Harrison Chase argues that as models get smarter, agent harnesses shift from deciding for the model to offering capabilities to it. In deepagents, each subagent gets its own model, tools, and permissions, while the main loop chooses which subagents to spawn and when.
great writeup by @pirroh
harness doesn't disappear as models get smarter - it shifts from deciding to offering
in deepagents you give each subagent its own model, tools, and permissions - the main loop picks which to spawn and when
docs: https://docs.langchain.com/oss/python/deepagents/subagents
https://x.com/i/article/2104968643021045760View quoted post on X
Source: Harrison Chase · x.comPublished · added here
