are considering.
- Missing context about important assumptions and practical constraints; the AI will also search accessible internal and public sources.
Where you come in
- Clarify judgments the available evidence cannot settle.
- Review the proposed test and correct its practical constraints. The activity designs the test; carrying it out requires a further request from you.
What you'll get
You’ll have a small test of a consequential uncertainty, a practical game plan, and criteria for deciding what its result would mean before making a bigger commitment.
You're done when
You have a small, practical test of a consequential uncertainty, with a complete game plan and a clear way to interpret the result before making a larger commitment.
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result. ### Start with the activity and the user's context Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear. Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them. ### Check the capabilities needed for this work Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit. When useful access is missing: - Explain what you cannot reach and how that material would help. - Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot. - If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response. - Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available. ### Ask focused questions and respect the answers Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful. Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements. ### Keep evidence and independent contributions distinct Distinguish evidence, inference, and missing information. Check your work against the source material. Use independent agents when your system actually supports delegation and independent investigation or review would improve the work: - Give each agent a bounded brief and the context appropriate to its role. - Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations. - Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately. ### Produce, check, and revise the result Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them. Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result. Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized. Help me design the fastest, cheapest, easiest real-world test of an important uncertainty in a big initiative. Do the analytical work and produce a thorough game plan. Ask one focused question at a time when you need my input. ### 1. Understand the initiative and the decision. Read the material I provide or ask me to describe the idea in my own words. Establish what we want to achieve, for whom, how the idea is supposed to work, what commitment we are considering, and what success would mean. Search connected documents, email, and chat for information about the initiative. Search the web for relevant public information where useful. Use what you find to fill gaps, then ask me about anything still missing that would materially change the test. ### 2. Identify what we most need to learn. Work backward from success. Identify the crucial assumptions: can it be built, at what cost, do users want it enough to act, can our organization support another product, or is a different uncertainty decisive? Separate what evidence already supports from what we are assuming. For each major uncertainty, explain how learning the answer could change the decision to proceed, change course, or stop. Check my judgment where the importance of an assumption depends on information you lack. ### 3. Compare a few small tests and choose one. Develop a few practical tests tied to those uncertainties. For each, state the question it answers, what we would actually do, what observable evidence it would produce, the time, cost, and effort required, and what it could not establish. Use available information to estimate requirements and label assumptions. Among tests that answer a consequential question, recommend the one that is fastest, cheapest, and easiest to run. Explain any tradeoff if no single test wins on all three. Avoid choosing a trivial question merely because it is easy to test. Match the evidence to the uncertainty: for example, a working technical experiment for buildability, observed customer behavior for demand, or a limited operational trial for support capacity. These are examples, not required categories. ### 4. Deliver a complete game plan. Specify the hypothesis, the test setup, participants or material needed and how to obtain them, tools or prototype required, responsible roles, sequence of actions, time and cost estimates, and the observations to record. Draft essential materials you can create now, such as a test script, interview questions, measurement sheet, or experiment brief. Keep them proportionate to the chosen test. - Define in advance what result would support proceeding, what would argue for revising or stopping, and what would remain inconclusive. Make thresholds explicit where meaningful and show the reasoning behind proposed numbers. - Identify confounders that could make the result misleading and the simplest way to address them. - Include a stopping point so the test stays small and a decision meeting or review immediately afterward. - Distinguish what this one test can establish from assumptions it leaves open. Present the recommended test and its game plan, ask for corrections to practical constraints, and revise accordingly. Do not launch the experiment or recruit participants unless I ask you to carry it out. These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
View full AI instructions
Design your big bet’s smallest real-world test.
What the AI will do
- Investigate your initiative and identify uncertainties whose answers could change the larger decision.
- Compare small real-world tests and recommend one based on what it teaches, time, cost, and effort.
- Write the full game plan and essential test materials, including how to interpret the result and when to stop and review it.
What you can provide
- Documents or a spoken account of the idea and the commitment you are considering.
- Missing context about important assumptions and practical constraints; the AI will also search accessible internal and public sources.
Where you'll take part
- Clarify judgments the available evidence cannot settle.
- Review the proposed test and correct its practical constraints. The activity designs the test; carrying it out requires a further request from you.
What you'll get
You’ll have a small test of a consequential uncertainty, a practical game plan, and criteria for deciding what its result would mean before making a bigger commitment.
Activity context
Before committing to a big idea, find the smallest test that would answer an important question about whether it can work.
For the user
Share documentation or a spoken download of the investment, product, project, or initiative, then paste the prompt below.
The AI will identify important uncertainties, compare small tests, and recommend one with a practical game plan. You’ll review what the test would teach you, how its result would affect the larger decision, and any practical constraints that need correcting.
Guidance for the AI
These are general instructions, not a description of this user's particular AI system, tools, access, or circumstances. Adapt the method to the user's goal and the capabilities you can actually use, while preserving the activity's essential sequence, review points, and intended result.
Start with the activity and the user's context
Read the complete activity and guide the user through it. Use the activity prompt yourself; the user does not need to paste it again. Keep the responsibilities of the user, the AI, and any colleague clear.
Begin with what the user has already supplied. Establish the intended result and resolve missing context through focused questions when needed. Work within the activity's stated scope, permissions, required confirmations, and stopping points, including any deliberate order for introducing information. Make progress with the available information and reasonable, clearly identified assumptions where the activity allows them.
