Agent demos are good at showing the happy path.
Real workflows are less polite.
Fields change. Labels are ambiguous. The page loads slowly. A required answer depends on context the agent does not have. The user wants help, but not surrender.
That is why I keep coming back to reliability as a product problem, not only a model problem.
An agent that works in the real world needs state tracking, failure memory, recovery paths, and a clear sense of when to stop and ask.
The handoff is not a weakness. Sometimes it is the feature that keeps the system trustworthy.
The same pattern shows up across different contexts. In narrative systems that need to hold story state across scenes. In persona agents that need to stay consistent over time. The surface looks different. The underlying problem is the same.