Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -179,7 +179,7 @@ The `Mention` object has two properties that you must set using the following:
* Include *@username* in the message text.
* Include the mention object inside the entities collection.

The Bot Framework SDK provides helper methods and objects to create mentions.
The Microsoft 365 Agents SDK (previously known as Bot Framework SDK) provides helper methods and objects to create mentions.

The following code shows an example of adding mentions to your messages:

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ ms.date: 01/29/2023

Microsoft 365 Agents Toolkit (previously known as Teams Toolkit) enables you to build applications that capture events and send them as interactive notifications to a personal, group chat, or a channel in Microsoft Teams. You can send notifications as plain text or [Adaptive Cards](../../../task-modules-and-cards/cards/cards-reference.md). The notification bot template creates an app that sends a message to Teams with Adaptive Cards triggered by HTTP post request.

The app template is built using the TeamsFx SDK, which provides a simple set of functions over Microsoft Bot Framework to implement your requirement. For example, a travel agency builds an app in Teams for their users to keep them up-to-date with the weather forecast. In the following flowchart, a Teams app notifies about the weather forecast to the users using an Adaptive Card:
The app template is built using the TeamsFx SDK, which provides a simple set of functions over Microsoft 365 Agents SDK (previously known as Bot Framework SDK) to implement your requirement. For example, a travel agency builds an app in Teams for their users to keep them up-to-date with the weather forecast. In the following flowchart, a Teams app notifies about the weather forecast to the users using an Adaptive Card:

:::image type="content" source="../../../assets/images/notification-bot/notification-new-scenario-diagram.png" alt-text="weather forecast sample notification scenario" lightbox="../../../assets/images/notification-bot/notification-new-scenario-diagram.png":::

Expand Down Expand Up @@ -47,7 +47,7 @@ You can send a bot notification in the following scenarios:

## Notification based on events

Bot Framework SDK provides the functionality to proactively message in Teams. TeamsFx SDK provides the functionality to manage bot's conversation references when a bot event is triggered. TeamsFx SDK recognizes the following bot events:
Microsoft 365 Agents SDK (previously known as Bot Framework SDK) provides the functionality to proactively message in Teams. TeamsFx SDK provides the functionality to manage bot's conversation references when a bot event is triggered. TeamsFx SDK recognizes the following bot events:

|**Event** |**Behavior** |
|---------|---------|
Expand Down Expand Up @@ -445,14 +445,14 @@ If storage isn't provided, you can use a default local file storage, which store

If you're using the default local file storage, Azure web app and Azure Functions clean up the local file during a restart or redeploy. You can also uninstall the bot from Teams, then install it to again add connections to the storage.

The `NotificationTargetStorage` is different from Bot Framework SDK's [custom storage](/azure/bot-service/bot-builder-custom-storage). The notification storage requires `read`, `write`, `delete`, and `list` functionalities but Bot Framework SDK's storage has `read`, `write`, and `delete` functionalities and doesn’t have the `list` functionality.
The `NotificationTargetStorage` is different from Microsoft 365 Agents SDK's (previously known as Bot Framework SDK) [custom storage](/azure/bot-service/bot-builder-custom-storage). The notification storage requires `read`, `write`, `delete`, and `list` functionalities but Microsoft 365 Agents SDK's (previously known as Bot Framework SDK) storage has `read`, `write`, and `delete` functionalities and doesn’t have the `list` functionality.

For more information about Azure blob storage, see the [notification storage implementation sample](https://github.com/OfficeDev/TeamsFx-Samples/blob/v3/adaptive-card-notification/src/store/blobStore.ts).

> [!NOTE]
>
> * It's recommended to use your own shared storage for production environment.
> * If you implement your own Bot Framework SDK's storage, for example, `botbuilder-azure-blobs.BlobsStorage`, you need to implement another storage for notification. You can share the same Blob Connection String with different containers.
> * If you implement your own Microsoft 365 Agents SDK's (previously known as Bot Framework SDK) storage, for example, `botbuilder-azure-blobs.BlobsStorage`, you need to implement another storage for notification. You can share the same Blob Connection String with different containers.

[Back to top](#build-an-interactive-notification-bot)

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ You can create a workflow bot to respond to the Adaptive Card triggered by users

## Card action handler

To simplify the creation of a workflow bot, the TeamsFx SDK provides an Adaptive Card action handler `TeamsFxAdaptiveCardActionHandler`. You can focus only on the development of workflow bot to respond to the card action without learning the Bot Framework.
To simplify the creation of a workflow bot, the TeamsFx SDK provides an Adaptive Card action handler `TeamsFxAdaptiveCardActionHandler`. You can focus only on the development of workflow bot to respond to the card action without learning the Microsoft 365 Agents SDK (previously known as Bot Framework SDK).

The following diagram illustrates how to respond to an Adaptive Card action with TeamsFx SDK:

Expand Down
10 changes: 5 additions & 5 deletions msteams-platform/bots/how-to/teams-conversational-ai/ai-ux.md
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,7 @@ Use the following types of updates while streaming responses:
You can use one of the following to stream the response:

- Use Teams AI library to add streaming to the agent.
- Call the Bot Framework APIs directly for streaming.
- Call the Microsoft 365 Agents SDK (previously known as Bot Framework SDK) APIs directly for streaming.

>[!NOTE]
>
Expand All @@ -90,7 +90,7 @@ Users must know the sources a custom engine agent uses to generate its final res
You can use one of the following to include citations for the resources used by the agent:

- Use Teams AI library citations module.
- Incorporate citations into the Bot Framework API calls.
- Incorporate citations into the Microsoft 365 Agents SDK (previously known as Bot Framework SDK) API calls.

> [!NOTE]
>
Expand All @@ -113,7 +113,7 @@ Examples of AI label:
You can use one of the following to include AI label in the agent's response:

- Use Teams AI library to add the AI label to all AI-generated messages automatically.
- Set the flag in the Bot Framework API for message activities.
- Set the flag in the Microsoft 365 Agents SDK (previously known as Bot Framework SDK) API for message activities.

### Ensure that the custom engine agent is an intelligent conversational bot

Expand All @@ -122,7 +122,7 @@ A custom engine agent must track a conversation's context and history to provide
You can use one of the following to ensure intelligent context-based conversation:

- Use Teams AI library to manage and pass conversational history and context to the LLM.
- Use Bot Framework SDK to:
- Use Microsoft 365 Agents SDK (previously known as Bot Framework SDK) to:

- **Manage context and conversation history**: Ensure that the agent can track the context and conversation history.
- **Identify conversation location**: Ensure the agent is aware of the platform on which the conversation is ongoing, such as on Teams, copilot.com, in a meeting side panel, or a group chat.
Expand Down Expand Up @@ -169,7 +169,7 @@ To collect the user feedback, you must:
You can use one of the following to enable feedback collection and usage:

- Use Teams AI library to add the feedback button property to the AI module. This property adds a feedback button to each AI-generated message automatically.
- Use the feedback flag in the Bot Framework API to add the feedback button for each message.
- Use the feedback flag in the Microsoft 365 Agents SDK (previously known as Bot Framework SDK) API to add the feedback button for each message.

> [!NOTE]
> Customizable feedback forms are available in [public developer preview](../../../resources/dev-preview/developer-preview-intro.md).
Expand Down