Multiple-Choice Prompts
Guide AI to select the best option from defined choices.
What It Is
Multiple-choice prompts present AI with a set of pre-defined options and ask it to select the most appropriate one based on given criteria. Instead of generating free-form responses, AI chooses from your curated list.
This technique combines the speed of constrained outputs with the nuance of having several valid options. You control the option space while leveraging AI's pattern-matching to handle the classification — consistency from your options, intelligence from AI's selection.
Why It Works
By constraining AI to pre-defined options, you eliminate the risk of unexpected or inappropriate responses. AI must select from your controlled set rather than generating from its full training data.
Multiple-choice format also makes AI's reasoning more consistent because it's matching your situation against clear categories you've defined. This produces more reliable, standardized outputs compared to open-ended prompts.
When To Use It
- Categorizing or routing items systematically
- Triage and prioritization decisions
- Sentiment or tone classification
- Status or stage determination
- Standardized assessment or evaluation
- When you don't know what the options should be
- Situations requiring creative or novel solutions
- Complex judgments needing detailed explanation
- When 'none of the above' would often be correct
- Open-ended exploration without clear categories
Ready-to-Use Templates
"Categorize this customer inquiry: A) Technical Support (product not working), B) Billing Question (payment or invoice issue), C) Sales Inquiry (pre-purchase question), D) Feature Request (wants new functionality). Inquiry: 'My credit card was charged twice this month.' Select only the letter."
"Assign priority to this lead — P1: Enterprise ready to buy, P2: Mid-market evaluating, P3: SMB researching, P4: Individual exploring. Lead: CTO of 500-person company requesting demo for Q1 implementation. Assign only the number."
"Classify sentiment — A) Very Positive (enthusiastic praise), B) Positive (satisfied), C) Neutral (factual), D) Negative (disappointed), E) Very Negative (angry). Review: 'I guess it's okay, not really what I expected though.' Select only the letter."
"Identify sales stage — 1) Awareness: just discovered us, 2) Consideration: evaluating options, 3) Decision: ready to buy, 4) Customer: already purchased. Prospect: 'Comparing your pricing with two competitors.' Select only the number."
"Select best action — A) Escalate to Manager (legal threat), B) Offer Refund (product defect), C) Provide Replacement (shipping damage), D) Offer Discount (minor inconvenience). Situation: Customer received product with scratched screen. Select only the letter."
Pro Tips
- Make options mutually exclusive: Each item should clearly belong to only one category — overlap creates confusion and inconsistent results.
- Provide brief descriptions: A short phrase after each option helps AI understand what distinguishes them, especially for edge cases.
- Use consistent formatting: Letters or numbers for easy parsing make these prompts ready for automation and batch processing.
- Include edge case guidance: Clarify how to handle borderline situations before running at scale — add a note like 'If between B and C, choose B.'
- Test with known examples: Verify AI selects correctly on a few examples you already know the answer to before applying at volume.
Understanding the Fundamentals
These techniques work because of how AI actually processes language. Our Making AI Make Sense series breaks down exactly why — making techniques like this intuitive instead of mysterious. 34 videos, free on YouTube.
Watch on YouTube →Need Help Applying AI to Your Business?
Templates teach the technique. We help you figure out where it actually fits in your work.
Eau Claire AI — Your path to AI, made clear.