Agents in Warp

Warp's agents are capable collaborators that help you write code, debug issues, and complete terminal workflows -- all from natural language prompts.

Describe what you want to do (you can even use your voice), and Warp’s agents will intelligently take action using your environment, codebase, and saved context to tailor their responses.

Agents can:

1. Write and edit code across single or multiple files.

2. Fix errors based on output or stack traces.

3. Execute shell commands and use the output to guide next steps

4. Automatically recover from common errors and retry with adjustments.

5. Learn and integrate with any tool that offers public docs or --help.

6. Leverage your saved Warp Drive contents, MCP servers, and Rules to provide tailored responses.

Give this prompt a try — open the below Prompt in Warp

Detect my current operating system. Based on that, navigate to the appropriate Warp themes directory (e.g. ~/.warp/ on macOS). 

Then, clone the official Warp themes repository using SSH ([email protected]:warpdotdev/themes.git) into that directory, following the structure and instructions provided in the repo’s README. If SSH does not work, try HTTPS (https://github.com/warpdotdev/themes.git) or via the GitHub CLI (gh repo clone warpdotdev/themes).

Agent Autonomy

Under Settings > AI > Agents > Permissions, you can control how much autonomy the agent has when performing different types of actions, such as:

• Reading files

• Creating plans

• Executing commands

• Calling MCP servers, and more

For each action, you can set the autonomy level to one of the following:

• Let the agent decide

• Always prompt for confirmation

• Always allow

• Never

You can also configure an allowlist and denylist for specific commands you always want to run—either with or without confirmation.

Managing multiple agents

You can run multiple agents in Warp simultaneously, monitor their status, and step in when needed—without losing track of what’s happening across your sessions. Each tab includes a status icon that shows the agent’s current state. All of your active agents are tracked in the Agent Management Panel, located in the top-right corner next to your avatar.

Agents will also notify you when they need input, such as permission to run a command or approval to apply a code diff. This lets you focus on other work, knowing you’ll be alerted when your attention is required.