Skip to content

Update bot-messages-ai-generated-content.md #14279

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
SharanGarcha-MSFT wants to merge 6 commits into
base: main
Choose a base branch
from
Open

Update bot-messages-ai-generated-content.md #14279

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
5997c5c
Update bot-messages-ai-generated-content.md
SharanGarcha-MSFT Apr 21, 2026
c41b2f1
Update bot-messages-ai-generated-content.md
SharanGarcha-MSFT Apr 22, 2026
652e36e
Update content
SharanGarcha-MSFT Apr 23, 2026
2737a9d
Update bot-messages-ai-generated-content.md
SharanGarcha-MSFT Apr 28, 2026
b35be84
Update bot-messages-ai-generated-content.md
SharanGarcha-MSFT Apr 28, 2026
a5d41ee
Update bot-messages-ai-generated-content.md
SharanGarcha-MSFT Apr 28, 2026
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
240 changes: 45 additions & 195 deletions msteams-platform/bots/how-to/bot-messages-ai-generated-content.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
title: Bot Messages with AI-generated Content
description: Learn how to add an AI label, sensitivity labels, citations, and feedback buttons for bots built using Teams SDK or Bot Framework SDK.
description: Learn how to add an AI label, sensitivity labels, citations, and feedback buttons for bots built using Teams SDK.
ms.topic: conceptual
ms.localizationpriority: medium
ms.date: 04/15/2026
Expand Down Expand Up @@ -84,29 +84,14 @@ An AI label on your bot message indicates that it’s generated by AI. While AI-

### Add AI label

If you're using **Teams SDK** to build your bot, AI label is automatically enabled for all AI-powered bot messages in the `ai` module within the `PredictedSayCommand` action. For more information, see [AIEntity interface](https://github.com/microsoft/teams-ai/blob/main/js/packages/teams-ai/src/actions/SayCommand.ts#L67).

If you're using **Microsoft Bot Framework SDK** to build your bot, include `additionalType` under the `entities` array of the `message` entity object. The following code snippet shows how to enable the AI label in a bot message:
To build your bot using **Teams SDK**, use the `addAiGenerated()` method to mark a message as AI-generated. The following code snippet shows how to enable the AI label in a bot message:

```javascript
Comment thread
SharanGarcha-MSFT marked this conversation as resolved.
await context.sendActivity({
type: ActivityTypes.Message,
text: `Hey! I'm a friendly AI bot. This message is generated by AI.`,
entities: [
{
type: "https://schema.org/Message",
"@type": "Message",
"@context": "https://schema.org",
additionalType: ["AIGeneratedContent"], // Enables AI label
}
]
app.message(/label/i, async ({ send }) => {
await send(new MessageActivity("Hi, this message is generated by AI").addAiGenerated());
});
```

| Property | Type | Required | Description |
|--|--|--|--|
| `additionalType` | Array | Yes | Enables AI label in the bot message.<br>Allowed value: `AIGeneratedContent` |

After you add an AI label, your bot's message shows an **AI generated** label next to the bot's name. When you hover over the AI label, a disclaimer appears stating, **AI-generated content may be incorrect.**. The AI label and disclaimer can't be customized for AI-powered bots.

### Error handling
Expand Down Expand Up @@ -162,112 +147,49 @@ Citations in your bot's messages can include the following:

### Add citations

If you're using **Teams SDK** to build your bot, citations are added to an AI-powered bot message automatically through `PredictedSayCommand` action. You can also modify the `PredictedSayCommand` action to add citations to your bot message. For more information, see [ClientCitation interface](https://github.com/microsoft/teams-ai/blob/main/js/packages/teams-ai/src/actions/SayCommand.ts#L42).

If you're using **Bot Framework SDK** to build your bot, include `citation` under the `entities` array. Following is an example code snippet:
If you're using **Teams SDK** to build your bot, Use `addCitation()` to include in-text references and citation metadata in your message. Following is an example code snippet:

# [JavaScript](#tab/js)
Comment thread
SharanGarcha-MSFT marked this conversation as resolved.
Outdated

```javascript
await context.sendActivity({
type: ActivityTypes.Message,
text: `Hey I'm a friendly AI bot. This message is generated through AI [1]`, // cite with [1],
entities: [
{
type: "https://schema.org/Message",
"@type": "Message",
"@context": "https://schema.org",
citation: [
{
"@type": "Claim",
position: 1, // Required. Must match the [1] in the text above
appearance: {
"@type": "DigitalDocument",
name: "AI bot", // Title
url: "https://example.com/claim-1", // Hyperlink on the title
abstract: "Excerpt description", // Appears in the citation pop-up window
text: "{\"type\":\"AdaptiveCard\",\"$schema\":\"http://adaptivecards.io/schemas/adaptive-card.json\",\"version\":\"1.6\",\"body\":[{\"type\":\"TextBlock\",\"text\":\"Adaptive Card text\"}]}", // Appears as a stringified Adaptive Card
keywords: ["keyword 1", "keyword 2", "keyword 3"], // Appears in the citation pop-up window
encodingFormat: "application/vnd.microsoft.card.adaptive",
image: {
"@type": "ImageObject",
name: "Microsoft Word"
},
},
},
],
},
],
})
app.message(/citation/i, async ({ send }) => {
const card = new AdaptiveCard(new TextBlock("Adaptive Card text"))
.withOptions({ version: "1.6" });
const appearance: CitationAppearance = {
name: "AI messages bot",
url: "https://example.com/claim-1",
abstract: "Excerpt description",
text: JSON.stringify(card),
keywords: ["keyword 1", "keyword 2", "keyword 3"],
icon: "Microsoft Word",
};
await send(
new MessageActivity("Hey I'm a friendly AI bot. This message is generated through AI [1]")
.addCitation(1, appearance)
);
});
```

