Prompting & Inference
Prompt Engineering
The practice of wording and structuring prompts to get better, more reliable results from a model.
Prompt engineering is the craft of shaping what you ask a model so it gives you what you need, through clear instructions, useful context, examples, and structure. It matters because small changes in phrasing can produce large changes in output quality. As models improve they need less of it, but for anything high-stakes or repeated, deliberate prompting is still what separates a flaky result from a dependable one.
Reference: Wikipedia: Prompt Engineering
Related terms
Prompt
The input you give a generative model, usually instructions or a question, that tells it what you want.
Few-Shot Learning
Guiding a model by including a handful of examples in the prompt so it can follow the pattern.
Chain-of-Thought
Prompting a model to reason step by step, which tends to improve its accuracy on hard problems.
System Prompt
A behind-the-scenes instruction that sets a model’s role, rules, and tone for an entire conversation.