15 AI Prompts for Brainstorming That Actually Work

"Brainstorm 10 ideas for X" is the most common AI prompt in the world, and also one of the worst. You get back a bullet list of safe, predictable ideas — the same ones you'd have thought of yourself in 30 seconds.

The trick to brainstorming with AI is forcing it into a mode that's different from "list things." Below are 15 prompts that do that, organized by what you want out of the session.

When you're starting cold

1. The 100-ideas dump

Give me 100 ideas for [topic]. Don't filter for quality. Include obvious ones, weird ones, bad ones, and one-word fragments. I want quantity, not curation.

Why it works: Quality kicks in around idea #40. Most "brainstorm 10" lists die at idea #10 because that's where you asked it to stop.

2. The constrained version

Give me 20 ideas for [topic] — but constraint: each idea must [fit a specific limit, e.g., "cost under $50", "be doable in one weekend", "involve only existing tools we already have"].

Why it works: Constraints generate creativity. Removing all constraints generates generic.

3. The "what would [person] do" prompt

Brainstorm ideas for [topic] from the perspective of [specific person: a 12-year-old / a frustrated customer / Marie Kondo / a hedge fund manager / someone who hates this product].

Why it works: Personas pull the AI out of its default voice.

When you have ideas but they're stuck

4. The contrarian

Here are my current ideas: [list]. Argue against every single one. Be specific about why each would fail.

Why it works: AI is usually too agreeable. Forcing disagreement surfaces real problems.

5. The remix

Here are 5 ideas: [list]. Combine them into 10 new ideas where each is a fusion of at least 2 of the originals.

Why it works: Combinatorial thinking. Often the best idea is two boring ideas stuck together.

6. The "opposite day"

Here's my idea: [idea]. Now give me the opposite. Now give me what's halfway between them.

Why it works: Forces you to look at the spectrum, not just the original point.

When you need lateral angles

7. The analogy generator

What's a non-obvious analogy for [problem]? Pick something from a totally different domain — biology, sports, war, cooking, music — and tell me what we can learn from how they solve similar problems.

Why it works: Cross-domain thinking is where genuinely novel ideas come from.

8. The "five whys" excavator

Here's the problem I'm trying to solve: [problem]. Ask "why" 5 times in sequence, going deeper each time, to find the root cause. Then brainstorm solutions for the root cause, not the surface problem.

Why it works: Most brainstorming attacks symptoms. Five whys gets you to the actual problem.

9. The constraint inversion

The constraint on my problem is [constraint]. What if that constraint were the opposite? Brainstorm ideas that only work if [opposite constraint] were true.

Why it works: Reveals which constraints are real and which are assumed.

When you need to evaluate

10. The pre-mortem

Imagine it's 12 months from now and [idea/project] has completely failed. Write the post-mortem. What went wrong? List the top 7 reasons in order of likelihood.

Why it works: Future-tense failure analysis surfaces risks you'd miss in present-tense planning.

11. The customer skeptic

Pretend you're a customer who just heard about [idea]. List every objection, doubt, and reason you wouldn't buy it. Be specific and harsh.

Why it works: AI defaults to being supportive. This explicitly disables that.

12. The "what would kill this"

If I launch [idea], what's the single thing most likely to kill it in the first 90 days? Then the next 90 days. Then the next year.

Why it works: Timeboxed risks are more actionable than abstract risks.

When you need to communicate the result

13. The elevator pitch generator

Here's my idea: [explanation]. Write 5 different one-sentence pitches — one for an investor, one for a customer, one for a teenager, one for a journalist, one as a tweet.

Why it works: Forces you to find the irreducible core of the idea.

14. The skeptic translator

Here's my idea: [explanation]. Now rewrite the explanation as if you were a skeptic explaining what's wrong with it.

Why it works: If you can articulate the case against your idea clearly, you understand it better.

15. The teach-it-back

Explain [idea] back to me as if I'd never heard it before, in under 100 words. If anything is unclear, ask me to clarify before writing.

Why it works: The "ask me to clarify" line catches gaps in your own thinking.

How to actually run a session

A few tactical tips for getting more out of these:

1. Don't stop at one prompt. Brainstorming with AI works best as a chain. Start with prompt #1, pick the most interesting result, run it through prompt #4, then #10. Layering modes produces better output than any single prompt.

2. Push back. When the AI gives you a flat list, reply: "those are all generic. Give me 10 weirder ones." The second pass is usually where the gold is.

3. Save the chat. Even if 9 of 10 ideas are bad, the one good idea is worth keeping. Most people lose great brainstorm output because they didn't bookmark it.

4. Mix modes within one session. Use the contrarian prompt right after the dump prompt. The contrast surfaces patterns you'd miss otherwise.

Try it

You can test any of these in Smillee AI without signing up. Copy a prompt, paste it in with your specific topic, and see what you get. If the first answer is weak, push back — that's where the real brainstorming starts.