Coding agent
Definition
A coding agent is an AI agent that works directly in a computer's files and command line: it reads, creates and edits files and runs commands based on plain-English instructions. Despite the name, it can do most file-based work, such as cleaning up spreadsheets or building a small app.
By Ronan Liedmeier, fractional head of growth and course author · Published 17 October 2026 · Last updated 17 October 2026
Also called: agentic coding tool, computer agent
With a chatbot you copy data into a chat window. A coding agent opens the files where they already sit, which makes jobs across hundreds of files practical for people who don't write code. Claude Code is one example.
How it works
You start the agent in a folder and describe the job and what "done" looks like. It reads what is there, proposes a plan, then edits files and runs commands in a loop, checking its own output as it goes. Claude Code's documentation describes this as an AI that can read files, run commands and make changes while you watch, redirect it or step away. Permission settings decide which actions need your approval first.
A second level is building small internal apps from a description. That works when the scope stays small, such as one job and a few screens.
Example
An analyst has 40 monthly sales exports in one folder, each with slightly different column names. She copies the folder and asks a coding agent to merge the copies into one spreadsheet and write a log of every column it renamed. Reading the log, she spots one column mapped to the wrong field and has the agent redo that step.
Common mistake
Pointing the agent at your only copy of important files with every action auto-approved. Work on a copy, keep approvals on for anything that moves or deletes files, and ask the agent to archive files instead of deleting them.
Learn it in AI Academy
- Coding Agents for Non-CodersBeginner · 14 min
- Coding Agents for Non-Devs, Level 2Advanced · 16 min
Related terms
- Claude Code
- Claude Code is Anthropic's AI agent that works inside your files and terminal: it reads a project, edits files, runs commands and connects to other tools. Anthropic built it for software work, but it also handles other tasks made of files, APIs and repeatable steps.
- AI agent
- An AI agent is an AI system that works toward a goal by choosing its own next steps: it picks a tool, uses it, looks at the result and repeats until the task is done. You set the goal and the limits, and the agent works out the path.
- Agent harness
- An agent harness is the software wrapped around an AI model that turns it into a working agent: it supplies the tools, file access, permissions, memory and the loop that chains actions together. The model does the reasoning; the harness decides what it can see and do.
- Human in the loop
- Human in the loop is a setup where an AI system pauses at set points so a person can approve or correct its work before it takes effect. It is used for actions that are hard to undo, such as sending emails to customers or moving money.