Guide on how to best use AI to build custom integrations fast.
Building custom integrations for Nango is much faster when using AI tools. This guide shows you how to leverage Cursor or Claude Code to build high-quality integrations quickly.
First, make sure your Nango project is properly initialized:
Copy
Ask AI
# If you don't have a nango-integrations folder yetnango init --ai cursor# Navigate to your integrations directorycd nango-integrations# Ensure your environment is configured# Check that .env contains your NANGO_SECRET_KEY_DEV# Get your dev secret from: https://app.nango.dev/dev/environment-settings
When working with your AI assistant, provide clear, specific prompts:
Example prompt structure:
Copy
Ask AI
I need to build a Nango custom [SYNC/ACTION] for [PROVIDER_NAME] called [INTEGRATION_NAME].## Context- Provider: [provider-name]- Integration: [integration-name]- Type: [sync/action]- Test connection ID: [connection-id]## Additional details- **Output schema**: [describe the expected data structure]- **Field mapping**: - `api_field_name` → `nango_field_name` - other transformations (ex: dates)- **API Documentation**: [link-to-docs]- **Data source**: [specific API endpoint(s) to call]- **Error handling requirements**Please implement this step by step and use `nango dryrun <integration-name> <connection-id> --validation [--input '{...}']` to test.
Start simple: Begin with basic functionality and iterate
Test frequently: Ensure the agent is running nango dryrun after each significant change
Provide feedback: Give clear feedback on what works and what doesn’t
Stay focused: Keep prompts focused on specific tasks
Review thoroughly: Always review AI-generated code before deploying
By following this guide and leveraging AI assistance effectively, you can build robust Nango integrations much faster than traditional development approaches.
Assistant
Responses are generated using AI and may contain mistakes.