> ## Documentation Index > Fetch the complete documentation index at: https://docs.coderabbit.ai/llms.txt > Use this file to discover all available pages before exploring further. # Fix findings with your AI agent > Send CodeRabbit findings and nitpicks from the IDE extension to GitHub Copilot, Cursor, Windsurf, Claude Code, Codex, opencode, Cline, Roo Code, Kilo Code, or Augment Code with Fix with AI, then review the result. **Fix with AI** sends a finding's instructions to a coding agent you choose, such as your editor's chat, Claude Code, or Codex. The agent makes the change in your workspace, and you review it as you would any other edit. With the default settings, **Fix with AI** in VS Code opens VS Code chat in agent mode and submits the prompt right away, so the agent can start editing your files at once. Cursor and Windsurf paste the prompt into their chat without sending it, and other editors, such as Antigravity, copy it to the clipboard. To read the prompt before an agent runs, turn off `coderabbit.autoStartTask`, or [choose another agent](#choose-your-agent). This is different from CodeRabbit's Coding Agent (Turns a user request, a review finding, a coding plan or a failing CI check into a task that CodeRabbit's agent implements in the cloud, then delivers as a commit or a stacked pull request for you to approve.), which runs in CodeRabbit's cloud, and from **Fix with AI** in CodeRabbit Security. See [Names that collide](https://docs.coderabbit.ai/code.md#names-that-collide). ## Choose your agent Set `coderabbit.agentType` to the agent you use; see [Open the settings](https://docs.coderabbit.ai/ide/settings.md#open-the-settings). The default is `Native`. | `agentType` value | What happens | Starts on its own | | - | - | - | | `Native` | Uses your editor's built-in chat, such as GitHub Copilot in VS Code. See [What Native does in each editor](#what-native-does-in-each-editor). | In VS Code, when `coderabbit.autoStartTask` is on | | `Claude Code` | Runs `claude` with the prompt in a terminal named "CodeRabbit - Claude Code" | Yes | | `Codex CLI` | Runs `codex` with the prompt in a terminal named "CodeRabbit - Codex" | Yes | | `opencode` | Runs `opencode run` with the prompt in a terminal named "CodeRabbit - opencode" | Yes | | `Claude Code Extension` | Opens the Claude Code extension with the prompt filled in | No, you send it | | `Cline` | Starts a Cline task, or pastes the prompt into Cline | When `coderabbit.autoStartTask` is on | | `Roo` | Starts a Roo Code task, or pastes the prompt into Roo Code | When `coderabbit.autoStartTask` is on | | `Kilo Code` | Starts a Kilo Code task, or pastes the prompt into Kilo Code | When `coderabbit.autoStartTask` is on | | `Augment Code` | Pastes the prompt into Augment chat | No, you send it | | `Clipboard` | Copies the prompt to the clipboard, so you can paste it into any agent | No | Requirements by agent type: * **Terminal agents** (`Claude Code`, `Codex CLI`, and `opencode`) run in the editor's integrated terminal, which stays open for the next handoff. The command runs right away: `claude` and `codex` start an interactive session with the prompt, and `opencode run` runs the prompt once. If the agent from the previous handoff is still running in that terminal, the extension types the new command into it as input; exit the agent or close the terminal first to start a fresh run. The extension adds no permission flags, so the agent's own approval prompts apply. The agent's CLI must be installed and on your `PATH` on the machine where the extension runs, which is the remote machine in a remote window. The extension doesn't check for it: if the CLI is missing, the terminal shows your shell's error, and the finding is still marked "Fixed with AI". * **Extension agents** (`Claude Code Extension`, `Cline`, `Roo`, `Kilo Code`, and `Augment Code`) need that agent's extension. If it's missing, the extension offers **View in Marketplace**. `Claude Code Extension` needs Claude Code extension version 2.1.0 or later, below 3.0.0. If a handoff fails for any reason, the prompt goes to the clipboard so you can paste it yourself. In a workspace you haven't trusted, only your user values of `coderabbit.agentType` and `coderabbit.autoStartTask` apply, so a repository you clone can't choose which agent runs or whether it starts on its own. See [Restricted Mode](https://docs.coderabbit.ai/ide/settings.md#restricted-mode). ### What Native does in each editor | Editor | What `Native` does | | - | - | | VS Code, VS Code Insiders, VSCodium, Code - OSS | Opens VS Code chat in agent