Explore prompts and AI conversations

This version makes the model wait for an answer, correct selectively, and keep an error log.

Zuri Mensah

Tutor me on testing prompts across ChatGPT, Claude, and Gemini. My current level: [beginner / some experience / advanced] What I need to do with it: [real task, exam, project, or conversation] Time available today: [minutes] Material I am using: [paste notes, example, code, data, or source] Teach one small idea at a time. Start with a two-question diagnostic. Wait for my answer before explaining.

Geminigemini-2.5-pro

Good. Do these without looking anything up: 1. Explain testing prompts across ChatGPT, Claude, and Gemini in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6315.1k

Micah Ellis@micahellis·2mo ago

The using property-based tests tutor prompt I saved

This version makes the model wait for an answer, correct selectively, and keep an error log.

Micah Ellis

Tutor me on using property-based tests. My current level: [beginner / some experience / advanced] What I need to do with it: [real task, exam, project, or conversation] Time available today: [minutes] Material I am using: [paste notes, example, code, data, or source] Teach one small idea at a time. Start with a two-question diagnostic. Wait for my answer before explaining. Use one worked example,

Geminigemini-2.5-pro

Good. Do these without looking anything up: 1. Explain using property-based tests in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6215k

Alina Petrov@alinapetrov·2mo ago

What I was getting wrong about writing eval cases before changing a prompt

Sharing the correction because the mistake looked reasonable until I tested it.

Alina Petrov

I want to learn writing eval cases before changing a prompt, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Geminigemini-2.5-pro

Good. Do these without looking anything up: 1. Explain writing eval cases before changing a prompt in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6315.2k

Haruto Abe@harutoabe·2mo ago

finding duplicated state in React: a study session that did not turn into more notes

A practical session with a worked example, a short test, and a clear stopping point.

Haruto Abe

I want to learn finding duplicated state in React, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Geminigemini-2.5-pro

Good. Do these without looking anything up: 1. Explain finding duplicated state in React in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6214.5k

Mira Khan@mirakhan·2mo ago

The agent handoff notes prompt I actually kept

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

Mira Khan

Help me turn a messy agent run into a clean handoff another person can pick up. 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

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 agent handoff notes, 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

3414k

Theo Vega@theovega·2mo 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

Miles Kim@mileskim·2mo ago

ChatGPT was overcomplicating a design critique that stays specific, so I reset the question

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

Miles Kim

Be blunt about my plan for a design critique that stays specific. 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, check the keyboard path.

Show all 3 messages

3304.2k

Oscar Lind@oscarlind·2mo ago

What I was getting wrong about tool approval gates for AI agents

Sharing the correction because the mistake looked reasonable until I tested it.

Oscar Lind

I want to learn tool approval gates for AI agents, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Claudeclaude-opus-4.5

Good. Do these without looking anything up: 1. Explain tool approval gates for AI agents in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6214k

Darius Cole@dariuscole·2mo ago

What I was getting wrong about context engineering for reliable agents

Sharing the correction because the mistake looked reasonable until I tested it.

Darius Cole

I want to learn context engineering for reliable agents, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

ChatGPTgpt-5

Good. Do these without looking anything up: 1. Explain context engineering for reliable agents in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6315k

Theo Young@theoyoung·2mo ago

A blunt review of my approach to prompting from examples

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

Theo Young

Give me a short checklist for prompting from examples. 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 - [ ] 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

3313.9k

Dalia Nasser@dalianasser·2mo ago

prompt injection basics for tool users: a study session that did not turn into more notes

A practical session with a worked example, a short test, and a clear stopping point.

Dalia Nasser

I want to learn prompt injection basics for tool users, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Geminigemini-2.5-pro

Good. Do these without looking anything up: 1. Explain prompt injection basics for tool users in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6313.9k

Kai Nolan@kainolan·2mo ago

How I ask for help with a dashboard that answers one question

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

Kai Nolan

Be blunt about my plan for a dashboard that answers one question. 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

Show all 3 messages

3304.1k

Maya Torres@mayatorres·2mo ago

A practice-first plan for using examples to teach output quality

I asked for a plan built around attempts and feedback, not a list of resources.

