This workflow with an AI agent is designed to navigate through a webpage to retrieve specific types of information (in this example, social media profile links).
The agent is equipped with two tools:
- Text tool: to retrieve all the text from the page,
- URLs tool: to extract all possible links from the page.
🔧 You can edit the prompt and JSON schema connected to the agent to return data other than social media profile links.
📂 This workflow uses Supabase as storage (input/output). Feel free to replace it with any other database of your choice.
How it works?
The workflow uses the input URL (website) as a starting point to retrieve the data (e.g., example.com). Using the "URLs tool", the agent retrieves all links from the page and navigates to them.
For example, if you want to retrieve contact information, the agent will try to find a subpage that might contain this information (e.g., example.com/contact) and extract the information using the text tool.
Set up steps
- Connect the database with input data (website addresses) or pin sample data to the trigger node.
- Configure the crawling agent to retrieve the desired data (e.g., modify the prompt and/or parsing schema).
- Set credentials for OpenAI.
- Optionally, split agent tools into separate workflows.
Other Workflows like this one
Your connected stack awaits to automate AI workflows with 24-7 uptime performance and engagement