Monitoring Agent Behavior
Heads up... You’re accessing parts of this content for free, with some sections shown as text.
Heads up... You’re accessing parts of this content for free, with some sections shown as text.
Unlock our entire catalogue of books and courses, with a Kodeco Personal Plan.
Unlock now
Once you know your assessment metrics, you must learn how to monitor them. If you have a complex graph with many nodes and LLM calls, it can be hard to track down errors when your agent isn’t behaving as you want it to. You have several tools to help with this, though.
Logging
Printing output messages in the notebook is the most direct way to gauge what’s going on in your AI agent workflow. So far in this module, you’ve been using print statements. However, you can also use the standard Python logging library for more granular control. This lets you set various logging levels or send output to a file instead of the console.
Step-by-Step Execution
JupyterLab has a debugger that lets you set breakpoints:
Streaming Output
LangGraph natively supports streaming output. This allows you to see what’s happening at each step along the way. Rather than calling app.invoke, you call app.stream:
Commercial Options
The makers of LangChain and LangGraph have released those libraries as open-source software. However, they also provide commercial products to help debug your AI agent app.
LangSmith
LangSmith lets you see information about the various nodes your graph traverses during execution in a nice visual format.
LangGraph Studio
LangGraph Studio is still in Beta and doesn’t support all platforms, so this lesson won’t cover it in depth. However, it looks like a promising way to interact with your graph more visually and intuitively. The following is a clip from one of their documentation images:
User Feedback
Low-tech monitoring solutions are just as important or even more important than high-tech ones. You should be collecting feedback from your users about where the pain points are with your agent: