# Few-shot prompting

> Showing an LLM a handful of worked examples inside the prompt so it copies the pattern - no fine-tuning needed.

The cheapest way to lift output quality, and usually the first thing we try before reaching for a trained model.

## Related terms

- https://dfieldsolutions.com/en/glossary/agent-memory.md
- https://dfieldsolutions.com/en/glossary/agentic-ai.md
- https://dfieldsolutions.com/en/glossary/ai-gateway.md
- https://dfieldsolutions.com/en/glossary/chunking.md

---

Source: https://dfieldsolutions.com/en/glossary/few-shot
DField Solutions — Torony köz 5-1.a, 2120 Dunakeszi, Hungary — +36 20 722 0002 — dezso@dfieldsolutions.com
Booking: see https://dfieldsolutions.com/en/contact
