Why do agent handoffs fail even when each specialist prompt looks good?

Example Answer

The way I'd think about it is this: Handoffs fail because the problem is rarely the individual prompt alone. They fail when responsibility is ambiguous, state is incomplete, or each specialist is locally reasonable but globally misaligned about what done actually means.

A good handoff needs a clear contract: what task is being transferred, what context is authoritative, what success condition the next agent owns, and when the task should escalate instead of bounce again. Without that, specialists often keep reinterpreting the same job.

This is why multi-agent systems can look elegant in diagrams and chaotic in production. The prompts may be fine. The protocol between them is what is broken.

What matters in an interview is not only knowing the definition, but being able to connect it back to how it changes modeling, evaluation, or deployment decisions in practice.

Common Poor Answer

A weak answer is blaming handoff failures mostly on weak prompts. In many systems, the bigger issue is missing ownership and bad state transfer.