Changelog

Browser Automation: First Steps in Web Interaction for Your Agents

You can now enable your agents to perform basic web interactions with our initial browser automation release!

Browser Automation v0 introduces foundational web capabilities to Relevance AI, allowing your agents to navigate websites, interact with basic web elements, and extract text-based information. Choose between bringing your own Airtop API key or our managed solution using Relevance credits.

➡️ Navigate to websites – Direct agents to specific URLs and web pages

➡️ Basic form interactions – Fill out simple forms and submit data

➡️ Text-based data extraction – Capture text content from web pages

➡️ Flexible integration options – Use your Airtop API key or our managed solution

➡️ Early-stage functionality – Important limitations apply (see below)

Current Limitations:

• Cannot analyze charts, images, or visual elements

• No capability to solve CAPTCHAs

• Limited authentication support (requires sharing credentials in chat)

• Restricted to basic web interactions only

With Browser Automation v0, you gain access to initial web capabilities while we gather feedback to guide future development of more robust browser features.

To access Browser Automation, search for "Browser Use" under tool steps when configuring your agent workflow.

Try our first browser automation release today and share what additional capabilities would be most valuable for your use cases!