Hey team,
I’m trying to pass something from an AI agent to a headless browser node (the URL). I can’t work out where it’s meant to go or how it’s meant to be formatted though. When talking to the AI in the docs… It says this:
I can’t see any connection line anywhere though? Is the AI hallucinating? It keeps saying I need to put it into the input field for the headless browser.
I had thought it’d be added like this:
Hello! I’ll clarify how the operator is supposed to work within the code and get back to you.
In the meantime, you might want to try our new Browser Use node, which can perform more advanced actions during web surfing.
Alternatively, you can use Firecrawl, which also works exceptionally well.
While I wait for a response, here’s another example of a super quick workaround that will allow us to use this here and now, through an additional scenario
Currently, the execution of nodules as tools is unfortunately not possible due to architectural limitations. However, this issue will be resolved in the future
Cool thanks Raian. I’ve tried using Firecrawl… But the issue that I had is if the URL doesn’t exist (I’m trying to build an enrichment agent for Scoro) then it just returns a big ole error which seems to be just stopping the whole process rather than letting it try something else. For example… One of the companies I was trying the enrichment with was a client of ours EIT. Their domain is https://www.eit.ac.nz but they only have the www subdomain goes to their website, without the www it errors (stupid I know). So when I tried that last it tried going to eit.ac.nz and then errored out and stopped the agent chain.
May I request some documentation around these nodes because I can’t find anything in the docs
This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.
