Personal agents now explain their tool calls, visualized

Arne Strickmann @arnestrickmannOriginally posted 2026.10.27

Open original on X

We now force personal agents like @bot, @Muse or @instinct to tell us why they want to make tool calls. This lets us group and visualize the background work agents perform, which is usually opaque, and see which agent did what, and when. It's pretty cool to expose this data back to the agent and ask "why did instinct change this document" or "what prompted muse to write this email". @hkonsti_ 🫡

This post quotes another post: “Sriram wants an overseer agent for his personal agents”