How to Build an AI Agent Prompt

Define an agent’s objective, tools, decision loop, stopping conditions, and escalation rules.

이 프롬프트는 현재 영어로 제공됩니다. 인터페이스는 선택한 언어로 유지됩니다.

Give the agent a bounded objective Describe the outcome and who owns the final decision. Avoid open-ended mandates that encourage unnecessary actions.

Define tools and authority List what each tool can do, when it may be used, and which actions require confirmation. Prompt rules complement rather than replace actual permission controls.

Make the loop visible A useful pattern is observe, plan, act, verify, and either finish or revise. Require the agent to use tool results as evidence and to handle errors explicitly.

State stopping conditions Define completion, retry limits, budget limits, and when to ask a person. Test malformed tool output, unavailable services, conflicting instructions, and attempts to expand scope.