Explore

Tagged #qualitative-data

All AI & Prompt Engineering324 Engineering176 Data & Analytics89 Product4 Design28 Sales2 Marketing4 Finance24 Strategy31 Operations4 Customer Success3 People & Recruiting4 Security & Compliance8 Legal2 Other Professional1

#qualitative-dataClear filters

Amara Ross@amaraross·2w ago

ChatGPT was overcomplicating messy survey responses, 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.

Amara Ross

Be blunt about my plan for messy survey responses. 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, keep assumptions next to the metric.

Show all 3 messages

3402.1k

Amara Ross@amaraross·2mo ago

I needed a usable answer on messy survey responses

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

Amara Ross

I am stuck on messy survey responses. I need to clean and code free-text survey answers without hiding disagreement, 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. 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

3303.5k

Amara Ross@amaraross·3mo ago

messy survey responses, minus the vague advice

I wanted help with messy survey responses without pretending the model knew facts I had not provided.

Amara Ross

Give me a short checklist for messy survey responses. 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 - [ ] 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

3403.6k

Amara Ross@amaraross·1mo ago

The question that cleaned up messy survey responses

I wanted help with messy survey responses without pretending the model knew facts I had not provided.

Amara Ross

Help me clean and code free-text survey answers without hiding disagreement. 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, s

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 messy survey responses, 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

340683

Amara Ross@amaraross·2mo ago

I stopped guessing about messy survey responses

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

Amara Ross

For messy survey responses, 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 messy survey responses, make the first test produce evidence you can compare, not just something that looks complete.

Show all 3 messages

330740