Why do we typically include a 10–20% overlap between text chunks? What happens to the retrieval quality if the overlap is zero?

AI agents often rely on external tools/APIs. How would you design a system that ensures robustness when these dependencies are unreliable or slow?

If an agent can take real-world actions (e.g., execute code, send emails, trigger workflows), how do you enforce safe behavior in production?

Agents generate a lot of "internal thought" and tool logs. How do you keep the context window from filling up with irrelevant logs during a long multi-step task?