// AI
Prompt Engineering
The craft of designing model inputs (system prompts, few-shot examples, output schemas) to elicit reliable outputs.
In depth
Once a fashionable job title, prompt engineering is now a baseline skill for anyone building on LLMs. Modern practice: structured output schemas, retrieval grounding, evaluation harnesses, and treating prompts like versioned code.
Related terms
LLM
Large Language Model, the transformer-based foundation model behind ChatGPT, Claude, Gemini and every 2024+ AI product.
RAG
Retrieval-Augmented Generation, grounding an LLM's response in retrieved documents to reduce hallucination.
Guardrails
The layer of policies, filters and validators that constrain LLM outputs to safe, on-brand, on-topic responses.