Thinking of hot-take blogs to write next – which seem most interesting: – Why LLM apps should be either a single LLM call or complex agent
– Multi agent patterns
– Single agent → multi agent → LangGraph
– Updated agent UX takes other? (prev blogs: https://
blog.langchain.dev/tag/in-the-loo
p/
…)

→ View original post on X — @hwchase17,