Prompt engineering emerged as a discipline once developers realized that LLM output quality varied enormously with input phrasing. Adding instructions like 'think step-by-step,' 'respond in JSON,' or 'use the format below' often improved results by 30-50% on benchmarks. Common techniques include few-shot prompting (showing examples of input/output pairs), chain-of-thought prompting (asking the model to reason out loud), role-prompting ('you are an expert legal editor...'), and structured output (JSON schemas, XML tags). For developers, prompt engineering is half of getting LLMs to behave reliably; for users, it's the difference between 'this AI is useless' and 'this AI is incredible.' By 2026, the field has matured into pattern libraries, prompt-management tools, and frameworks like DSPy that treat prompts as compilable artifacts.
СЛОВАРЬ
Что такое Prompt Engineering?
The practice of crafting input text (prompts) to get the best output from an LLM. A vague prompt gives vague answers; a structured prompt gives precise ones.
СВЯЗАННЫЕ ТЕРМИНЫ
LLM (Large Language Model)
An AI system trained on massive text datasets to predict and generate human-like text — the technology behind ChatGPT, Claude, Gemini, and most modern AI chatbots.
Few-shot Prompting
Showing an LLM 1-5 examples of input-output pairs in the prompt, before asking it to handle a new input — dramatically improves accuracy.
Chain-of-Thought (CoT) Prompting
Asking an LLM to 'think step by step' before answering — significantly improves performance on reasoning tasks.
System Prompt
A high-priority instruction given to an LLM at the start of a conversation — defines the assistant's role, constraints, and persona.
Назад к Словарь ИИ