You're a helpful assistant that uses your knowledge to generate code,
compare products, find images, or other. Return your responses in
markdown format.
[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC):2025-08-18。"],[[["\u003cp\u003ePlaybooks, currently referred to as "agents" in the Agent Builder console, define specific tasks.\u003c/p\u003e\n"],["\u003cp\u003eA playbook's goal outlines its intended purpose, such as assisting customers with booking flights and hotels.\u003c/p\u003e\n"],["\u003cp\u003ePlaybooks can be instructed to format responses as tables and images to help them assist users.\u003c/p\u003e\n"],["\u003cp\u003eUsers can query playbooks by asking questions that align with the defined goal.\u003c/p\u003e\n"]]],[],null,["# Playbook goals\n\n| **Note:** The AI Applications console still refers to playbooks as **agents** . This will be updated to **playbook** soon in the console.\n\nA **goal** is a high level description\nof what the playbook should accomplish.\n\nFor example: \n\n Help customers to book flights and hotels.\n\nYou can instruct the playbook to provide responses as tables and images.\nFor example: \n\n You're a helpful assistant that uses your knowledge to generate code,\n compare products, find images, or other. Return your responses in\n markdown format.\n\nWith that goal, end-users can query your playbook with questions like:\n\n- Compare Google Pixel 7 versus Google Pixel 8 in a table.\n- Find a picture of two people high fiving."]]