#business prompts and AI conversations · PitHub

Theo Vega@theovega·2w ago

A smaller way to tackle a pricing page review

A compact prompt and the response it produced. Replace the bracketed parts with your own details.

Theo Vega

For a pricing page review, should I build a complete plan first or test one small slice? I have limited time and I do not want throwaway work.

ChatGPTgpt-5

Test one slice, but choose a slice that crosses the riskiest part of the problem. A tiny easy demo will only prove the easy part. Use this decision rule: - If reversing the choice is cheap, try it. - If the choice locks in data, money, or other people’s time, write the full decision first. - If uncertainty is concentrated in one step, test that step before planning around it. For a pricing page review, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages

3404k

Asha Morgan@ashamorgan·2w ago

The checklist I use for a tiny business forecast

I wanted help with a tiny business forecast without pretending the model knew facts I had not provided.

Asha Morgan

I am stuck on a tiny business forecast. I need to build a transparent cash forecast with assumptions that can be updated monthly, but my current attempt is getting vague and too big. What would you check first?

Claudeclaude-opus-4.5

First, shrink the decision. Do not solve the whole subject at once. 1. Start from observed behavior. 2. Write the riskiest assumption down. 3. Choose a measurable next test. Write down the result you need by the end of this session. Then choose one input you trust and make a first pass that can be checked. If that pass fails, you will know which assumption to revisit instead of starting over.

Show all 3 messages

3302.4k

Mateo Patel@mateopatel·3w ago

I needed a usable answer on a pre-mortem for launch day

The useful bit was asking for trade-offs and a smallest test before committing to a full plan.

Mateo Patel

I am stuck on a pre-mortem for launch day. I need to imagine a launch failed and turn likely causes into checks and owners, but my current attempt is getting vague and too big. What would you check first?

Geminigemini-2.5-pro

First, shrink the decision. Do not solve the whole subject at once. 1. Start from observed behavior. 2. Write the riskiest assumption down. 3. Choose a measurable next test. Write down the result you need by the end of this session. Then choose one input you trust and make a first pass that can be checked. If that pass fails, you will know which assumption to revisit instead of starting over.

Show all 3 messages

3402.4k

Noor Diaz@noordiaz·4w ago

My notes from fixing customer interviews without leading

Not magic wording, just enough context and a clear definition of done. Easy to adapt.

Noor Diaz

I am stuck on customer interviews without leading. I need to write interview questions that uncover behavior instead of collecting compliments, but my current attempt is getting vague and too big. What would you check first?

ChatGPTgpt-5

First, shrink the decision. Do not solve the whole subject at once. 1. Start from observed behavior. 2. Write the riskiest assumption down. 3. Choose a measurable next test. Write down the result you need by the end of this session. Then choose one input you trust and make a first pass that can be checked. If that pass fails, you will know which assumption to revisit instead of starting over.

Show all 3 messages

3303.9k

Mateo Patel@mateopatel·1mo ago

a pre-mortem for launch day, minus the vague advice

This started as a messy question about a pre-mortem for launch day. The follow-up made the answer practical.

Mateo Patel

Give me a short checklist for a pre-mortem for launch day. I want something I can run before I call the work done.

Geminigemini-2.5-pro

Use this pass: - [ ] The goal is one sentence and names the user or decision - [ ] Inputs are current, relevant, and traceable - [ ] Assumptions are visible - [ ] Start from observed behavior - [ ] Write the riskiest assumption down - [ ] Choose a measurable next test - [ ] One failure case has been tested - [ ] The next owner and next action are clear If you cannot check an item, mark it unknown. Do not quietly treat unknown as done.

Show all 3 messages

3303.8k

Asha Morgan@ashamorgan·4w ago

a tiny business forecast: the version with actual constraints

Not magic wording, just enough context and a clear definition of done. Easy to adapt.

Asha Morgan

Give me a short checklist for a tiny business forecast. I want something I can run before I call the work done.

Claudeclaude-opus-4.5

Use this pass: - [ ] The goal is one sentence and names the user or decision - [ ] Inputs are current, relevant, and traceable - [ ] Assumptions are visible - [ ] Start from observed behavior - [ ] Write the riskiest assumption down - [ ] Choose a measurable next test - [ ] One failure case has been tested - [ ] The next owner and next action are clear If you cannot check an item, mark it unknown. Do not quietly treat unknown as done.

Show all 3 messages

3402.3k

Theo Vega@theovega·1mo ago

The checklist I use for a pricing page review

This started as a messy question about a pricing page review. The follow-up made the answer practical.

Theo Vega

I am stuck on a pricing page review. I need to find where pricing language creates uncertainty and propose clearer choices, but my current attempt is getting vague and too big. What would you check first?

