Codersarts Blog.

Large language models are excellent at understanding intent and generating language — but they don't natively know what the temperature in London is right now. The solution is tool use (also called function calling): you define a structured tool specification, register it with the LLM, and when the model needs live data it emits a special tool_use message instead of a text response. Your backend intercepts that signal, calls the real data source, and feeds the result back int

Want your chatbot to remember what you said earlier? In this beginner-friendly guide, we build on our previous LangGraph chatbot and add memory using MemorySaver. Learn how to persist conversation history, manage sessions using threads, and inspect state — step-by-step.