By
–
Sam on where decision models fit in a harness and how to use Jev with LangChainhttps://t.co/TgYoOiLJXd
— Harrison Chase (@hwchase17) 8 octobre 2026
https://t.co/pRYMKQuLGq
Sam on where decision models fit in a harness and how to use Jev with LangChain https://
langchain.com/blog/building-
a-harness-with-jev
…
By
–
interrupt london is next tuesday really looking forward to hearing from Orange and OVO on what's actually working with agents in production. we're also running hands-on workshops on Deep Agents and Engine
By
–
One cool thing deepagents now supports: dynamically loading tools when is a skill is loaded Some skills require specific tools that you may not always want to have available. This now allows you to pair them With openai/anthropic models, it’s possible to do this in a way where
By
–
cool to see cognition doing "dreaming" – memory needs an offline cleanup loop, not just better retrieval, otherwise stale records pile up
— Harrison Chase (@hwchase17) 5 octobre 2026
open q is how inferred memories get validated before the agent uses them
glad it's an open standard too – memory should be open…
cool to see cognition doing "dreaming" – memory needs an offline cleanup loop, not just better retrieval, otherwise stale records pile up open q is how inferred memories get validated before the agent uses them glad it's an open standard too – memory should be open
By
–
we're seeing our coding agent costs decrease significantly for second month in row longer blog on this later, but three quick steps we took 1/ cost visibility. you cant control what you cant measure. Start tracking everything to langsmith. This gives us super granular
By
–
specialized agents or one mega agent?
— Harrison Chase (@hwchase17) 3 octobre 2026
we're having this debate internally… https://t.co/xlDRNi3bEg
specialized agents or one mega agent? we're having this debate internally…
By
–
cool project by @dbreunig in langchain this is ModelRouterMiddleware – jev reads the first message, picks the model, and that model handles the whole run jev is cheap enough that you can also re-pick after each tool result with a custom hook docs: https://
docs.langchain.com/oss/python/int
egrations/providers/typesafe#model-routing
…
By
–
good pattern from this google paper the verifier starts from a clean context, so the explorer's reasoning can't talk it into a bad proof so the explorer can try wild ideas and the verifier tosses the wrong ones same reason deepagents subagents get their own context
By
–
every agent team ends up wanting its own review ui over their traces – LangSmith Custom Apps lets you build it on your own data and ship it right into the workspace
By
–
Memory is hard to get working well, especially in a company setting
— Harrison Chase (@hwchase17) 2 octobre 2026
Making some improvements to how we memory in managed deepagents! https://t.co/dHRQ2JhRV4
Memory is hard to get working well, especially in a company setting Making some improvements to how we memory in managed deepagents!