How do you implement "Long-Term Memory" for an agent so it remembers a user's preference from a conversation that happened three weeks ago?

What does a production-grade observability stack for AI agents look like? What metrics, logs, and traces are essential? How would you debug a scenario where an agent produces correct outputs 95% of the time but fails unpredictably?

When would you store a summary of a document in the vector DB but retrieve the full text for the LLM?

When would you use a "Manager Agent" to delegate tasks to "Worker Agents" rather than having one single agent do everything?