Day 8: Use ChatGPT for Brainstorming and Question Development

One small win today
Keep one idea that fits the time, cost, and contact constraints.
Let’s try itListen with Prism
Prism guides you through the whole lesson. Listen straight through, or choose a chapter. Pause whenever you want to try something.
Complete podcast · 8 min 04 sec · AI-generated character voice
Jump to a chapter
Day 8: Use ChatGPT for Brainstorming and Question Development audio transcript
Welcome
Prism: Hi, I’m Prism. Welcome to the Day 8 lesson: Use ChatGPT for Brainstorming and Question Development. I’ll guide you through the whole lesson. Pause whenever you want to try something. Chapter links and the full transcript are available alongside the player, so you can return to the part you need.
Your one useful idea
Prism: Here’s the one idea to keep in your pocket today. Give a goal and constraints, ask for distinct approaches, and compare their effort and drawbacks before choosing.
Why this helps
Prism: Let’s connect this to a real working day. Cue says: AI can give you different angles when you feel stuck. The useful part is choosing, so today you will ask for fewer ideas and explain your choice.
Before you begin
Prism: A quick check before we get our draft-making shoes on. More ideas do not automatically mean better ideas. Ask for differences in audience or approach, then judge feasibility yourself.
Try it together
Prism: Ready to make a little progress? Here’s the quick route and the full practice. You can pause after the steps and work in your own time. Quick version: Ask for three ideas, reject any that break the constraints, and keep one promising option. About 10 minutes is enough. Step 1. Choose the mock goal below. Step 2. Generate five distinct ideas. Step 3. Keep three and write one reason to reject another. Practice material or example: Mock goal: help new colleagues find the right support contact. Constraints: one week, no new software, and a small internal team.
Simple and Expanded prompts
Prism: Time to frame the request. Both prompt versions are in this lesson. You only need to try one. I’ll read both versions so you can hear the difference. Pause and copy the exact text from the lesson if you’re practising. Here’s the Simple prompt. Suggest five distinct ways to help new colleagues find the right support contact in one week without new software. For each, give the audience, effort, and one drawback. Recommend three to explore, with reasons. Label assumptions.
Prism: Here’s the complete Expanded prompt. Suggest five distinct ways to help new colleagues find the right support contact in one week without new software. For each, give the audience, effort, and one drawback. Recommend three to explore, with reasons. Label assumptions. Make the five ideas meaningfully different, not five versions of a web resource. Respect the one-week and no-new-software limits. Rank options by usefulness and effort, and include one question that could change the ranking. Pick the version that fits your task. One useful prompt is enough. Give it a try when you’re ready.
A worked example
Prism: Let’s open a little window onto one possible result. This example is written for the course. Your assistant’s answer can look different. One possible result: Option: a single-sheet contact guide in an existing shared folder. Effort: small. Drawback: someone must keep it current. Question: which three support questions confuse new starters most? Why it works: The idea fits the constraints and exposes the maintenance cost instead of hiding it. Cue says: Ask for different approaches, then choose what fits. Folio says: One week and no new software are useful limits, not obstacles to ignore. Watch for: "Build a new support chatbot" ignores the no-new-software limit and is too large for this exercise.
Spot the Wobble
Prism: Tiny detective break! Let’s spot the wobble. Draft to check: Let’s build a new support chatbot. Question: Our exercise allows no new software. Which idea fits? A: Buy a chatbot platform and start building. B: Try a single-sheet contact guide in the existing shared folder. What do you think?
*A short thinking pause. Pause the player for as long as you need.*
Prism: Here’s my check. The answer is B Why: A useful idea fits the constraints. The contact guide can be tested with tools already available. A wobble is a clue, not a disaster. That little check is how a draft gets stronger.
Keep something useful
Prism: Let’s give your useful work a home. Save three feasible ideas, their drawbacks, and one question for the full practice, or just keep your checked quick result. Keep the input beside it and note one thing you checked.
Review and save
Prism: Time for the satisfying bit: checking what you made. The quick finish counts. You don’t have to do every extra. Are the ideas meaningfully different and feasible within the constraints? Quick finish: Keep one idea that fits the time, cost, and contact constraints. You can stop here. Done when: Full practice: You have three distinct, feasible options, a drawback for each, and one question to investigate. You can stop here. Extra practice, only if useful: Develop a third idea and ask one colleague-style question about it.
Your optional official video
Prism: If you’d like to see the tool in action, there’s an optional official video embedded in this lesson. We’ll explain what to notice. You can watch later. Cue says: Listen for the extra details that make a request useful. Add your audience and constraints before asking for three ideas. Watch: How to Ask ChatGPT Better Questions , OpenAI Academy (official OpenAI YouTube channel, published September 16, 2026, verified October 2, 2026). Keep it small: About 1 minute and 47 seconds. This clip uses meal planning. Borrow the prompting habit for brainstorming, then choose an idea yourself. Watching is optional.
Questions you might be wondering
Prism: Two questions you might be wondering about. Let’s clear them up. How do I get useful brainstorming ideas from AI? Give a goal and constraints, ask for distinct approaches, and compare their effort and drawbacks before choosing. How many ideas do I need? Five initial ideas are enough today. Keep three strong options and explain why you rejected another.
Quick quiz: question 1
Prism: Question 1 of our three little checks. What should you include when asking for brainstorming help? Option A. Only a request for lots of ideas. Option B. The goal and practical constraints. Option C. A requirement that every idea sound equally promising. Want a hint? Think about what makes an idea usable within your situation. Pause to choose. Keep listening when you’re ready for the answer.
*A short thinking pause. Pause the player for as long as you need.*
Prism: The answer is B. The goal and practical constraints. A goal, one-week limit, and no-new-software boundary focus the ideas.
Prism: If you spotted it, lovely work! If you picked another answer, you’ve found something useful to practise. There’s no score to chase.
Quick quiz: question 2
Prism: Question 2 of our three little checks. Which idea fits the mock constraints? Option A. Purchase and deploy a new company-wide platform this week. Option B. Build a custom system over six months. Option C. Draft a single-sheet contact guide using existing tools. Want a hint? Today's team has one week and no new software. Pause to choose. Keep listening when you’re ready for the answer.
*A short thinking pause. Pause the player for as long as you need.*
Prism: The answer is C. Draft a single-sheet contact guide using existing tools. A small guide fits the time and tool limits while addressing the support-contact goal. Another little check in your toolkit. You’re building a habit one answer at a time.
Quick quiz: question 3
Prism: Question 3 of our three little checks. Before choosing an idea, what should you compare? Option A. Effort, drawbacks, and whether the options are meaningfully different. Option B. Only which name sounds most exciting. Option C. How confidently the assistant recommends it. Want a hint? A useful shortlist helps you make a practical tradeoff. Pause to choose. Keep listening when you’re ready for the answer.
*A short thinking pause. Pause the player for as long as you need.*
Prism: The answer is A. Effort, drawbacks, and whether the options are meaningfully different. Comparing feasibility and drawbacks helps you choose an approach worth investigating. Three checks, one stronger understanding. The online quiz lets you try again until each answer clicks.
Your next small step
Prism: Before you leave, keep the original input beside your checked result. Your judgment is the part no assistant can replace. You made room for one useful step today. That counts. Day 9 is ready whenever you are. Cue asks, Folio makes, Prism checks. See you for your next small win!
See today’s example with your practice partners

