Prompt Engineering

The practice of designing inputs to LLMs to reliably produce useful outputs — through structure, examples, role-setting and constraints.

Prompt engineering is how you control an LLM without changing its weights. Effective techniques include explicit role and task definition, few-shot examples, output schemas (JSON, XML), step-by-step reasoning prompts, and clear acceptance criteria.

Modern systems combine prompting with structured tools: function calling, JSON mode, and constrained decoding force the model into machine-readable output. Inside agents, prompts are layered — a system prompt, a task prompt, retrieved context, and tool descriptions are stitched together for each step.

As models get stronger, the centre of gravity is shifting from clever phrasing to good context engineering: giving the model the right information, tools and examples for the task.

Related terms

More to explore

Other wiki entries that touch on Prompt Engineering.