Prompt Engineering

Appears in 2 papers · 4 tutorials

The practice of carefully designing the text prompt to get better outputs from a language model.

As used in Paper 12 — Language Models are Few-Shot Learners →

The practice of carefully designing the text prompt to get better outputs from a language model. Includes choosing the number of examples, the format (bullet points, line breaks, etc.), the phrasing of instructions, and adding role instructions like "You are a sentiment classifier."

As used in Paper 14 — Chain-of-Thought Prompting Elicits Reasoning in Large Language Models →

The practice of carefully crafting input prompts to achieve desired model behavior without changing model weights. CoT is fundamentally a prompt engineering technique — no model retraining required. The quality of CoT examples (clarity, step size, coverage) significantly affects performance, making prompt engineering critical.

As used in AI Agents →

The craft of writing prompts that get good results.

As used in Prompt Engineering →

The craft of wording prompts — with structure, examples, and constraints — to get reliable, high-quality results from a model.

As used in Retrieval-Augmented Generation (RAG) →

Wording the prompt well (examples, format, step-by-step) to steer the model within one request.

As used in AI Production Engineering →

The craft of writing effective instructions for an LLM. Important but only the start of production work. (Mod 1)

Paper 12 — Language Models are Few-Shot Learners → Paper 14 — Chain-of-Thought Prompting Elicits Reasoning in Large Language Models → AI Agents → Prompt Engineering → Retrieval-Augmented Generation (RAG) → AI Production Engineering →