Few-shot examples

Few-shot prompting (also called multishot prompting) is a technique where you include a small number of carefully crafted input-output examples directly inside your prompt before your actual request. Instead of describing what you want in abstract terms, you show Claude concrete demonstrations — Claude reads the pattern from those examples and applies it to new inputs. This is distinct from zero-shot prompting, where no examples are given, or single-shot prompting, where only one example is provided. The technique works because language models are highly sensitive to demonstrated patterns. Showing Claude two to five examples of the input format, reasoning style, output structure, and tone you expect is generally more reliable than writing lengthy prose instructions. Examples can be wrapped in XML tags (e.g., `<examples>` containing individual `<example>` blocks) so Claude can cleanly distinguish demonstration data from the live task. Few-shot examples are not a special feature you toggle on — they are a prompting technique baked into how you write your prompt. They work across every Claude interface: claude.ai chat, the desktop and mobile apps, the Anthropic API, and Claude Code. Token usage counts toward your normal plan limits, but no extra settings or plan upgrades are required to use the technique.