MCP serverSave straight from your agent

About us How it works FAQ Blog Contact us

Home Explore Create Sign in

Explore

Loading…

Explore

Tagged #statistics

Active New Most used Recommended

All AI & Prompt Engineering324 Engineering176 Data & Analytics89 Product4

Browse by tag

#ai314#chatgpt211#claude208#gemini208#prompting182#agents174#context-engineering172#coding160

Customer Success3

People & Recruiting4

Security & Compliance8

Other Professional1

#statisticsClear filters

NENeha Kapoor@nehakapoor·2w ago

A practice-first plan for cohort analysis without mixing time grains

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

Neha Kapoor

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.

ChatGPTgpt-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

6411.6k

JAJasper Wong@jasperwong·3w ago

A practice-first plan for data cleaning rules you can reverse

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

Jasper Wong

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.

Claudeclaude-opus-4.5

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

6212.5k

CECelia Ramos@celiaramos·4w 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

TOTomas Varga@tomasvarga·1mo 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

EMEmil Novak@emilnovak·4w ago

I finally found a good way to learn reading uncertainty in a dashboard

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

Emil Novak

I want to learn reading uncertainty in a dashboard, 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 reading uncertainty in a dashboard 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

6312.5k

LULucia Marin@luciamarin·1mo ago

What I was getting wrong about reading uncertainty in a dashboard

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

Lucia Marin

I want to learn reading uncertainty in a dashboard, 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 reading uncertainty in a dashboard 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

6414.3k

DADalia Nasser@dalianasser·2mo ago

checking an A/B test before celebrating: 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 checking an A/B test before celebrating, 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 checking an A/B test before celebrating 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

6314k

SISilas Berg@silasberg·2mo ago

writing a metric contract: 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.

Silas Berg

I want to learn writing a metric contract, 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 writing a metric contract 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

6314.5k

IDIdris Bello@idrisbello·1mo ago

What I was getting wrong about writing a metric contract

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

Idris Bello

I want to learn writing a metric contract, 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 a metric contract 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

6212.2k

ALAlina Petrov@alinapetrov·2mo ago

What I was getting wrong about data cleaning rules you can reverse

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

Alina Petrov

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

6313.8k

PRPriya Hsu@priyahsu·3w ago

Forked from@drewbell/How I ask for help with TypeScript types at an API boundary

What finally made an experiment readout click for me

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

Priya Hsu

Help me analyze an A/B test with guardrails, uncertainty, and practical significance. 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. Oth

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 an experiment readout, I would start with these checks: - Fix the grain before calculating - Keep assumptions next to the metric - Show uncertainty in the output If you share real material, remove anything private first and replace bracketed fields with concrete details.

Show all 3 messages

340569

ANAnya Volkov@anyavolkov·4w ago

What I was getting wrong about checking an A/B test before celebrating

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

Anya Volkov

I want to learn checking an A/B test before celebrating, 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 checking an A/B test before celebrating 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

6311.2k

MIMicah Ellis@micahellis·2mo ago

The checking an A/B test before celebrating 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 checking an A/B test before celebrating. 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 wor

Geminigemini-2.5-pro

Good. Do these without looking anything up: 1. Explain checking an A/B test before celebrating 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

6214.1k

KEKenji Fujita@kenjifujita·2w ago

I finally found a good way to learn checking an A/B test before celebrating

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

Kenji Fujita

I want to learn checking an A/B test before celebrating, 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 checking an A/B test before celebrating 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

621284

NONoura Kassem@nourakassem·3w ago

I finally found a good way to learn writing a metric contract

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

Noura Kassem

I want to learn writing a metric contract, 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 a metric contract 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

631732

PRPriya Hsu@priyahsu·2mo ago

My notes from fixing an experiment readout

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

Priya Hsu

I am stuck on an experiment readout. I need to analyze an A/B test with guardrails, uncertainty, and practical significance, 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. Fix the grain before calculating. 2. Keep assumptions next to the metric. 3. Show uncertainty in the output. 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

3303.4k

ZUZuri Mensah@zurimensah·2mo ago

The cohort analysis without mixing time grains tutor prompt I saved

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

Zuri Mensah

Tutor me on cohort analysis without mixing time grains. 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

Geminigemini-2.5-pro

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

6313.9k

PRPriya Hsu@priyahsu·2mo ago

A blunt review of my approach to an experiment readout

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

Priya Hsu

Give me a short checklist for an experiment readout. 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 - [ ] Fix the grain before calculating - [ ] Keep assumptions next to the metric - [ ] Show uncertainty in the output - [ ] 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

3403.4k

ADAdrian Cho@adriancho·2mo ago

The reading uncertainty in a dashboard tutor prompt I saved

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

Adrian Cho

Tutor me on reading uncertainty in a dashboard. 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 e

Claudeclaude-opus-4.5

Good. Do these without looking anything up: 1. Explain reading uncertainty in a dashboard 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

6213k

MAMalik Johnson@malikjohnson·3mo ago

The data cleaning rules you can reverse tutor prompt I saved

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

Malik Johnson

Tutor me on data cleaning rules you can reverse. 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 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

6313.5k

MAMaya Torres@mayatorres·3mo ago

A practice-first plan for writing a metric contract

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

Maya Torres

I want to learn writing a metric contract, 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 writing a metric contract 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

6313.6k

SOSoraya Aziz@sorayaaziz·2mo ago

reading uncertainty in a dashboard: 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.

Soraya Aziz

I want to learn reading uncertainty in a dashboard, 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 reading uncertainty in a dashboard 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

6312k

RORonan Byrne@ronanbyrne·2mo ago

A practice-first plan for checking an A/B test before celebrating

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

Ronan Byrne

I want to learn checking an A/B test before celebrating, 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 checking an A/B test before celebrating 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

6312.6k

PRPriya Hsu@priyahsu·1mo ago

Gemini found the hole in my an experiment readout plan

I wanted help with an experiment readout without pretending the model knew facts I had not provided.

Priya Hsu

For an experiment readout, 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 an experiment readout, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages

330626

HAHaruto Abe@harutoabe·2mo ago

cohort analysis without mixing time grains: 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 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.

Geminigemini-2.5-pro

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

6211.2k

FAFatima Saleh@fatimasaleh·2mo ago

data cleaning rules you can reverse: 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.

Fatima Saleh

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.

ChatGPTgpt-5

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

6411.1k

JOJonah Okafor@jonahokafor·2w ago

Forked from@celiaramos/I finally found a good way to learn cohort analysis without mixing time grains

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.

Jonah Okafor

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

6100

NENeha Kapoor@nehakapoor·2w ago

Forked from@harutoabe/cohort analysis without mixing time grains: a study session that did not turn into more notes

cohort analysis without mixing time grains: 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.

Neha Kapoor

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.

Geminigemini-2.5-pro

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

6100

YUYuna Patel@yunapatel·2w ago

Forked from@nehakapoor/A practice-first plan for cohort analysis without mixing time grains

A practice-first plan for cohort analysis without mixing time grains

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

Yuna Patel

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.

ChatGPTgpt-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

6100

EVEva Kovac@evakovac·2w ago

Forked from@oscarlind/What I was getting wrong about cohort analysis without mixing time grains

What I was getting wrong about cohort analysis without mixing time grains

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

Eva Kovac

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

6100

#software-learning100

#data-literacy50

#prompt-template50

#trending-questions50