Test an idea before spending time and effort on it
Prepare evidence and alternatives, ask for criticism that tests assumptions, then run a small experiment.
Let's understand the idea
If you present a service or project idea enthusiastically, the assistant may encourage it simply because you sound excited. Ask it to understand the problem, evidence, and constraints, then give the strongest reasons for and against it and the alternatives. Criticism doesn't mean automatic rejection.
Tie each observation to information or an assumption, and identify what needs research or testing. Instead of a major decision based on a generated estimate, choose a small test and a criterion for continuing or adjusting. The assistant organizes thinking. The decision stays grounded in your information and review.
Tools for this workflow
Choose from what's available to you. You can use these prompts with several tools. What they can carry out depends on supported features and files.
See tool details and uses in the Tools library →Examples to expand the idea
A doctor considers starting online consultations. Instead of asking “Is my idea good?”, they request the strongest reasons it could fail and the alternatives. They decide to test it for a month, two hours a week, before paying for a platform.
Compare two work options
Write the constraints, criteria, evidence, and time available. Avoid a combined score that gives incomplete information false precision.
Critique a presentation or plan
Request objections from the audience's perspective, with evidence and a suggestion addressing the cause.
Review a business assumption
Separate documented demand from impressions based on a few comments. Don't project profits without data.
Steps from start to delivery
Open any step by its heading. Each explains what to do, why, and what to check before continuing.
1Write the decision and constraintsA clear decision you can review.Details
Without a specific decision, criticism becomes generic.
What should I do?
- Define the idea, alternatives, resources, and duration.
- Write a success criterion or stopping condition.
2Gather current evidenceA list of evidence and assumptions.Details
Mark assumptions clearly.
What should I do?
- Gather requests, data, or original links.
- Write what you know, what you expect, and what you don't yet know.
3Ask for support and criticismCriticism with reasons instead of token opposition.Details
The goal is to uncover a significant weakness.
What should I do?
- Ask for the strongest supporting argument and strongest objection.
- Rank concerns by impact and what can be tested.
4Design a small testA test tied to the decision.Details
A test reduces a specific uncertainty.
What should I do?
- Choose the most important assumption you can test.
- Define inputs, duration, metric, and the decision after the result.
5Write and review a memoA justified decision or a clear unanswered question preventing one.Details
The memo explains what you chose and why.
What should I do?
- Summarize the decision, evidence, alternatives, and limits of confidence.
- Define what would change your mind and when to review.
Prompts for your work
Open a prompt and fill in your details. Empty fields remain visible so you don't forget them.
Test my idea with evidenceOpen it to copy or tailor the prompt
Prepare the listed inputs and start with the prompt in an available tool. Open the output and review it against your work.
Copy the prompt as it is, or tailor it with your details first.
Tailor the prompt to your workOptional: add your details and the prompt adjusts itself
View full prompt
Why is the prompt written this way?
The research purpose and chosen sources make the result useful, rather than report length or link count.
Prepare the decision memoOpen it to copy or tailor the prompt
Copy the prompt as it is, or tailor it with your details first.
Tailor the prompt to your workOptional: add your details and the prompt adjusts itself
View full prompt
Did the result serve your original goal?
Return to the inputs and sources, and open the output where you'll use it. Check these points before relying on it.
- Is evidence separate from assumptions?
- Were alternatives considered fairly?
- Will the test actually change the decision?
If there's a problem, name the unsuitable part, show an example, and request a specific edit.