Agent Handoff
The process of transferring a task, conversation, or workflow from one AI agent to another—or from an AI agent to a human—while preserving full context. Effective handoffs include conversation history, resolved entities, attempted actions, and the reason for the transfer. Poor handoffs force the receiving agent or human to start from scratch, frustrating users and wasting time. Handoff protocols are a core feature of multi-agent systems and human-in-the-loop architectures.
Written by Max Zeshut
Founder at Agentmelt · Last updated Sep 9, 2026
Example
A support agent handles a billing question but detects the customer also has a technical issue. It hands off to a technical support agent with the full conversation, the customer's account details, and a summary: 'Billing resolved—customer also reports intermittent API timeouts since Tuesday.'
Frequently asked questions
- What makes a good agent handoff?
- A good handoff transfers three things: context (what happened so far), state (what data has been collected), and intent (why the handoff is happening and what the receiving agent should do next). The user should never have to repeat information.