The Unreasonable Effectiveness of an LLM Agent Loop with Tool Use

Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by mtaras on Friday May 16, 2025 @08:16AM (#44004504)

No, I personally don't have notes that would be valuable enough for the system I was looking for, so notes is just how I'm calling my agent's long-term memory. All I do is provide it with tools to message me and manage it's own notes, useful context (recent chat history, its saved notes, calendar events, etc), and it can act upon the info.

The elegance of the system unfolded when I realized that I can not specify any interaction rules beforehand — I just talk to the system, it saves notes for itself, and later acts upon them. I've only started testing it, but so far it's been working as intended.

[ Parent | on HN ]

Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by triangleman on Friday May 16, 2025 @10:20AM (#44005858)

What do you mean by "message me" and "later" in this context?

[ Parent | on HN ]

Re:The Unreasonable Effectiveness of an LLM Agent Loop with ... by mtaras on Friday May 16, 2025 @10:27AM (#44005930)

"Message me" is through a bot in my main messenger app, so the agent is just a chat window for me. "Later" happens per my requests, and agent has an ability to do something later because I just automatically invoke it on a schedule periodically, and ask it "check notes and chat history — do you need to do something, like message the user to remind them of something", and agent has the message_user tool to do that (that goes to the messenger bot API). Or it can decide to do nothing.

[ Parent | on HN ]