Glossary

Prompt Engineering

Structuring instructions and context so an AI model produces reliable, useful output.

Prompt engineering is the practice of designing the instructions and context you give an AI model to get reliable results. For coding agents it includes clear task framing, relevant context, constraints, examples, and project-level instructions the agent should always follow.

As agents take on larger tasks, prompt engineering shifts from clever one-liners toward durable, reusable context — project instruction files, conventions, and guardrails that shape every run.

Learn more

Related guides on the Agents UI blog and related terms in this glossary.

Try Agents UI

A native terminal for AI coding agents with persistent sessions, SSH workflows, and built-in editing.

Download View on GitHub

Related

Context Window

The maximum amount of text (tokens) a model can consider at once.

AI Coding Agent

An AI program that autonomously reads, writes, and runs code to complete development tasks.

Agentic Coding

A workflow where an autonomous AI agent plans and executes multi-step coding tasks, not just single completions.

Prompt Engineering For Ai Coding Agents

Read the guide →

Configure Ai Coding Agents Project Instructions

Read the guide →