Maya Torres

I want to learn using examples to teach output quality, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Claudeclaude-opus-4.5

Good. Do these without looking anything up: 1. Explain using examples to teach output quality in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6314.2k

Anika Kim@anikakim·2mo ago

The checklist I use for Postgres query tuning

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

Anika Kim

I am stuck on Postgres query tuning. I need to read an EXPLAIN plan and choose the smallest index or query change that matters, 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. Reproduce the failure before changing code. 2. Keep the patch smaller than the diagnosis. 3. Write the rollback before deployment. 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

3303.8k

Sana Raman@sanaraman·2mo ago

My notes from fixing long-document context

I wanted help with long-document context without pretending the model knew facts I had not provided.

Sana Raman

I am stuck on long-document context. I need to work through a long document without losing definitions, exceptions, or open questions, 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. 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

3314k

regex raccoon@regex_raccoon·2mo ago

Gemini priced my consulting rate and then argued me out of the number

I wanted validation for £450/day. I left with £700 and a much better answer to 'why so much'.

regex raccoon

Going freelance as a policy analyst. 9 years in-house, last salary £68k. I'm thinking £450/day. Sanity check me.

Geminigemini-2.5-pro

Your number is anchored to your salary, and that's the wrong anchor. Let me show you why, then give you a real one. **Why £450 is too low** Start from what you need, not what you earned: - 260 weekdays a year - minus 25 holiday, 8 bank holidays, ~5 sick = 222 - minus admin, marketing, invoicing, the work of finding work — realistically 25–30% of your time - **≈ 155 billable days**, and that's an optimistic first year At £450 that's £69,750 revenue. Then subtract employer pension (~£4k), no sick pay, no paid holiday, your own equipment, insurance, accountant, and the ~£8k of employer NI your ol

Show all 4 messages

4204.2k

Celia Ramos@celiaramos·3mo ago

I finally found a good way to learn cohort analysis without mixing time grains

The useful change was doing a small retrieval check before reading more.

Celia Ramos

I want to learn cohort analysis without mixing time grains, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Claudeclaude-opus-4.5

Good. Do these without looking anything up: 1. Explain cohort analysis without mixing time grains in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6314.9k

Leila Lane@leilalane·2mo ago

How I ask for help with accessibility review for a form

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

Leila Lane

Be blunt about my plan for accessibility review for a form. 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

Show all 3 messages

3404k

Micah Ellis@micahellis·2mo ago

Forked from@kenjifujita/I finally found a good way to learn prompt injection basics for tool users

The prompt injection basics for tool users tutor prompt I saved

This version makes the model wait for an answer, correct selectively, and keep an error log.

Micah Ellis

Tutor me on prompt injection basics for tool users. My current level: [beginner / some experience / advanced] What I need to do with it: [real task, exam, project, or conversation] Time available today: [minutes] Material I am using: [paste notes, example, code, data, or source] Teach one small idea at a time. Start with a two-question diagnostic. Wait for my answer before explaining. Use one work

Geminigemini-2.5-pro

Show all 6 messages

6214.5k

Samir Shah@samirshah·2mo ago

A blunt review of my approach to a safe dependency upgrade

This started as a messy question about a safe dependency upgrade. The follow-up made the answer practical.

Samir Shah

Give me a short checklist for a safe dependency upgrade. 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 - [ ] Reproduce the failure before changing code - [ ] Keep the patch smaller than the diagnosis - [ ] Write the rollback before deployment - [ ] 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

3304.2k

Lina Bennett@linabennett·2mo ago

A smaller way to tackle metrics with fuzzy definitions

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

Lina Bennett

For metrics with fuzzy definitions, 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 metrics with fuzzy definitions, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages

3303.6k

Ben Brooks@benbrooks·2mo ago

React state that keeps drifting: the version with actual constraints

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

Ben Brooks

Give me a short checklist for React state that keeps drifting. I want something I can run before I call the work done.

Claudeclaude-opus-4.5

Show all 3 messages

3302.8k

Anya Volkov@anyavolkov·2mo ago

What I was getting wrong about reviewing code written by an agent

Sharing the correction because the mistake looked reasonable until I tested it.

Anya Volkov

I want to learn reviewing code written by an agent, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Claudeclaude-opus-4.5

Good. Do these without looking anything up: 1. Explain reviewing code written by an agent in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6312.9k

Mira Khan@mirakhan·2mo ago

A smaller way to tackle agent handoff notes

I wanted help with agent handoff notes without pretending the model knew facts I had not provided.

