+ :::column span="":::

+ :::image type="icon" source="../../../../assets/icons/bot-requirement-agent.png" link="#bot-requirements-for-custom-engine-agents" border="false":::

+ :::column-end:::

+ :::column span="":::

+ :::image type="icon" source="../../../../assets/icons/white-bg.png" border="false":::

+ :::column-end:::

+ :::column span="":::

+ :::image type="icon" source="../../../../assets/icons/white-bg.png" border="false":::

+ :::column-end:::

+ * Instructional phrases, for example, 'if the user says X', 'ignore', 'delete', 'reset', 'new instructions', 'Answer in Bold', or 'Do not print anything'. [*Must fix*]

+ Microsoft Entra single sign-on (SSO) for message extension works in the same way as it does in Teams or Outlook. If you enabled SSO for your app, add the Office app Copilot’s client application identifier to the Microsoft Entra app registration of your bot in your tenant's App registrations portal.

+* The declarative agent must provide confirmation prompts aligned with user-initiated actions, using clear language that explicitly seeks the user's permission. [*Must fix*]

+ Confirmation prompt can be set by using `body` property in the `Confirmation` object in the function's Function capabilities object in the manifest. For more information, see [customizing confirmation text](/microsoft-365-copilot/extensibility/api-plugin-confirmation-prompts?branch=main&branchFallbackFrom=public-preview#customizing-confirmation-text).

+ | Pass example | Fail example |

+ | | |

+ | For a function which searches tickets - "Do you want to allow searching in Contoso?" "Do you want to allow searching for tickets?" | Do you want to proceed?" --> Does not indicate what the function does. |

+ | For a function which creates a new order "Do you want to proceed with creating a new order?" | Searches tickets" --> Does not seek permission |

+ | For a function which creates a new ticket: "Do you want to proceed with creating a new ticket?" | "Creates tickets" --> Does not seek permission |

+* For declarative agents, any action with consequences on the external system mustn't have `isConsequential` flag set as ΓÇÿFalseΓÇÖ. [*Must fix*]

+ For more details, see [overriding prompt behavior](/microsoft-365-copilot/extensibility/api-plugin-confirmation-prompts?branch=main&branchFallbackFrom=public-preview#overriding-prompt-behavior).

+ | Operation type | Actions | Expected value for `isConsequential` flag |

+ | | | |

+ | Create | Consequential | True |

+ | Read | Non-consequential | False or True |

+ | Update | Consequential | True |

+ | Delete | Consequential | True |

+ | Command description | Consequential function? | Expected value for `isConsequential` flag |

+ | | | |

+ | Returns a list of quest recommendations based on the user's interest. If there is no quote recommendations, then create a new one. | Yes | True |

+ | Returns a list of meditation recommendations based on the user's preferences. | No | False or True |

+ | Returns a list of quest recommendations based on the user's interest. If there is no quote recommendations, then create a new one. | Yes | True |

+[Back to top](#validation-guidelines-for-copilot-agents)

+## Bot requirements for custom engine agents

+A custom engine agent is a conversational Teams bot that must meet the following requirements:

+1. A custom engine agent must always contain conversation bot based on Large Language Models (LLMs) for seamless user interaction. [*Must fix*]

+1. The bot ID declaration as a custom engine agent node must be same as the bot ID defined in the bot node in the app manifest. [*Must fix*]

+1. User must be able to reference custom engine agent in Microsoft 365 Copilot and handoff chat experience in Teams. [*Good-to-fix*]

+1. Bot must include the following UX design components:

+ 1. An [AI label](/microsoftteams/platform/bots/how-to/bot-messages-ai-generated-content?tabs=after%2Cbotmessage#ai-label) that enables a user to identify that the message was generated using AI. [*Must fix*]

+ 1. A [feedback button](/microsoftteams/platform/bots/how-to/bot-messages-ai-generated-content?tabs=after%2Cbotmessage#feedback-buttons) that enables a user to provide positive or negative feedback to the agent's messages. [*Must fix*]

+ 1. A [citation](/microsoftteams/platform/bots/how-to/bot-messages-ai-generated-content?tabs=after%2Cbotmessage#citations) that enables a user to refer to the source of the bot message through in-text citations and references. [*Must fix*]

+ 1. A [sensitivity label](/microsoftteams/platform/bots/how-to/bot-messages-ai-generated-content?tabs=after%2Cbotmessage#sensitivity-label) that enables a user to understand the confidentiality of the bot message. [*Good-to-fix*]

+ 1. An agent must stream itΓÇÖs responses to the user. [*Must fix*]

+ 1. An agent must include at least three prompt starters or a welcome message. [*Must fix*]

+ For more information, see [bot welcome messages](teams-store-validation-guidelines.md#bots-1).

+ 1. A bot should offer at least two context-specific suggestions or prompts to the user, rather than generic or fixed ones. [*Must fix*]

+<details><summary>Bot first run user experience</summary>

+* A bot in personal scope must always send welcome message or provide prompt starters. [*Must fix*]

+ If you're using prompt starters, ensure the following guidelines are met:

+ Prompt starters help users start a conversation with your bot. To enable prompt starters, the `commands` property in app manifest needs to be defined.

+ * The bot must provide at least one command that enables the user to know about the value proposition of the app. [*Must fix*]

+ * Prompt starters or commands must be functional and return responses. [*Must fix*]

+ * Command description must be coherent and clearly communicate value of the command. [*Must fix*]

+ * Prompt starters or commands must be relevant to the app's functionality. [*Must fix*]

+ * The bot must have at least three unique prompt starters or commands. [*Good-to-fix*]

+ If your app sends a welcome message, ensure the following guidelines are met:

+ * If the app has a complex configuration flow (requires an enterprise license or lacks an intuitive sign up flow), then bots in such apps must always include configuration related information while sending a welcome message during the first run.

+ For best experience, the welcome message must include the value offered by the bot to users, who installed the bot in channel, how to configure the bot, and briefly describe all supported bot commands. You can display the welcome message using an Adaptive Card with buttons for better usability. For more information, see [how to trigger a bot welcome message](~/bots/how-to/conversations/send-proactive-messages.md). For apps without a complex configuration flow, you can choose to trigger a welcome message during the bot first run experience. However, if a welcome message is triggered, it must follow the welcome message guidelines.

+ :::image type="content" source="../../../../assets/images/submission/validation-bot-welcome-message.png" alt-text="Graphic shows an example of bot sending a welcome message when the bot has a complex configuration workflow.":::

+ :::image type="content" source="../../../../assets/images/submission/validation-bot-no-welcome-message.png" alt-text="Graphic shows an example of bot not sending a welcome message when the bot has a complex configuration workflow.":::