
Gave it a quick shot right now, and gonna be honest - while the premise seems nice, the sample project is very transparently AI slop generated with a prompt that, I can only assume, included an instruction like “for every sentence that doesn’t include a whimsical quip, I’m gonna kill a kitten”. It is absolutely grating to read. I don’t care if you do that in your marketing copy, but keep that shit out of technical documentation, it’s annoying, it’s distracting, and it’s turning me off the entire project. Like wtf is this:



That depends on the harness though. In the plain model output it will be clear if a tool call happened, and it depends on the application UI around it whether that’s directly shown to the user, or if you only see the LLM’s final response based on it.