AI agent
Also called coding agent or agentic AI
An AI model that works toward a goal on its own by planning, using tools, checking the results, and repeating until the task is done.
Fix the signup form so new users can create an account. Reproduce the bug in the preview first, find the cause, make the smallest fix, then sign up with a test email to confirm it works. Ask me before changing the database schema.
Paste into Layerwise or any AI coding tool.
What is AI agent?
An agent takes a goal, such as "fix the broken signup form," and works through it in a loop. It plans, reads the files it needs, edits code, runs the app or the tests, checks what happened, and goes around again until the job is done or it needs your input.
Coding agents act through tool calls, so they can do what you would do at a computer: search the project, open files, run commands, and read errors. That loop lets them catch and fix many of their own mistakes before they report back.
Give an agent a clear goal and a way to check success, such as "the tests pass" or "the page works at phone width." Review what it changed, and decide which actions need your approval, such as commands that reach the network or edits outside the project.
Related terms
All termsTool call
A request from an AI model to run a named action, such as reading a file, searching, or running a command, whose result goes back to the model.
Plan mode
A mode in AI coding tools where the agent researches the project and proposes a step-by-step plan for your approval before it edits any files.
MCP
The Model Context Protocol: an open standard that connects AI apps to outside tools and data, such as files, databases, and design apps.
Vibe coding
A way of building software by describing what you want to an AI model and steering the result in conversation, without writing the code yourself.
Build it with Layerwise
Describe your app, watch it run in a live preview, and publish it with a database, storage, and sign-in built in.