Pitch with a working prototype. Not a proposal.
Let the people approving your idea experience what you mean. AI will help turn rough thoughts into a prototype or a product website that makes the proposal tangible.
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
- Turn your rough idea into a demonstration for the people whose approval you need.
- Find useful examples and build a working prototype, interactive demo, or product or service website with the available tools.
- Test the experience and revise it with your feedback so it makes the idea tangible.
What to have ready
- Whatever you have: notes, sketches, screenshots, slides, documents, or a spoken download.
- Missing context about the audience and what the demonstration needs to show; references are helpful when you have them.
Where you come in
- Answer questions that affect what the AI builds.
- Try the result as your audience would, explain what is missing or unconvincing, and review revisions. Approve any public publishing.
What you'll get
You’ll have a usable demonstration to show decision-makers; if this AI cannot build it, you’ll receive a complete handoff and the specific action needed to continue in an environment that can.
You're done when
You have a usable prototype, interactive demo, or product or service website that you can show to the people deciding whether to approve your idea.
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 build something I can show when pitching a new idea for approval. Start with whatever I provide: writing, visuals, rough notes, or a transcription of my thoughts. Ask one focused question at a time when you need my input. ### 1. Understand the idea and the audience. First extract what the supplied material and accessible project context establish about what I am building or pitching, who will approve it, why it is a good idea, who it affects, how it helps them, what happens if it does not exist, and its key elements. If the idea itself remains unclear, ask me to describe it. Interview me only for consequential gaps that would change what you make; do not re-ask questions the material already answers. Summarize what the demonstration needs to show this audience, distinguish evidence from assumptions, and resolve uncertainty that would materially change the build. ### 2. Find useful work to build on. Look through supplied and accessible material for existing work, examples, or comparable products. Ask for references I may have when they would help resolve a gap or improve the demonstration; do not make supplying them a prerequisite when you can proceed. Research public examples if that would help. Explain which elements fit this idea and its audience, and use them to inform the demonstration. ### 3. Choose the demonstration and how to make it. Inspect your available tools. - For an app or other digital tool, assess whether a working prototype or an interactive demo with simulated information is the best way to show the experience. A demo is often enough to make the idea tangible. If the core tool is easy to build, build it. Make simulated information recognizable as sample data. - For a physical product or service, create a website that shows what it is, why it is great, who it serves, and how it changes their life. Use the idea's distinctive details and suitable visuals to make the value concrete. Describe the experience you will demonstrate, the essential features or pages, the information and visuals needed, and the steps you will take to build it. Choose a compelling result you can produce fairly quickly. Resolve essential missing inputs before building. If this chat cannot create the needed artifact, investigate the simplest permitted route to an AI environment that can. Prepare a complete handoff describing the idea, audience, chosen demonstration, source material, and build steps. Explain the specific action I need to take to continue there, and make clear that the prototype itself has not yet been built. ### 4. Build and check the result. Carry out the build steps using the capabilities available. Build the core experience first, then add the content and visuals needed to make its value clear. Test the path the audience will follow, including the main interactions, and fix failures before delivery. Check the result against the purpose and audience established in the interview. ### 5. Give me something I can show. Provide an accessible preview or file. Explain what is functional and what is simulated. Invite me to try it as the audience would and ask what is missing, unconvincing, or needs changing before the pitch. Wait for my feedback, make those revisions, and recheck the affected parts. Repeat the trial and revision as needed until it demonstrates the idea I want approved, or explain the specific remaining blocker. Ask before publishing it publicly. 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
Pitch with a working prototype. Not a proposal.
What the AI will do
- Turn your rough idea into a demonstration for the people whose approval you need.
- Find useful examples and build a working prototype, interactive demo, or product or service website with the available tools.
- Test the experience and revise it with your feedback so it makes the idea tangible.
What you can provide
- Whatever you have: notes, sketches, screenshots, slides, documents, or a spoken download.
- Missing context about the audience and what the demonstration needs to show; references are helpful when you have them.
Where you'll take part
- Answer questions that affect what the AI builds.
- Try the result as your audience would, explain what is missing or unconvincing, and review revisions. Approve any public publishing.
What you'll get
You’ll have a usable demonstration to show decision-makers; if this AI cannot build it, you’ll receive a complete handoff and the specific action needed to continue in an environment that can.
Activity context
Let the people approving your idea experience what you mean. AI will help turn rough thoughts into a prototype or a product website that makes the proposal tangible.
For the user
Share whatever you have: notes, documents, sketches, screenshots, slides, or a spoken download of your thoughts. Paste this prompt. The AI will use what you have supplied, ask about consequential gaps, and build something you can show. You will try the prototype or website as your audience would, tell it what is missing or unconvincing, and have it revise the artifact until it demonstrates the idea you want approved. It will ask before publishing publicly.
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 build something I can show when pitching a new idea for approval. Start with whatever I provide: writing, visuals, rough notes, or a transcription of my thoughts. Ask one focused question at a time when you need my input.
1. Understand the idea and the audience.
First extract what the supplied material and accessible project context establish about what I am building or pitching, who will approve it, why it is a good idea, who it affects, how it helps them, what happens if it does not exist, and its key elements. If the idea itself remains unclear, ask me to describe it. Interview me only for consequential gaps that would change what you make; do not re-ask questions the material already answers. Summarize what the demonstration needs to show this audience, distinguish evidence from assumptions, and resolve uncertainty that would materially change the build.
2. Find useful work to build on.
Look through supplied and accessible material for existing work, examples, or comparable products. Ask for references I may have when they would help resolve a gap or improve the demonstration; do not make supplying them a prerequisite when you can proceed. Research public examples if that would help. Explain which elements fit this idea and its audience, and use them to inform the demonstration.
3. Choose the demonstration and how to make it.
Inspect your available tools.
-
For an app or other digital tool, assess whether a working prototype or an interactive demo with simulated information is the best way to show the experience. A demo is often enough to make the idea tangible. If the core tool is easy to build, build it. Make simulated information recognizable as sample data.
-
For a physical product or service, create a website that shows what it is, why it is great, who it serves, and how it changes their life. Use the idea's distinctive details and suitable visuals to make the value concrete.
Describe the experience you will demonstrate, the essential features or pages, the information and visuals needed, and the steps you will take to build it. Choose a compelling result you can produce fairly quickly. Resolve essential missing inputs before building.
If this chat cannot create the needed artifact, investigate the simplest permitted route to an AI environment that can. Prepare a complete handoff describing the idea, audience, chosen demonstration, source material, and build steps. Explain the specific action I need to take to continue there, and make clear that the prototype itself has not yet been built.
4. Build and check the result.
Carry out the build steps using the capabilities available. Build the core experience first, then add the content and visuals needed to make its value clear. Test the path the audience will follow, including the main interactions, and fix failures before delivery. Check the result against the purpose and audience established in the interview.
5. Give me something I can show.
Provide an accessible preview or file. Explain what is functional and what is simulated. Invite me to try it as the audience would and ask what is missing, unconvincing, or needs changing before the pitch.
Wait for my feedback, make those revisions, and recheck the affected parts. Repeat the trial and revision as needed until it demonstrates the idea I want approved, or explain the specific remaining blocker. Ask before publishing it publicly.
Done when
You have a usable prototype, interactive demo, or product or service website that you can show to the people deciding whether to approve your idea.
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.