Key Takeaway
Give a goal and constraints, ask for distinct approaches, and compare their effort and drawbacks before choosing.
Why It Matters
Cue: AI can give you different angles when you feel stuck. The useful part is choosing, so today you will ask for fewer ideas and explain your choice.
Know Before You Try
More ideas do not automatically mean better ideas. Ask for differences in audience or approach, then judge feasibility yourself.

Try It
Quick version: Ask for three ideas, reject any that break the constraints, and keep one promising option. About 10 minutes is enough.
- Choose the mock goal below.
- Generate five distinct ideas.
- Keep three and write one reason to reject another.
Practice material or example: Mock goal: help new colleagues find the right support contact. Constraints: one week, no new software, and a small internal team.

Prompt
Primary Prompt
Pick one to try. Simple gets you moving. Expanded adds structure. Both include the practice inputs.
Suggest five distinct ways to help new colleagues find the right support contact in one week without new software. For each, give the audience, effort, and one drawback. Recommend three to explore, with reasons. Label assumptions.Suggest five distinct ways to help new colleagues find the right support contact in one week without new software. For each, give the audience, effort, and one drawback. Recommend three to explore, with reasons. Label assumptions.
Make the five ideas meaningfully different, not five versions of a webpage. Respect the one-week and no-new-software limits. Rank options by usefulness and effort, and include one question that could change the ranking.Worked Example
: see a result and what to check
One possible result: Option: a one-page contact guide in an existing shared folder. Effort: small. Drawback: someone must keep it current. Question: which three support questions confuse new starters most?
Why it works: The idea fits the constraints and exposes the maintenance cost instead of hiding it.
Watch for: "Build a new support chatbot" ignores the no-new-software limit and is too large for this exercise.

Spot the Wobble
Draft to check: Let’s build a new support chatbot.
Our exercise allows no new software. Which idea fits?
Reveal Prism’s check
B is the better choice. A useful idea fits the constraints. The contact guide can be tested with tools already available.
Spotted it? Nice checking. Missed it? Now you know what to look for.
Make Something Useful
Save three feasible ideas, their drawbacks, and one question for the full practice, or just keep your checked quick result. Keep the input beside it and note one thing you checked.

Review and Save
Are the ideas meaningfully different and feasible within the constraints?
Quick finish: Keep one idea that fits the time, cost, and contact constraints. You can stop here.
Done when: Full practice: You have three distinct, feasible options, a drawback for each, and one question to investigate. You can stop here.
Want one more little stretch?
Develop a third idea and ask one colleague-style question about it.

Watch with Cue
Cue: Listen for the extra details that make a request useful. Add your audience and constraints before asking for three ideas.
Watch: How to Ask ChatGPT Better Questions | OpenAI Academy (official OpenAI YouTube channel, published September 16, 2026, verified October 2, 2026).
Show video player: How to Ask ChatGPT Better Questions | OpenAI Academy
Keep it small: About 1:47. This clip uses meal planning. Borrow the prompting habit for brainstorming, then choose an idea yourself. Watching is optional.
FAQ
How do I get useful brainstorming ideas from AI?
Give a goal and constraints, ask for distinct approaches, and compare their effort and drawbacks before choosing.
How many ideas do I need?
Five initial ideas are enough today. Keep three strong options and explain why you rejected another.

Three little checks
“Let’s see what stuck! Pick an answer and I’ll help you check it. You can try again as often as you like.”
Question 1 of 3
Lovely work. Three checks complete!
You’ve practiced the key ideas and checked the reasons. Keep that curiosity for the next day.

A small win worth keeping
Checked and saved? You can call it a day. Come back when you’re ready.
Progress is saved in this browser when available.
Stored on this device. No account or cross-device sync.
Course position: Day 8 of 30 · ChatGPT module
Continue: Day 9: Produce a Project Framing and Question Set
Sources and review date
Product features and interfaces can change. OpenAI ChatGPT Learn is the reference for current details. Course content reviewed October 2, 2026.