I have been continuing my experiments with ZeroClaw and its browser
integration. Most of my goals with AI are explainable AI. I want to be able to
see the tool calls that it makes to answer my questions. I want to know if the
query was properly grounded. To answer some of these questions I enabled otel
so I can see the tool calls in grafana, I also encourage the agent to use tools
in the prompts. However, using the browser seems to be a challenge for the
agent on a headless server (how do rpa tools do this stuff anyways?). I also
want to ensure that my use of AI is as private as possible for me. The most
important part of any summarizer/explainer is how did it come to this
conclusion.
After evaluating numerous claws in an attempt to build some kind of assistant
and wanting to see what all the hype was about, I have settled on
ZeroClaw. It’s neat because it’s written in rust, and is relatively new
and seems to have learned from several previous attempts. Although it seems
like there are several potentially malicious forks floating around. This is my
experience with it, and my absolute frustration with these AI solutions. Which
is mostly just the absolute laziness of the documentation or lack there of or
just not useful to the average consumer of it. This blog post is just a stream
of consciousness instead of being a well edited and separated blog post.