what he said 🗣️ the very best agents today obsessively tailor the harness layer around the model I’m looking at you “5 things I learned fro…

what he said 🗣️ the very best agents today obsessively tailor the harness layer around the model I’m looking at you “5 things I learned from the Claude code leak” bros 👀 orchestration patterns, tool descriptions, skill body (should it mention another skill?), PROMPTS!!, middleware/hooks all the details matter, it’s almost artisanal 👨🏼‍🍳 go try deepagents 😴 and make evals and trace them in LangSmith to make them better 😴😴 im excited about agent harnesses because i think are the first stable agent abstractions we can build on top (which is why we're investing so much in deepagents) we always wanted to run llms in a loop and have them call tools (remember autoGPT? that's all that was) but the models…

'Claude Code isn't magic. The harness layer is just software, and software is something any dev can shape to fit how they want to work.' Che…
the real future of the very best vertical products is Model/Harness Choice + Openness easy to deploy infra is nice (great release from Ant) …
This is why you need model agnostic harnesses
Open Harness, separated from model providers is a critical architectural pattern.
It seems like the day has come to leave Anthropic. Initially, I loved Claude Code. It was a good harness and a simple TUI... and I had learn…
You want a strong opensource and fully customisable harness?! None other than langchain’s deepagents. Try it yourself if in doubt.

Source: Harrison Chase (X) | 2026-04-10

Related