Hey, this is Lance. I want to talk a bit about memory patterns for agents, focusing specifically on deep agents. Now, you might think about memory in two different ways.Explicit updating of agent memory and implicit updating of agent memory. Let me talk about the first one. So, explicit updating agent memory, you can see a great example of right here.This is the cloud code change log. This is recent yesterday. So cloud code recently removed this pound shortcut which you could previously use for updating mem ...

Hey, this is Lance from Langchain. I want to talk of a few general context engineering principles and how they show up in various popular agents like manis like cloud code and also in our recently released deep agents package and CLI. So first agent can be simply thought of as an LLM calling tools in a loop. An LLM kind of makes a tool call.Tool is executed. observation from a tool goes back to the LM and this continues until some termination condition. Now the length of tasks that AI agents can perform is ...