Skip to content

Agents interact with the outside world through tools. When you ask an agent to search the web, write code, or make a phone call, it uses the appropriate tool behind the scenes. You see every tool call and its result inline in the chat.

Research & web

What you can askWhat the agent uses
"Search for recent articles about AI in healthcare"Web search
"Read this article and summarize it" (paste URL)Web fetch or browser
"Go to this website and fill out the contact form"Browser automation
"Take a screenshot of this page"Browser automation

Code & files

What you can askWhat the agent uses
"Run this shell command: ls -la"Shell execution
"Write a Python script to process this CSV"Python execution
"Create a Node.js script to fetch data from this API"Node.js execution
"Read the report I uploaded earlier"File operations
"Generate a PDF report and give me the download link"File operations

Communication

What you can askWhat the agent uses
"Call this number and ask about my order status"Voice calls

Built-in capabilities

Some tools are used automatically by agents without you needing to ask:

How tools are assigned to agents

Each agent has a set of tool groups you can toggle on or off in the agent settings. You choose which tools each agent needs. A research agent might only need web search and browsing. A coding agent needs shell, Python, and file tools.

Some tools are always available to every agent (memory, file output, identity, messaging). The rest are configurable per agent.

Sandboxing

Code execution tools (shell, Python, Node.js) run in a sandboxed environment with restrictions on filesystem access, network connections, and execution time. This keeps your system safe even when agents run untrusted code.

See Sandbox for details on how sandboxing works and how to configure it.