AI features for Teams and Classic bots
Important
Power Virtual Agents capabilities and features are now part of Microsoft Copilot Studio following significant investments in generative AI and enhanced integrations across Microsoft Copilot.
Some articles and screenshots may refer to Power Virtual Agents while we update documentation and training content.
If you create bots in the Microsoft Copilot Studio app in Teams, or if you have bots marked Classic in the Microsoft Copilot Studio web app, you can enable additional features for those bots that improve how the core AI in Microsoft Copilot Studio works.
The unified authoring canvas includes a raft of improvements to the types of AI used by Microsoft Copilot Studio which build upon these features. Bots created with the unified authoring canvas include next-generation AI features that supersede or replace the features listed in this topic.
This topic provides details and instructions for using these AI features for backwards compatibility with older bots and to support some specific support scenarios. In most cases, you should create or convert your bots with the unified authoring canvas to get the best implementation of multiple AI technologies.
Important
The AI features available to you depend on how (or when) you created your bot.
The AI features on this page are only available if:
- You create your bot in the Teams app
- You create a Classic bot
- You created your bot before May 23, 2023
Generative AI features (such as generative answers and Copilot) are only available if you create or convert a bot using the unified authoring canvas in the Microsoft Copilot Studio web app.
Prerequisites
- Your bot must be marked Classic, or it must be a bot you created in the Teams app.
- Learn more about what you can do with Microsoft Copilot Studio.
AI models in Microsoft Copilot Studio - background
Microsoft Copilot Studio hosts multiple AI models and AI capabilities on a single service, the core of which is a transformer-based natural language understanding (NLU) model.
Traditionally, intent triggering (how an AI model determines the intent of a question posed to it, by using NLU to understand what a user is asking) is formalized as a multi-class classification problem, in which the model is highly associated with known categories; any change to these categories will result in the need to build a new AI model.
Microsoft Copilot Studio, however, employs a language understanding model that uses an example-based approach, powered by a deep neural model. This type of large-scale model only needs to be trained once with large amounts of data using AI supercomputing, and can then be used for specific tasks with few examples without further training. The use of this model is part of the AI at Scale initiative by Microsoft, and means the way AI is developed and used is changing. Specifically for Microsoft Copilot Studio, the use of this model allows for an intuitive way for bot makers to work on their bot content confidently, without having to involve AI experts.
With the Microsoft Copilot Studio model, you only need to provide a few examples when you craft trigger phrases for a topic. The examples for a single topic usually consist of 5 to 10 phrases.
Shorter trigger phrases are better, and you should aim for 2 to 10 words. You just need to make sure trigger phrases are semantically different: changing a single verb or noun could be enough to expand a topic's coverage. Adding things like new articles (changing or adding 'the' or 'a' or 'an'), changing capitalization, adding contractions (you're or don't), or adding plurals won't improve the triggering because contractions are already accounted for in the AI model.
Entities used in corresponding topics will automatically be identified in user intents when matched with their trigger phrases. For example the user intent "I want to book a ticket to Boston" will match with the trigger phrase "I want to book a ticket to Paris".
Topic overlap detection
Topic overlap detection helps improve topic triggering accuracy by finding overlaps between topics. Resolving topic overlaps can help reduce the need for the bot to ask clarifying questions before triggering a topic.
Tip
Topic overlap detection is in general availability and supports all languages supported in Microsoft Copilot Studio.
After you enable advanced AI capabilities, you can view a list of overlapped topics. In the navigation menu, select Analytics, then select the Topic triggering tab.
The list shows each overlapping topic along with a similarity score, which represents the overall overlapped status for a topic, and the number of topics that overlap with the listed one. The similarity score is determined by the AI as it evaluates how semantically similar the overlapping trigger phrases are to each other. A higher score indicates that a particular topic has one or more trigger phrases that are close to another topic's trigger phrases.
You can sort the list by its similarity score, topic name, or number of trigger phrase overlaps.
If you select an item in the list, the Topic overlap details pane will open.
In this example, there's one trigger phrase in the "Languages support in Microsoft 365?" topic (For which languages is Microsoft 365 available?) that semantically overlaps with a trigger phrase in the "Use Microsoft 365 in other languages?" topic (Can I use Microsoft 365 in languages other than the one I originally purchased?). Here, the AI has determined that both trigger phrases are semantically similar (they contain similar phrases, words, and grammar).
