AI Agent
An AI that does not just answer, it acts: reads files, runs tools, makes changes, and works toward a goal across multiple steps with limited supervision.
What it is
An AI agent is a model that can take actions, not just produce text. Instead of only answering a question, it can read your files, run commands, edit code, check the result, and keep going until a goal is met. Claude Code is an agent: you describe an outcome, and it works through the steps to get there.
Why this matters for designers
This is the shift behind βagenticβ design work. You move from asking for snippets to delegating outcomes: βbuild this section from the Figma frame and match our tokens.β Your job changes from writing every instruction to setting the goal, the constraints, and the quality bar, then reviewing the result.
How it works in practice
- You give the agent a goal and the context it needs.
- It plans, takes actions (read, write, run), and observes what happened.
- It iterates until the goal is met or it needs your input.