Prompt engineering is how you communicate with LLMs effectively. Techniques include:
- **System prompts** — setting the model's role and constraints - **Few-shot examples** — showing the model what good output looks like - **Chain-of-thought** — asking the model to reason step by step - **Structured output** — requesting specific formats (JSON, XML)
Good prompt engineering can dramatically improve output quality without any model changes. It's the most accessible AI skill.