Mira Khan

For agent handoff notes, 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 agent handoff notes, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages

3314k

Eva Kovac@evakovac·2mo ago

The designing idempotent background jobs tutor prompt I saved

This version makes the model wait for an answer, correct selectively, and keep an error log.

Eva Kovac

Tutor me on designing idempotent background jobs. My current level: [beginner / some experience / advanced] What I need to do with it: [real task, exam, project, or conversation] Time available today: [minutes] Material I am using: [paste notes, example, code, data, or source] Teach one small idea at a time. Start with a two-question diagnostic. Wait for my answer before explaining. Use one worked

ChatGPTgpt-5

Good. Do these without looking anything up: 1. Explain designing idempotent background jobs in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6413.2k

Noor Diaz@noordiaz·2mo 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

Tomas Varga@tomasvarga·3mo ago

Forked from@evakovac/The separating model mistakes from missing context tutor prompt I saved

I finally found a good way to learn data cleaning rules you can reverse

The useful change was doing a small retrieval check before reading more.

Tomas Varga

I want to learn data cleaning rules you can reverse, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Geminigemini-2.5-pro

Good. Do these without looking anything up: 1. Explain data cleaning rules you can reverse in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6214.8k

Felix Silva@felixsilva·2mo ago

The cache invalidation without folklore prompt I actually kept

This started as a messy question about cache invalidation without folklore. The follow-up made the answer practical.

Felix Silva

Help me define keys, freshness, and invalidation from actual read and write paths. 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. Otherw

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 cache invalidation without folklore, I would start with these checks: - Reproduce the failure before changing code - Keep the patch smaller than the diagnosis - Write the rollback before deployment If you share real material, remove anything private first and replace bracketed fields with concrete details.

Show all 3 messages

3303k

Haruto Abe@harutoabe·3mo ago

tool approval gates for AI agents: a study session that did not turn into more notes

A practical session with a worked example, a short test, and a clear stopping point.

Haruto Abe

I want to learn tool approval gates for AI agents, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Geminigemini-2.5-pro

Show all 6 messages

6214.2k

Rowan Blake@rowanblake·2mo ago

testing API failure paths: a study session that did not turn into more notes

A practical session with a worked example, a short test, and a clear stopping point.

Rowan Blake

I want to learn testing API failure paths, but I keep collecting explanations instead of getting better at it. I have 35 minutes. Start by checking what I already know.

Claudeclaude-opus-4.5

Good. Do these without looking anything up: 1. Explain testing API failure paths in two sentences. 2. Give one situation where you would use it and one where you would not. I am checking your current model, not your vocabulary. A partial answer is more useful than a polished guess.

Show all 6 messages

6213.9k

Explore

Explore

Explore

The testing prompts across ChatGPT, Claude, and Gemini tutor prompt I saved

The using property-based tests tutor prompt I saved

What I was getting wrong about writing eval cases before changing a prompt

finding duplicated state in React: a study session that did not turn into more notes

The agent handoff notes prompt I actually kept

A smaller way to tackle a pricing page review

ChatGPT was overcomplicating a design critique that stays specific, so I reset the question

What I was getting wrong about tool approval gates for AI agents

What I was getting wrong about context engineering for reliable agents

A blunt review of my approach to prompting from examples

prompt injection basics for tool users: a study session that did not turn into more notes

How I ask for help with a dashboard that answers one question

A practice-first plan for using examples to teach output quality

The checklist I use for Postgres query tuning

My notes from fixing long-document context

Gemini priced my consulting rate and then argued me out of the number

I finally found a good way to learn cohort analysis without mixing time grains

How I ask for help with accessibility review for a form

The prompt injection basics for tool users tutor prompt I saved

A blunt review of my approach to a safe dependency upgrade

A smaller way to tackle metrics with fuzzy definitions

React state that keeps drifting: the version with actual constraints

What I was getting wrong about reviewing code written by an agent

A smaller way to tackle agent handoff notes

The designing idempotent background jobs tutor prompt I saved

My notes from fixing customer interviews without leading

I finally found a good way to learn data cleaning rules you can reverse

The cache invalidation without folklore prompt I actually kept

tool approval gates for AI agents: a study session that did not turn into more notes

testing API failure paths: a study session that did not turn into more notes