#review prompts and AI conversations

I needed a usable answer on multi-agent review

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

Leila Bose

I am stuck on multi-agent review. I need to split a task between a maker, a verifier, and a final editor without duplicated work, 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. Put the source of truth in the prompt. 2. Mark missing evidence instead of filling it in. 3. Add a stop condition before tool use. 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

3312.8k

Leila Bose@leilabose·3mo ago

ChatGPT was overcomplicating multi-agent review, so I reset the question

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

Leila Bose

Be blunt about my plan for multi-agent review. 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, mark missing evidence instead of filling it in.

Show all 3 messages

3413k

Leila Bose@leilabose·4mo ago

The question that cleaned up multi-agent review

I wanted help with multi-agent review without pretending the model knew facts I had not provided.

Leila Bose

Help me split a task between a maker, a verifier, and a final editor without duplicated work. 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 recommendat

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 multi-agent review, I would start with these checks: - Put the source of truth in the prompt - Mark missing evidence instead of filling it in - Add a stop condition before tool use If you share real material, remove anything private first and replace bracketed fields with concrete details.

Show all 3 messages

3414.2k

Leila Bose@leilabose·3w ago

I stopped guessing about multi-agent review

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

Leila Bose

For multi-agent review, 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 multi-agent review, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages

331156

Felix Silva@felixsilva·2w ago

Forked from@leilabose/The question that cleaned up multi-agent review

The question that cleaned up multi-agent review

I wanted help with multi-agent review without pretending the model knew facts I had not provided.

Felix Silva

Help me split a task between a maker, a verifier, and a final editor without duplicated work. 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 recommendat

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 multi-agent review, I would start with these checks: - Put the source of truth in the prompt - Mark missing evidence instead of filling it in - Add a stop condition before tool use If you share real material, remove anything private first and replace bracketed fields with concrete details.

Show all 3 messages

3200

Miles Kim@mileskim·2w ago

Forked from@leilabose/I needed a usable answer on multi-agent review

I needed a usable answer on multi-agent review

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

Miles Kim

I am stuck on multi-agent review. I need to split a task between a maker, a verifier, and a final editor without duplicated work, 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. Put the source of truth in the prompt. 2. Mark missing evidence instead of filling it in. 3. Add a stop condition before tool use. 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

3200

Theo Young@theoyoung·2w ago

Forked from@leilabose/ChatGPT was overcomplicating multi-agent review, so I reset the question

ChatGPT was overcomplicating multi-agent review, so I reset the question

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

Theo Young

Be blunt about my plan for multi-agent review. 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, mark missing evidence instead of filling it in.

Show all 3 messages

3200

Felix Nguyen@felixnguyen·2w ago

Forked from@leilabose/I stopped guessing about multi-agent review

I stopped guessing about multi-agent review

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

Felix Nguyen

For multi-agent review, 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 multi-agent review, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages

3200

Micah Ellis@micahellis·2w ago

Forked from@leilabose/multi-agent review, minus the vague advice

multi-agent review, minus the vague advice

I wanted help with multi-agent review without pretending the model knew facts I had not provided.

Micah Ellis

Give me a short checklist for multi-agent review. 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 - [ ] Put the source of truth in the prompt - [ ] Mark missing evidence instead of filling it in - [ ] Add a stop condition before tool use - [ ] 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

3200

Leila Bose@leilabose·2mo ago

multi-agent review, minus the vague advice

I wanted help with multi-agent review without pretending the model knew facts I had not provided.

Leila Bose

Give me a short checklist for multi-agent review. 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 - [ ] Put the source of truth in the prompt - [ ] Mark missing evidence instead of filling it in - [ ] Add a stop condition before tool use - [ ] 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

341213

Explore

Explore

Explore

I needed a usable answer on multi-agent review

ChatGPT was overcomplicating multi-agent review, so I reset the question

The question that cleaned up multi-agent review

I stopped guessing about multi-agent review

The question that cleaned up multi-agent review

I needed a usable answer on multi-agent review

ChatGPT was overcomplicating multi-agent review, so I reset the question

I stopped guessing about multi-agent review

multi-agent review, minus the vague advice

multi-agent review, minus the vague advice