Check the capabilities needed for this work
Inspect relevant available tools, connectors, and data. Use small, relevant, non-destructive checks to establish whether necessary access or a capability actually works. Naming a product does not establish access to it. Let this activity determine what needs checking; do not impose a universal preliminary questionnaire or a full system audit.
When useful access is missing:
- Explain what you cannot reach and how that material would help.
- Investigate practical setup, connection, export, or other access alternatives before asking the user to gather material or troubleshoot.
- If progress depends on access, request only the specific user action or permission needed to enable it or provide the material another way. Continue useful independent work while awaiting the response.
- Offer to walk the user through an export or upload. Welcome files, links, copied text, rough notes, or an interview as supported by your system and the activity, and use the best available route. If the missing access is optional, continue with what is available.
Ask focused questions and respect the answers
Ask questions only when necessary to complete the work well or satisfy the activity's required review points. Build on answers already supplied. Ask one question at a time, or a small group of closely related questions. Wait on work that depends on the answer, and continue useful work that does not. Explain unfamiliar language with examples where helpful.
Confirm answers or decisions you supply on the user's behalf before treating them as the user's final answers or decisions. This does not require separate approval of every sourced finding; follow the activity's specific review requirements.
Keep evidence and independent contributions distinct
Distinguish evidence, inference, and missing information. Check your work against the source material.
Use independent agents when your system actually supports delegation and independent investigation or review would improve the work:
- Give each agent a bounded brief and the context appropriate to its role.
- Keep discovery independent until synthesis where the activity requires it. Preserve any requirement for the user or colleagues to contribute before seeing other explanations.
- Follow the activity's stated fallback and any required confirmation when independent agents or fresh contexts are unavailable. Preserve reviewer isolation where required; describe shared-context or sequential passes accurately.
Produce, check, and revise the result
Do the substantive investigation and production. Carry the activity through to the most complete, usable result within its scope, rather than ending with a plan or handing the main work back to the user. When missing information does not prevent useful work, proceed with clearly identified assumptions where the activity permits them.
Check the result against the activity's completion criteria. At each substantive delivery, state what is complete and any material unfinished work, assumptions, helpful missing information, and remaining uncertainty. Explain how these affect what the user can use, and help the user revise the result.
Preserve the activity's stopping point. Do not turn a rehearsal, investigation, or test-design activity into execution that the user has not authorized.
Your AI prompt
Help me design the fastest, cheapest, easiest real-world test of an important uncertainty in a big initiative. Do the analytical work and produce a thorough game plan. Ask one focused question at a time when you need my input.
1. Understand the initiative and the decision.
Read the material I provide or ask me to describe the idea in my own words. Establish what we want to achieve, for whom, how the idea is supposed to work, what commitment we are considering, and what success would mean. Search connected documents, email, and chat for information about the initiative. Search the web for relevant public information where useful. Use what you find to fill gaps, then ask me about anything still missing that would materially change the test.
2. Identify what we most need to learn.
Work backward from success. Identify the crucial assumptions: can it be built, at what cost, do users want it enough to act, can our organization support another product, or is a different uncertainty decisive? Separate what evidence already supports from what we are assuming. For each major uncertainty, explain how learning the answer could change the decision to proceed, change course, or stop. Check my judgment where the importance of an assumption depends on information you lack.
3. Compare a few small tests and choose one.
Develop a few practical tests tied to those uncertainties. For each, state the question it answers, what we would actually do, what observable evidence it would produce, the time, cost, and effort required, and what it could not establish. Use available information to estimate requirements and label assumptions.
Among tests that answer a consequential question, recommend the one that is fastest, cheapest, and easiest to run. Explain any tradeoff if no single test wins on all three. Avoid choosing a trivial question merely because it is easy to test. Match the evidence to the uncertainty: for example, a working technical experiment for buildability, observed customer behavior for demand, or a limited operational trial for support capacity. These are examples, not required categories.
4. Deliver a complete game plan.
Specify the hypothesis, the test setup, participants or material needed and how to obtain them, tools or prototype required, responsible roles, sequence of actions, time and cost estimates, and the observations to record.
Draft essential materials you can create now, such as a test script, interview questions, measurement sheet, or experiment brief. Keep them proportionate to the chosen test.
-
Define in advance what result would support proceeding, what would argue for revising or stopping, and what would remain inconclusive. Make thresholds explicit where meaningful and show the reasoning behind proposed numbers.
-
Identify confounders that could make the result misleading and the simplest way to address them.
-
Include a stopping point so the test stays small and a decision meeting or review immediately afterward.
-
Distinguish what this one test can establish from assumptions it leaves open.
Present the recommended test and its game plan, ask for corrections to practical constraints, and revise accordingly. Do not launch the experiment or recruit participants unless I ask you to carry it out.
Done when
You have a small, practical test of a consequential uncertainty, with a complete game plan and a clear way to interpret the result before making a larger commitment.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.
These instructions were written in September 2026 using the frontier models available at the time. You may now have better tools or models, or restrictions that make some tasks harder. Your AI should adapt to the tools and access you actually have and find the best available way to help. Everything here is a starting suggestion for you and your AI, not a proven best practice for every setup. Feel free to rewrite any of it to better meet your needs.