# [Python](#tab/python)

```python
@app.message("citation")
async def on_message(context: TurnContext, state: TurnState):
appearance = Appearance(
name="Understanding AI Citations in Python",
abstract=snippet("A brief extract demonstrating the integration of AI Citations in Python.", 477),
url="https://example.com/py-ai-citations",
keywords=["Python", "Citations"],
image=AppearanceImage(name="Microsoft Excel"),
usage_info=SensitivityUsageInfo(
name="Creative Work",
description="Sensitive content information for Python AI citation.",
position=1,
pattern= Pattern(
in_defined_term_set= "ColorSet",
name= "Red",
term_code= "#FF0000")
)
)

# Create the client citation with a specific position and the defined appearance.
citation = ClientCitation(
position=1,
appearance=appearance
)

# Create the AIEntity, including the citation and overall sensitivity usage information.
ai_entity = AIEntity(
additional_type=["AIGeneratedContent"],
citation=[citation],
usage_info=SensitivityUsageInfo(
name="Creative Work",
description="Overall message sensitivity information for AI citations.",
@app.on_message_pattern(re.compile(r"citation", re.IGNORECASE))
async def add_citations(ctx: ActivityContext[MessageActivity]):
await ctx.send(
MessageActivityInput(
text="Hey I'm a friendly AI bot. This message is generated through AI [1]",
).add_citation(
position=1,
pattern=Pattern(
in_defined_term_set="ColorSet",
name= "Red",
term_code="#FF0000",
)
appearance=CitationAppearance(
name="AI messages bot",
url="https://example.com/claim-1",
abstract="Excerpt description",
text=AdaptiveCard(version="1.6", body=[TextBlock(text="Adaptive Card text")]).model_dump_json(by_alias=True, exclude_none=True),
keywords=["keyword 1", "keyword 2", "keyword 3"],
icon=CitationIconName.MICROSOFT_WORD,
),
)
)

# Use the helper function to format citation tags within a sample message.
sample_text = "This is an AI-generated message with citation [doc1]."
formatted_text = format_citations_response(sample_text)
print("Formatted Text:", formatted_text)

# Retrieve citations used in the formatted text.
used_citations = get_used_citations(formatted_text, [citation])
print("Used Citations:", used_citations)
print("AI Entity:", ai_entity)
await context.send_activity(
Activity(
type=ActivityTypes.message,
text=formatted_text,
entities=[
AIEntity(
citation=(list(used_citations) if used_citations else []),
additional_type=["AIGeneratedContent"],
),
],
)
)

return True
```

---
Expand Down Expand Up @@ -331,31 +253,14 @@ Feedback buttons are located at the footer of the bot’s message and include a

### Add feedback buttons

For a bot built using **Teams SDK**, Teams enables feedback buttons for all bot messages when `enable_feedback_loop` is set to `true` in the `ai` module.
To enable feedback buttons in a bot built using **Teams SDK**, use the `addFeedback()` method on the message activity.

```javascript
Comment thread
SharanGarcha-MSFT marked this conversation as resolved.
export const app = new Application<ApplicationTurnState>({
ai: {
planner: planner,
enable_feedback_loop: true
},
```

For more information, see the [const app variable](https://github.com/microsoft/teams-ai/blob/main/js/samples/04.ai-apps/h.datasource-azureOpenAI/src/app.ts#L65).
app.message(/feedback/i, async ({ send }) => {

After you enable feedback buttons, all `SAY` commands from the bot have `feedbackLoopEnabled` in the `channelData` object automatically set to `true`.
await send(new MessageActivity("This is an example of a feedback button - this helps to provide feedback for a message").addFeedback());

To enable feedback buttons in a bot built using **Bot Framework SDK**, define a `feedbackLoop` object under the `channelData` object of your bot message.

```javascript
await context.sendActivity({
type: ActivityTypes.Message,
text: `Hey! I'm a friendly AI bot!`,
channelData: {
feedbackLoop: { // Enable feedback buttons
type: "custom"
},
});
});
```

| Property | Type | Required | Description |
Expand All @@ -382,53 +287,14 @@ You must respond to this invoke call with a dialog (referred to as task modules

### Handle feedback

The bot receives user input from the feedback form through a bot invoke flow. For bots built using **Teams SDK**, the bot invoke request is automatically handled. To handle feedback, use the `app.feedbackLoop` method to register a feedback loop handler to be called when the user provides feedback.
The bot receives user input from the feedback form through a bot invoke flow. For bots built using **Teams SDK**, the bot invoke request is automatically handled. Handle user feedback using the `message.submit.feedback` event.

```javascript
app.feedbackLoop(async (_context: TurnContext, _state: TurnState, feedbackLoopData: FeedbackLoopData) => {
// custom logic here...
});
app.on("message.submit.feedback", async (context) => {
// custom logic here...
});
```

For more information, see the [asynchronous callback function](https://github.com/microsoft/teams-ai/blob/main/js/samples/04.ai-apps/h.datasource-azureOpenAI/src/app.ts#L111).