Claudeclaude-opus-4.5

First, shrink the decision. Do not solve the whole subject at once. 1. Start from observed behavior. 2. Write the riskiest assumption down. 3. Choose a measurable next test. Write down the result you need by the end of this session. Then choose one input you trust and make a first pass that can be checked. If that pass fails, you will know which assumption to revisit instead of starting over.

Show all 3 messages

3402.7k

Noor Diaz@noordiaz·1mo ago

A blunt review of my approach to customer interviews without leading

I kept the useful constraints and dropped the role-play. It works better when the missing details are stated plainly.

Noor Diaz

Give me a short checklist for customer interviews without leading. I want something I can run before I call the work done.

ChatGPTgpt-5

Use this pass: - [ ] The goal is one sentence and names the user or decision - [ ] Inputs are current, relevant, and traceable - [ ] Assumptions are visible - [ ] Start from observed behavior - [ ] Write the riskiest assumption down - [ ] Choose a measurable next test - [ ] One failure case has been tested - [ ] The next owner and next action are clear If you cannot check an item, mark it unknown. Do not quietly treat unknown as done.

Show all 3 messages

3403.9k

Asha Morgan@ashamorgan·2mo ago

I asked Gemini for a second opinion on a tiny business forecast

The first answers were broad enough to be useless. This version asks for assumptions, evidence, and a next step.

Asha Morgan

Be blunt about my plan for a tiny business forecast. I am going to collect everything, ask for a polished answer, and fix details later. What is likely to go wrong?

Geminigemini-2.5-pro

Three things. - “Everything” has no boundary, so weak inputs and strong inputs will be treated alike. - A polished answer can hide missing evidence. Ask for gaps and assumptions before prose. - “Fix details later” means there is no acceptance test now. A safer sequence is: define the decision, choose the minimum trusted inputs, make an ugly first pass, check it, then polish. For this task, write the riskiest assumption down.

Show all 3 messages

3403.8k

Caleb Bose@calebbose·3w ago

A blunt review of my approach to a competitor brief

The useful bit was asking for trade-offs and a smallest test before committing to a full plan.

Caleb Bose

Give me a short checklist for a competitor brief. I want something I can run before I call the work done.

ChatGPTgpt-5

Use this pass: - [ ] The goal is one sentence and names the user or decision - [ ] Inputs are current, relevant, and traceable - [ ] Assumptions are visible - [ ] Start from observed behavior - [ ] Write the riskiest assumption down - [ ] Choose a measurable next test - [ ] One failure case has been tested - [ ] The next owner and next action are clear If you cannot check an item, mark it unknown. Do not quietly treat unknown as done.

Show all 3 messages

330849

Mateo Patel@mateopatel·2mo ago

ChatGPT was overcomplicating a pre-mortem for launch day, so I reset the question

A compact prompt and the response it produced. Replace the bracketed parts with your own details.

Mateo Patel

Be blunt about my plan for a pre-mortem for launch day. I am going to collect everything, ask for a polished answer, and fix details later. What is likely to go wrong?

ChatGPTgpt-5

Three things. - “Everything” has no boundary, so weak inputs and strong inputs will be treated alike. - A polished answer can hide missing evidence. Ask for gaps and assumptions before prose. - “Fix details later” means there is no acceptance test now. A safer sequence is: define the decision, choose the minimum trusted inputs, make an ugly first pass, check it, then polish. For this task, write the riskiest assumption down.

Show all 3 messages

3303.8k

Caleb Bose@calebbose·1mo ago

How I ask for help with a competitor brief

Sharing the wording because it gave me something I could check instead of a confident wall of text.

Caleb Bose

Be blunt about my plan for a competitor brief. I am going to collect everything, ask for a polished answer, and fix details later. What is likely to go wrong?

Claudeclaude-opus-4.5

Three things. - “Everything” has no boundary, so weak inputs and strong inputs will be treated alike. - A polished answer can hide missing evidence. Ask for gaps and assumptions before prose. - “Fix details later” means there is no acceptance test now. A safer sequence is: define the decision, choose the minimum trusted inputs, make an ugly first pass, check it, then polish. For this task, write the riskiest assumption down.

Show all 3 messages

3302.3k

Caleb Bose@calebbose·2mo ago

What finally made a competitor brief click for me

The useful bit was asking for trade-offs and a smallest test before committing to a full plan.

Caleb Bose

Help me compare competitors by customer, workflow, pricing, and evidence without copying marketing claims. Context: - Goal: [what a good result lets me do] - Current situation: [paste notes, draft, data, or constraints] - Audience: [who will use the result] - Deadline or limit: [time, budget, tools, length] Before answering, ask up to three questions only if the answers would materially change you

Geminigemini-2.5-pro

This is usable as written. The important parts are the definition of done, the instruction to expose assumptions, and the request for a smallest test. For a competitor brief, I would start with these checks: - Start from observed behavior - Write the riskiest assumption down - Choose a measurable next test If you share real material, remove anything private first and replace bracketed fields with concrete details.

