Skip to content
ReviewRamble

The weekly brief

AI, reviewed, in your inbox.

  • New reviews of tools, models, MCP servers and repos, with the verdict up front
  • Re-checked prices and ratings when something changes
  • New analysis pieces as they are published

Models, agents, MCP servers and the tools actually worth your time.

One email a week. Unsubscribe with the link in any brief. How we use your email

AI code editor

An AI code editor is a code editor or IDE with language models built in, offering completions, chat about the codebase and an agent mode that can plan and make changes across many files.

Also called: agentic IDE, AI IDE

By Divya Sharma · Checked Nov 15, 2026 · How we review

AI code editors put the model where the developer already works. Most began as forks or extensions of an existing editor, such as VS Code, and added AI features on top.

Common features

- Inline completion that predicts the next lines as you type. - Chat that can see your files and answer questions about the code. - Inline edits: select code, describe a change, review the diff. - An agent mode in which a coding agent plans a task, edits files and runs commands, pausing for your approval.

Agentic IDE

"Agentic IDE" describes editors built around that agent mode rather than around completion. Kiro, for example, adds specs, where the agent first writes requirements, a design and a task list, and hooks that run actions when files change or tasks finish. This is a form of spec-driven development.

How it differs from a terminal agent

A terminal agent such as Claude Code runs outside the editor and works through the shell. An AI code editor shows changes as diffs in the editor and keeps you closer to each edit. Many developers use both. Popular editors include Cursor, and GitHub Copilot adds similar features to existing editors.

Limits

The editor makes AI changes easy to accept, which makes them easy to accept without reading. Review agent edits as you would a colleague's.

Related terms

Coding agent
A coding agent is an AI agent that works on software directly: it reads a codebase, edits files, runs commands and tests, and repeats until a change works, rather than only suggesting code for a person to paste.
Vibe coding
Vibe coding is building software by describing what you want to an AI model and accepting the code it writes without reading or reviewing it, judging the result only by whether the program seems to work.
Spec-driven development
Spec-driven development is a way of working with coding agents in which you first write a specification of what to build and why, then have the agent turn it into a plan, a task list and finally code.
Agent hooks
Agent hooks are user-defined commands or scripts that a coding agent runs automatically at set points in its work, such as before a tool call or after a file edit, to check, block or extend what it does.
Agent instructions file (AGENTS.md)
An agent instructions file is a Markdown file in a code repository, such as AGENTS.md or CLAUDE.md, that a coding agent reads at the start of a session to learn the project's commands, conventions and rules.

Sources