mode and submits the prompt to GitHub Copilot or another chat agent you have installed. When `coderabbit.autoStartTask` is off, it pastes the prompt into the chat without sending it. | | Cursor and Windsurf | Opens the editor's chat and pastes the prompt without sending it | | Antigravity, Kiro, Trae, Qoder, Positron, and other editors | Copies the prompt to the clipboard and shows "Codegen instructions copied to clipboard" | To have an agent start on its own in Cursor, Windsurf, or the other editors, choose a terminal agent, or `Cline`, `Roo`, or `Kilo Code` with `coderabbit.autoStartTask` on. ### Start the agent automatically or review the prompt first `coderabbit.autoStartTask` is on by default. It decides whether `Native` in VS Code, `Cline`, `Roo`, and `Kilo Code` start right away. Turn it off to read or edit the prompt before the agent runs. ## Fix one finding **1. Open the finding in the editor** In **Findings** or **Nitpicks**, select **Open in editor** on the finding. **2. Select Fix with AI** Select the sparkle **Fix with AI** icon in the comment thread's title bar. The icon appears only when the finding includes instructions for an agent. **3. Check the change** The agent edits your files. Review the change, then [review again](#review-fix-and-review-again) to check it. The finding is marked "Fixed with AI" as soon as the extension hands it off, including when the prompt only went to the clipboard. If the agent didn't make the change, select **Unresolve** on the finding in **Findings** to reopen it. ## Fix several findings at once After a review completes with unresolved findings, **Findings** shows a **Fix all issues** button: 1. Select **Fix all issues**. 2. Choose **Select files** or **Select comments**. 3. Pick the files or findings to fix. When the review also has unresolved nitpicks, **More fix options** appears next to **Fix all issues**. Choose **Fix issues and nitpicks** to include them, or **Fix issues only** to leave them out. In **Nitpicks**, **Fix all nitpicks** sends every unresolved nitpick, without asking you to pick. Everything you pick goes to your agent as one prompt, and every finding in it is marked "Fixed with AI". Select **Unresolve** on any finding the agent didn't fix. ## Review, fix, and review again 1. Make changes, yourself or with an agent, and commit. With `coderabbit.autoReviewMode` set to `auto`, every new commit starts the [automatic review](https://docs.coderabbit.ai/ide/review.md#review-automatically-after-each-commit) unless you cancel it, including commits an agent makes in a terminal. With `prompt`, a commit starts a review only when you answer **Yes** to the notification. 2. Hand the findings to your agent with **Fix with AI** or **Fix all issues**. 3. Review again. An automatic review starts only after a commit and covers committed changes, so commit the agent's edits, or start a review yourself with **Uncommitted changes** to check them before you commit. The next review covers only what changed since the last one. After an amend or a rebase, it covers the whole branch. See [Review again after more changes](https://docs.coderabbit.ai/ide/review.md#review-again-after-more-changes). The next review looks only at what changed since the last one and doesn't re-check earlier findings, so a finding that no longer appears isn't confirmed as fixed. See [Review again after more changes](https://docs.coderabbit.ai/ide/review.md#review-again-after-more-changes). Each review, including each automatic one, counts toward your [hourly limit](https://docs.coderabbit.ai/ide/review.md#hourly-limits). **Fix with AI** doesn't start on its own when a review finishes; you start each handoff. If you'd rather have your agent start reviews and read the findings itself, use the CodeRabbit CLI with [agent skills](https://docs.coderabbit.ai/cli/skills.md). To install both from the editor, run **CodeRabbit: Set up CLI and skills**; see [Set up the CLI and agent skills](https://docs.coderabbit.ai/ide/install.md#set-up-the-cli-and-agent-skills). ## What's next > **[Work with findings](https://docs.coderabbit.ai/ide/findings.md)** > > Apply suggestions yourself, ignore findings, or reopen ones the agent didn't fix. > **[Agent skills for the CLI](https://docs.coderabbit.ai/cli/skills.md)** > > Let your coding agent run CodeRabbit reviews itself with CodeRabbit skills. > **[Troubleshooting](https://docs.coderabbit.ai/ide/troubleshooting.md#fix-with-ai)** > > Find out why a handoff only copied to the clipboard or the agent didn't start. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.