Using an LLM to call tools in a loop is the simplest form of an agent. This architecture, however, can yield agents that are “shallow” and fail to plan and act over longer, more complex tasks. Applications like “Deep Research”, “Manus”, and “Claude Code” have gotten around this limitation by| LangChain Blog
This is our second post focused on UX for agents. We discuss ambient background agents, which can handle multiple tasks at the same time, and how they can be used in your workflow.| LangChain Blog
At Sequoia’s AI Ascent conference in March, I talked about three limitations for agents: planning, UX, and memory. Check out that talk here. In this post I will dive deeper into UX for agents. Thanks to Nuno Campos, LangChain founding engineer for many of the original thoughts and analogies| LangChain Blog
The fourth installment in our "In the Loop Series," in which we talk about what planning means for an agent and how to improve it.| LangChain Blog
The second installment in our "In the Loop" series, focusing on what cognitive architecture means.| LangChain Blog