Show all 3 messages

3303.7k

Caleb Bose@calebbose·3mo ago

Gemini found the hole in my a competitor brief plan

This started as a messy question about a competitor brief. The follow-up made the answer practical.

Caleb Bose

For a competitor brief, should I build a complete plan first or test one small slice? I have limited time and I do not want throwaway work.

Geminigemini-2.5-pro

Test one slice, but choose a slice that crosses the riskiest part of the problem. A tiny easy demo will only prove the easy part. Use this decision rule: - If reversing the choice is cheap, try it. - If the choice locks in data, money, or other people’s time, write the full decision first. - If uncertainty is concentrated in one step, test that step before planning around it. For a competitor brief, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages

3403.7k

Theo Vega@theovega·3mo ago

The a pricing page review prompt I actually kept

Sharing the wording because it gave me something I could check instead of a confident wall of text.

Theo Vega

Help me find where pricing language creates uncertainty and propose clearer choices. Context: - Goal: [what a good result lets me do] - Current situation: [paste notes, draft, data, or constraints] - Audience: [who will use the result] - Deadline or limit: [time, budget, tools, length] Before answering, ask up to three questions only if the answers would materially change your recommendation. Othe

ChatGPTgpt-5

This is usable as written. The important parts are the definition of done, the instruction to expose assumptions, and the request for a smallest test. For a pricing page review, I would start with these checks: - Start from observed behavior - Write the riskiest assumption down - Choose a measurable next test If you share real material, remove anything private first and replace bracketed fields with concrete details.

Show all 3 messages

3304k

Theo Vega@theovega·2mo ago

I asked Gemini for a second opinion on a pricing page review

The useful bit was asking for trade-offs and a smallest test before committing to a full plan.

Theo Vega

Be blunt about my plan for a pricing page review. I am going to collect everything, ask for a polished answer, and fix details later. What is likely to go wrong?

Geminigemini-2.5-pro

Three things. - “Everything” has no boundary, so weak inputs and strong inputs will be treated alike. - A polished answer can hide missing evidence. Ask for gaps and assumptions before prose. - “Fix details later” means there is no acceptance test now. A safer sequence is: define the decision, choose the minimum trusted inputs, make an ugly first pass, check it, then polish. For this task, write the riskiest assumption down.

Show all 3 messages

3302.6k

Theo Vega@theovega·2mo ago

a pricing page review: the version with actual constraints

Sharing the wording because it gave me something I could check instead of a confident wall of text.

Theo Vega

Give me a short checklist for a pricing page review. I want something I can run before I call the work done.

Claudeclaude-opus-4.5

Use this pass: - [ ] The goal is one sentence and names the user or decision - [ ] Inputs are current, relevant, and traceable - [ ] Assumptions are visible - [ ] Start from observed behavior - [ ] Write the riskiest assumption down - [ ] Choose a measurable next test - [ ] One failure case has been tested - [ ] The next owner and next action are clear If you cannot check an item, mark it unknown. Do not quietly treat unknown as done.

Show all 3 messages

3301.2k

Noor Diaz@noordiaz·3mo ago

What finally made customer interviews without leading click for me

I kept the useful constraints and dropped the role-play. It works better when the missing details are stated plainly.

Noor Diaz

Help me write interview questions that uncover behavior instead of collecting compliments. Context: - Goal: [what a good result lets me do] - Current situation: [paste notes, draft, data, or constraints] - Audience: [who will use the result] - Deadline or limit: [time, budget, tools, length] Before answering, ask up to three questions only if the answers would materially change your recommendation

Geminigemini-2.5-pro

This is usable as written. The important parts are the definition of done, the instruction to expose assumptions, and the request for a smallest test. For customer interviews without leading, I would start with these checks: - Start from observed behavior - Write the riskiest assumption down - Choose a measurable next test If you share real material, remove anything private first and replace bracketed fields with concrete details.

Show all 3 messages

3402.6k

Mateo Patel@mateopatel·3mo ago

I stopped guessing about a pre-mortem for launch day

Sharing the wording because it gave me something I could check instead of a confident wall of text.

Mateo Patel

For a pre-mortem for launch day, should I build a complete plan first or test one small slice? I have limited time and I do not want throwaway work.

Claudeclaude-opus-4.5

Test one slice, but choose a slice that crosses the riskiest part of the problem. A tiny easy demo will only prove the easy part. Use this decision rule: - If reversing the choice is cheap, try it. - If the choice locks in data, money, or other people’s time, write the full decision first. - If uncertainty is concentrated in one step, test that step before planning around it. For a pre-mortem for launch day, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages

3402.5k

Noor Diaz@noordiaz·3mo ago

Gemini found the hole in my customer interviews without leading plan

The first answers were broad enough to be useless. This version asks for assumptions, evidence, and a next step.

