Agent Hand-Off Prompt: Passing Work Between Specialist Agents
Write the message format one agent sends to another so nothing is lost.
Added October 15, 2026. Written with AI assistance and checked for clarity and placeholders; not reviewed by a lawyer, accountant, clinician or other professional. How these prompts are made
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
Write a hand-off protocol for agents that pass work to each other. The agents and their roles: [AGENT_ROLES]. A typical task that crosses agents: [CROSS_AGENT_TASK]. The information that is often lost: [LOST_INFORMATION]. Define a hand-off message with fields: goal in one sentence, current state, work done (with links or ids), decisions and the reasons, constraints and permissions, open questions, expected output format, deadline, and what to do on failure. Provide the full text of the prompt each agent receives to read a hand-off and the checklist to confirm understanding before starting (restate the goal and list assumptions). Add rules for avoiding loops (maximum hand-offs, a return path to a human), for not widening permissions, and for recording each hand-off in a log. Show a sample hand-off for the task above and the receiving agent's confirmation, then list the five most likely misunderstandings and the field that prevents each. Keep the format compact enough to fit in about 250 tokens.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.