Post

In my quest to understand the true nature of an Agent I have been thinking a lot about the loop and the actions and the environment. And I think i see where we're headed next. Agents are not going to be like chatbots. They are going to be like programming languages come alive.

expanso🍝

@ment.tools

Under this kind of paradigm, how much are the sub-agent invocations/function-calls complete vs condensed context dumps? How hard would it be for the ‘main loop’ to pull reasoning for why decisions were made by child agents?

6/2/26, 11:47 pm0 reposts2 likes

‏ deepfates

@deepfates.com.deepfates.com.deepfates.com.deepfates.com.deepfates.com

7 Feb

currently they are not transparent, intentionally I think, to preserve the non-leaky abstraction. I'm interested in what happens if the traces are large to the context as well though...