[Building Agents, 3] I Guess Handoff is the Most Important Feature

agents
software
ai
Author

Weyland Joyner

Published

February 10, 2026

The point of an agent is that it should have a tight, simple core loop for tool calling and returning a response to the user. At this level the tool call, or sequence of tool calls, is the unit of work. Once you get above this level of abstraction, you’re looking at the thread itself as the unit of work, and here’s where you get into some design decisions within the agent harness. What should we do to keep our threads short and focused?

I think what we want is a really well-designed handoff feature, where an external LLM summarizes the conversation and then passes that summary into your new thread. This is what I think Amp does on thread:handoff and I’m figuring out how to implement it myself.