Use API nodes within chains
Make external API calls at any point in your Prompt Chain to integrate with third-party services. The API node lets you validate data, log events, fetch information, or perform any HTTP request without leaving your chain. Simply configure the endpoint, method, and payload to connect your AI workflow with external systems.
Configuring API nodes
Create an API node
- Drag from the start node or any existing node to create a connection
- Select API from the node type menu
API node editor
Configure HTTP API requests with standard parameters and custom scripts. The editor provides a complete interface to set up your API endpoints.
Request configuration
- Select HTTP methods (GET, POST, PUT, DELETE)
- Add request headers
- Configure query parameters
- Define request body
Advanced options
- Write pre-request scripts to modify request parameters.
- Add post-response scripts to transform API responses.
- Test API calls directly from the editor.
Select output field (optional)
Click run to test your API endpoint. By default, the entire response body is set as the node output. To use a specific field from the response use the Select output field dropdown to choose the desired response field.
Debug AI agent errors step by step
Identify and fix errors at each step of your AI workflow with detailed diagnostics
Deploy Prompt Chains
Quick iterations on prompt chains should not require code deployments every time. With more and more stakeholders working on prompt engineering, its critical to keep deployments of prompt chains as easy as possible without much overhead. Prompt chain deployments on Maxim allow conditional deployment of prompt chain changes that can be used via the SDK.