Two different choices
When someone asks “which AI should I use for coding?”, they are usually mixing two decisions:
-
Tool: where you work. It can be an ADE, an IDE, a CLI, a cloud app, an editor with a plugin, or a prompt-to-app platform.
-
Model: the brain that generates the answer. It might be from the GPT, Claude, Gemini, Kimi, Llama, Gemma, DeepSeek, GLM, or another family.
These layers combine, but they are not the same thing. Cursor and Open Code are tools. GPT 5.6, Fable 5, Gemini, and Kimi are example brains.
The simple rule: tool is the environment. Model is what “thinks”.
Four work surfaces
Every week a new tool promises to revolutionize how you program. Instead of listing everything that exists, think in four surfaces:
-
AI-integrated IDEs: classic editors with an AI layer in the editing flow. Autocomplete, inline chat, and suggestions while you type. AI assists; you stay at the center. Examples: VS Code with GitHub Copilot, JetBrains AI Assistant, Kimi Code for VS Code.
-
ADEs (AI Development Environments): environments built around the agent. Editor, terminal, and integrations exist so the agent can read the repo, edit multiple files, run commands, and iterate with validation. Examples: Cursor, Windsurf, Google Antigravity, Zed, Kiro.
-
AI CLIs: command-line tools that read files, run commands, and make changes directly in the terminal. Examples: Claude Code, Codex CLI, OpenCode, Kimi Code, GitHub Copilot CLI.
-
Cloud apps and agents: you send a well-described task, the tool works in an isolated environment, researches the repo, proposes a plan, works on a branch, and returns a diff or pull request. Examples: Codex (cloud), Google Jules, GitHub Copilot coding agent, Devin.
The boundary is getting blurry. The same vendor shows up in the terminal, the editor, and the cloud. Categories still help, but the main question is not “which tool is best?”. The question is: which surface removes the most friction for this task?
In cloud agents, an emerging pattern is Research → Plan → Code → Review: research the repo, propose a plan, execute on a branch, and only open a PR after human review. No vendor owns that flow, but more tools converge on it.