Using semantically similar trigger phrases for two different topics can lead to confusion as the bot may not know which topic to open, and will need to ask follow-up questions to the bot user.
Identifying semantically similar trigger phrases can also help you determine if you have topics that themselves are similar and could be consolidated to simplify the bot authoring process, or edited to make the topics more distinct.
On the Topic overlap details pane, you can select the link to go directly to the specific topic. You can also make changes to the trigger phrase (or delete it) directly on the Topic overlap details pane. Select Save to apply any changes.
After you save the changes in the Topic overlap details pane, the overlapping status will automatically be refreshed. You can always manually refresh the topic overlap status by selecting the refresh button on the topic overlap UI.
Topic suggestion from chat transcripts (preview)
This feature analyzes sessions between your bot and users and surfaces suggestions for you based on unmatched user input.
Once enabled, go to Analytics > Topic triggering (preview). A list of potential topics will be shown, with the number of times a query about this topic was made by users of the bot. The top 200 suggestions will be shown.
The topic suggestion analyzer automatically runs once every one to two hours. It scans through all new queries made since the analyzer last ran, groups together queries to which it couldn't match an existing topic, and presents them in the list. Your bot will need at least 100 new conversations (from the last time any suggestion was generated) to trigger the process, and only those suggestions with more than three user sessions will be shown.
When you select an item in the suggestion list, a topic suggestion window will appear, showing the topic with some suggested trigger phrases. The suggested trigger phrases are based on the queries made by the bot users that couldn't be matched to an existing topic.
After reviewing the suggested trigger phrases, you can choose to delete the entire suggested topic (for example, if it's irrelevant to the bot) or add it to your list of topics by selecting Add to topics.
Conversation personalization (preview)
Important
The conversation personalization (preview) capability will be retired on 28 September 2023. From that date onwards, you won't be able to enable this capability in any new or existing bots. The capability will also be disabled for any existing bots that have it enabled.
The unified authoring canvas includes a raft of improvements to the types of AI used by Microsoft Copilot Studio. Wherever possible, we recommend you create and convert your bots with the unified authoring canvas.
For this capability, the bot reuses information from Microsoft Graph and Microsoft Entra ID throughout the conversation. This feature allows the bot to use already existing information to enhance and personalize future conversations. For example, if a user mentions a name, email, or zip code these properties are stored and used in later conversations without having to reprompt the user.
Specifically, with this feature enabled, when the bot asks questions such as those in the following table, the corresponding user information is pulled from Microsoft Graph and Microsoft Entra ID (for authenticated users) and provided as prompts for the user to choose as an option.
| Sample bot questions | User property automatically filled from Microsoft Graph or Microsoft Entra ID |
|---|---|
|
Address |
|
Annual income |
|
Date of birth |
|
Business phone number |
|
City of residence |
|
Country of residence |
|
Email address |
|
Fax number |
|
First name |
|
Gender |
|
Home phone number |
|
Job title |
|
Last name |
|
Manager's name |
|
Marital status |
|
Middle name |
|
Mobile phone number |
|
Nick name |
|
Number of children |
|
Spouse/partner name |
|
State/province of residence |
|
Zip code |
Enable or disable AI capabilities
Important
You can't enable these features for bots aren't marked Classic. This includes any bots created (or converted) in the web app after May 23, 2023, or any bots that weren't created with the unified authoring canvas (such as those you created specifically for certain scenarios, which you chose when you created the bot).
The conversation personalization (preview) capability will be retired on 28 September 2023. From that date onwards, you won't be able to enable this capability in any new or existing bots. The capability will also be disabled for any existing bots that have it enabled, and it will be removed from the AI capabilities page in Microsoft Copilot Studio.
The unified authoring canvas includes a raft of improvements to the types of AI used by Microsoft Copilot Studio. Wherever possible, we recommend you create and convert your bots with the unified authoring canvas.
To enable these older AI capabilities in Microsoft Copilot Studio:
- Open the bot you want to enable the features for:
- In the web app, the bot must be marked with Classic.
- In the Teams app, the bot can be any bot.
- Expand the Settings tab, then select AI capabilities.
- For each feature, select the checkbox to turn the feature on or off.
- Select Save at the top of the tab.
Feedback
Submit and view feedback for