Use Examples (Multishot Prompting)

Examples are your secret weapon for getting Claude to generate exactly what you need. By providing a few well-crafted examples, you dramatically improve accuracy, consistency, and performance — especially for tasks requiring structured outputs.

For maximum effectiveness, examples should be: Relevant (mirror your actual use case), Diverse (cover edge cases and vary enough to avoid unintended patterns), and Clear (wrapped in <example> tags for structure).

Without examples, Claude may not list multiple categories, includes long unwanted explanations, and formats inconsistently. One example fixes everything.

Our CS team is overwhelmed with unstructured feedback. Your task is to analyze feedback and categorize issues for our product and engineering teams. Use these categories: UI/UX, Performance, Feature Request, Integration, Pricing, and Other. Also rate the sentiment (Positive/Neutral/Negative) and priority (High/Medium/Low). Here is an example:

<example>
Input: The new dashboard is a mess! It takes forever to load, and I can't find the export button. Fix this ASAP!
Category: UI/UX, Performance
Sentiment: Negative
Priority: High
</example>

Now, analyze this feedback: {{FEEDBACK}}

In tests, prompts with examples produce outputs that are more structured, more consistent across multiple runs, and more aligned with the intended format. Without examples, Claude often adds explanatory text, uses inconsistent formatting, and may miss multi-label categorizations. Examples eliminate ambiguity that instructions alone cannot resolve.