Noor Diaz

For customer interviews without leading, should I build a complete plan first or test one small slice? I have limited time and I do not want throwaway work.

Geminigemini-2.5-pro

Test one slice, but choose a slice that crosses the riskiest part of the problem. A tiny easy demo will only prove the easy part. Use this decision rule: - If reversing the choice is cheap, try it. - If the choice locks in data, money, or other people’s time, write the full decision first. - If uncertainty is concentrated in one step, test that step before planning around it. For customer interviews without leading, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages

3302.5k

Noor Diaz@noordiaz·2mo ago

How I ask for help with customer interviews without leading

I wanted help with customer interviews without leading without pretending the model knew facts I had not provided.

Noor Diaz

Be blunt about my plan for customer interviews without leading. I am going to collect everything, ask for a polished answer, and fix details later. What is likely to go wrong?

Claudeclaude-opus-4.5

Three things. - “Everything” has no boundary, so weak inputs and strong inputs will be treated alike. - A polished answer can hide missing evidence. Ask for gaps and assumptions before prose. - “Fix details later” means there is no acceptance test now. A safer sequence is: define the decision, choose the minimum trusted inputs, make an ugly first pass, check it, then polish. For this task, write the riskiest assumption down.

Show all 3 messages

3401.1k

Asha Morgan@ashamorgan·2mo ago

Forked from@devali/I asked Gemini for a second opinion on a first draft that sounds corporate

The a tiny business forecast prompt I actually kept

Not magic wording, just enough context and a clear definition of done. Easy to adapt.

Asha Morgan

Help me build a transparent cash forecast with assumptions that can be updated monthly. Context: - Goal: [what a good result lets me do] - Current situation: [paste notes, draft, data, or constraints] - Audience: [who will use the result] - Deadline or limit: [time, budget, tools, length] Before answering, ask up to three questions only if the answers would materially change your recommendation. O

ChatGPTgpt-5

This is usable as written. The important parts are the definition of done, the instruction to expose assumptions, and the request for a smallest test. For a tiny business forecast, I would start with these checks: - Start from observed behavior - Write the riskiest assumption down - Choose a measurable next test If you share real material, remove anything private first and replace bracketed fields with concrete details.

Show all 3 messages

3401k

Mateo Patel@mateopatel·3mo ago

The question that cleaned up a pre-mortem for launch day

This started as a messy question about a pre-mortem for launch day. The follow-up made the answer practical.

Mateo Patel

Help me imagine a launch failed and turn likely causes into checks and owners. Context: - Goal: [what a good result lets me do] - Current situation: [paste notes, draft, data, or constraints] - Audience: [who will use the result] - Deadline or limit: [time, budget, tools, length] Before answering, ask up to three questions only if the answers would materially change your recommendation. Otherwise,

Claudeclaude-opus-4.5

This is usable as written. The important parts are the definition of done, the instruction to expose assumptions, and the request for a smallest test. For a pre-mortem for launch day, I would start with these checks: - Start from observed behavior - Write the riskiest assumption down - Choose a measurable next test If you share real material, remove anything private first and replace bracketed fields with concrete details.

Show all 3 messages

3301.1k

Asha Morgan@ashamorgan·3mo ago

A smaller way to tackle a tiny business forecast

I kept the useful constraints and dropped the role-play. It works better when the missing details are stated plainly.

Asha Morgan

For a tiny business forecast, should I build a complete plan first or test one small slice? I have limited time and I do not want throwaway work.

ChatGPTgpt-5

Test one slice, but choose a slice that crosses the riskiest part of the problem. A tiny easy demo will only prove the easy part. Use this decision rule: - If reversing the choice is cheap, try it. - If the choice locks in data, money, or other people’s time, write the full decision first. - If uncertainty is concentrated in one step, test that step before planning around it. For a tiny business forecast, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages

330963

Caleb Bose@calebbose·3mo ago

My notes from fixing a competitor brief

A compact prompt and the response it produced. Replace the bracketed parts with your own details.

Caleb Bose

I am stuck on a competitor brief. I need to compare competitors by customer, workflow, pricing, and evidence without copying marketing claims, but my current attempt is getting vague and too big. What would you check first?

ChatGPTgpt-5

First, shrink the decision. Do not solve the whole subject at once. 1. Start from observed behavior. 2. Write the riskiest assumption down. 3. Choose a measurable next test. Write down the result you need by the end of this session. Then choose one input you trust and make a first pass that can be checked. If that pass fails, you will know which assumption to revisit instead of starting over.

Show all 3 messages

340906