Skip to main contentBuilt-in tools are capabilities provided directly by the model providers that can be enabled for your agents. These tools allow your agents to perform specialized tasks like generating images, searching the web, and executing code.
Overview
The Agent Builder provides access to three built-in tools that leverage the native capabilities of supported LLM providers:
- Image Generation Tool - Generate images from text descriptions
- Web Search Tool - Search the web for real-time information
- Code Execution Tool - Execute code in a sandboxed environment
These tools are automatically handled by the model providers when enabled, requiring no additional configuration or setup.
To enable built-in tools for your agent:
- Navigate to your agent in the Agent Builder
- Click on the Tools tab
- Toggle the switch next to each tool you want to enable
- Save your agent configuration
Each tool can be enabled or disabled independently. When enabled, the agent will have access to that tool’s capabilities during conversations.
The Image Generation Tool allows your agent to create images based on text descriptions. This tool is useful for:
- Creating visual content from descriptions
- Generating illustrations or graphics
- Producing images for presentations or documents
The Web Search Tool enables your agent to search the internet for real-time information. This tool is useful for:
- Finding current events and news
- Looking up factual information
- Getting up-to-date data and statistics
- Researching topics that require recent information
The Code Execution Tool allows your agent to write and execute code in a sandboxed environment. This tool is useful for:
- Performing mathematical calculations
- Analyzing data
- Running code snippets
- Solving computational problems
- Generating code examples
Provider Compatibility
| Tool | OpenAI | Anthropic | Gemini |
|---|
| Image Generation | ✅ | ❌ | ✅ |
| Web Search | ✅ | ✅ | ❌ |
| Code Execution | ✅ | ✅ | ✅ |