For a bot built using **Bot Framework SDK**, you must have an `onInvokeActivity` handler to process the feedback. Ensure that you return a status code `200` with an empty JSON object as a response.

The following code snippet shows how to handle feedback received in a bot invoke and return a response with the status code `200`:

```javascript
public async onInvokeActivity(context: TurnContext): Promise<InvokeResponse> {
try {
switch (context.activity.name) {
case "message/submitAction":
console.log('Your feedback is ' + JSON.stringify(context.activity.value))
// Your feedback is {"actionName":"feedback","actionValue":{"reaction":"like","feedback":"{\"feedbackText\":\"This is my feedback.\"}"}}
return CreateInvokeResponse(200, {});
default:
return {
status: 200,
body: `Unknown invoke activity handled as default- ${context.activity.name}`,
};
}
} catch (err) {
console.log(`Error in onInvokeActivity: ${err}`);
return {
status: 500,
body: `Invoke activity received- ${context.activity.name}`,
};
}
}

export const CreateInvokeResponse = (
status: number,
body?: unknown
): InvokeResponse => {
return { status, body };
};
```

Store the feedback by saving message IDs and content of messages your bot sends and receives. When your bot gets an invoke request with feedback, match the message ID with the corresponding feedback.

> [!NOTE]
> Teams doesn't store or process feedback. It doesn't provide an API or a storage mechanism.

Expand All @@ -438,7 +304,7 @@ If a user uninstalls your bot and still has access to the bot chat, Teams remove

| Error code | Description |
| --- | --- |
| 400 | `message/submitAction` invoke response isn't empty. |
| 400 | `message.submit.feedback` event app.message(/label/i, async ({ send }) => { response isn't empty. |

## Sensitivity label

Expand All @@ -459,9 +325,7 @@ Bot responses might contain confidential information or be accessible only to ce

### Add sensitivity label

For bots built using **Teams SDK**, sensitivity label can be added through `PredictedSayCommand` action. For more information, see [SensitivityUsageInfo interface](https://github.com/microsoft/teams-ai/blob/main/js/packages/teams-ai/src/types/AIEntity.ts#L46).

For bots built using **Bot Framework SDK**, add a sensitivity label to your bot message by modifying the message to include `usageInfo` in the `entities` object.
For bots built using **Teams SDK**, add a sensitivity label to your bot message by modifying the message to include `usageInfo` in the `entities` object.

The following code snippet shows how to add sensitivity labels to both bot messages and citation reference:

Expand Down Expand Up @@ -544,20 +408,6 @@ After you add the sensitivity label, your bot message displays a shield icon. Us
| 400 | Citation level `usageInfo.@id` value doesn't match the message level `usageInfo.@id` in at least one instance. |
| 400 | There are multiple citation-level `usageInfo` properties with the same `@id`, but their `name` and `description` properties are different. |

## Modify `PredictedSayCommand`

For a bot built using Teams SDK, the `PredictedSayCommand` provides control on how AI label, citation, feedback button, and sensitivity label are added to the bot's activity. Following is the code snippet to modify `PredictedSayCommand`:

```JavaScript
app.ai.action<PredictedSayCommand>(AI.SayCommandActionName, async (context, state, data, action) => {
// custom logic here...
await context.sendActivity(data.content);
return "";
});
```

For more information about `PredictedSayCommand`, see [PredictedSayCommand interface](/javascript/api/%40microsoft/teams-ai/predictedsaycommand?view=msteams-client-js-latest&preserve-view=true).

## Code samples

| Sample name | Description | Node.js | .NET |
Comment thread
SharanGarcha-MSFT marked this conversation as resolved.
Outdated
Expand Down
2 changes: 1 addition & 1 deletion msteams-platform/includes/teams-ai-lib-v2-rec.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
> [!IMPORTANT]
>
> - Teams AI library is now renamed to Teams SDK.
> - Teams AI library v1 is deprecated. We recommend that you upgrade your agents to use the updated [Teams SDK](/microsoftteams/platform/teams-ai-library/welcome).
> - Teams AI library v1 is deprecated. We recommend that you upgrade your agents to use the updated [Teams SDK](/microsoftteams/platform/teams-sdk/getting-started/quickstart).
>
> Teams SDK is now generally available for JavaScript and C#, supports Python in developer preview. It provides a simplified SDK, support for Model Context Protocol (MCP), Agent-to-Agent communication (A2A), and streamlined tools to enable developers to build intelligent agents for Teams.