Yeah, we've noticed it overthinks simple tasks that could be solved with a single table scrape. The agent architecture is built for complex, multi-source problems so it overengineers straightforward queries.
Working on better task classification upfront to route simple requests more directly.
Quickly hit your limits but on a complex dataset requiring looking at a lot of unstructured data on a lot of different web page, it seems to do really well!https://hn.webhound.ai/dataset/c6ca527e-1754-4171-9326-11cc8...