INC Preview Feature
This feature is in PREVIEW and may not yet be available to all customers. Functionality, scope and design may change considerably.
PRECONDITIONS: TENANT ADMIN CONSENT
✅Virtual Users use AI-driven functionality which requires Tenant Administrator consent. This consent needs to be granted once in the Data Privacy Tenant Settings > Artificial Intelligence section.
Virtual Users are helpful, rapid-response self-service bots that can meet customer requests without the need of a Nimbus queue. You can configure them at your convenience, to be used variably within your Nimbus Workflows. The benefits are as follows:
- Responsive: A bot can answer your customers immediately, without them having to wait in queues.
- Scaling: Virtual Users can be added to any service, either as a fallback or first-responder.
- Universal: By adjusting each Virtual User's instructions and parametrization, the Virtual User can address and help the customer in many ways.
Scenario comparison
Usually during a classic IVR scenario, the verbal input from a customer needs to be very specific. When editing your workflows you need to consider all outputs in the Conversation Handling Activities, as the correct exit is taken only when the exact word is said. Meanwhile, the Nimbus AI Intent Analyzer understands a natural sentence and recognizes the semantics, which is mapped to a predefined list of intents. The intent with the highest probability is then selected.
💡To showcase, here is an example:
Classic IVR scenario
- Announcement: “Welcome to our Service”
- Static prompt: “If you want to talk to sales, say "Sales", If you want to to speak to Accounting, say “Accounting”.
- Customer replies: “Sales”
The announcement now checks the audio for the exact correct wording pattern. Any misinterpretations (e.g. dialects, quality) could lead to a repeat loop or false redirect.
Virtual User scenario
- Greeting by the Virtual User: "Hello, how can I help you today?
- Customer: I would like to discuss my current product licensing terms, specifically the addition of additional features.
The AI identifies the customer's intent by scanning for keywords and routes the call to the right queue/Nimbus Service. The customer does not have to follow any further instructions or repeat signal words. Any missing information can be requested in an active dialogue. This improves caller's IVR experience, as there is no need to press digits or pay attention to repeating pre-recorded instructions.
💡Further applications
Virtual Users - and their underlying AI models - can be applied for a variety of use cases. In extension to the intent analysis, you may achieve other results such as:
- Detecting urgency of a conversation. The bot automatically checks for keywords and passes the call to the right Nimbus service or user, for example by using workflow paths that bring Task Priority or services using Skills and Responsibilities into play.
- Convenient caller identification the against a CRM system or another 3rd party platform / database. The AI automatically requests and provides parameters during natural conversation, then intelligently decides where to route a call next.
Setup
INC AI and Virtual User Preconditions
PRECONDITIONS: AI and Virtual User
Nimbus Tenant Admin rights are required:
- …to enable the use of AI features you need to grant consent in the Data Privacy Tenant Settings.
- …to create AI Configuration items in Nimbus Admin portal and access Service Distribution Settings to test workflows with configured Virtual Users.
Nimbus License Management:
- Contact Center Enterprise Routing Note that Virtual Users – using AI-driven functionality – are exclusive to Contact Center and Enterprise Routing services. For more details, refer to Nimbus Features > Service Features.
- In addition to the Service requirement you also require an additional license per Virtual User. This license can either be applied directly in the Virtual User configuration steps below or - in bulk - via Admin > Licensing view. The license enables usage of the “Add Virtual User” Workflow Activity. For additional Virtual User licenses on your service, get in touch with your Customer Success representative.
Bot Preconditions
✅Nimbus Configuration dependencies:
-
All Virtual Users require Bots to be configured. The bot determines the AI model / service that the Virtual User integrates into.
Learn more…
INC Language model comparison matrix
Type Primary Use Case Limitations Integration Effort M365 Copilot – Direct Line 3.0 Enterprise voice interactions with Microsoft 365 Copilot, enabling transcription of spoken conversations grounded in M365 work data and supporting natural interruption. - For generalized use for Microsoft 365 and Copilot Studio scenarios, rather than custom external voice agents;
- Subject to Microsoft licensing and service capacity limits.
Medium – Native to the Microsoft 365 ecosystem. Requires configuration within Nimbus, plus integration with Azure Copilot Studio API handle topics.
🔎 See: Use Case - Setting up a Nimbus Virtual User using CopilotNimbus AI Services – Audio Intent Analyzer Low latency, conversational AI, real-time audio stream. Contact‑center audio analysis focused on speech‑to‑text, intent, language, and sentiment detection for intelligent routing and IVR replacement. - Primarily for intent classification rather than full speech‑to‑speech conversation
Low – Configuration stays within Nimbus, parametrization is done directly in workflows as part of the “Virtual User” activity.
🔎 See: Use Case - Setting up a Nimbus Virtual User for Intent Analysis
Azure OpenAI – Audio GPT Realtime1 Low latency, conversational AI, real-time audio stream. Used as speech‑in / speech‑out conversational AI for building custom voice Agents that can cover a wide range of roles. - Not end‑user ready out of the box.
- Needs custom client and backend integration, with regional availability determined by Microsoft1.
- Subject to Microsoft licensing and service capacity limits.
Medium – Native to the Microsoft 365 ecosystem. Requires configuration within Nimbus, plus integration with Azure Copilot Studio API handle topics.
Allows customers to bring their own LLM and 3rd party integrations.
🔎 See: Use Case - Setting up a Nimbus Virtual User using OpenAI GPT Realtime
Comparison: Types of Bots for Nimbus Virtual Users Notes
1 Due to Microsoft Azure AI Foundry GPT-Realtime availability in limited regions, data processed by Nimbus Virtual User GPT-Realtime integration will temporarily leave your regional boundary:
- DE01, DE02, CH01, CH02, UK01, EU01, AU01) and computation will be performed in Sweden Central region. No persistent storage of your data occurs as part of this process.
- US01 cluster customers' data will not leave the regional boundary.
-
Depending on your bot configuration, you may need to configure:
- Bot Response Templates, to map answers from the bot back into workflow parameters.
- Speech Recognizers (Transcribers) to convert the Customer voice into text for the bot to process.
General Configuration
| Field | Description |
|---|---|
| Name | The name of the Virtual User, as it will appear in other selection dialogues of Nimbus (e.g. within Workflows). |
| Organization Unit | Determines where the Bot will be available for selection. |
| Description |
A Nimbus-internal description, e.g. “Support Bot for first response IVR”. 💡This field is just for identification within Nimbus and will have no impact on the Bot behavior. |
Bot Configuration
Virtual Users in Nimbus are defined as Configuration > Virtual Users within your Nimbus Administration. By using the Organization Units approach, the bot configuration can be used flexibility across multiple services if necessary.
| Field | Description |
|---|---|
| Bot |
✅ Precondition: Requires a Bot to be configured before becoming available for selection. 💡The selection of your Bot determines which underlying API and AI large language model (LLM) used to interact with Customers and formulate a response. Note that bots leverage external features and APIs with cost outside of your Nimbus subscription.2 ⮑ Depending on your bot choice, configurable fields below will change. |
| Bot Response template |
✅ Preconditions:
|
| Language |
✅Precondition:
💡Defines the spoken language of your bot, using direct Audio-to-Audio speech models. 💡Further languages will be made available in the near future. |
| User Voice |
✅Precondition:
💡Defines the tone of voice for your bot. The selection is automatically adjusted to be compatible with the Language selected above. 💡Further voice models will be made available in the near future. |
| System Instruction |
✅Precondition:
💡Allows to define the initial instructions for your bot. You can add Nimbus Custom Parameters or System Fields to be part of this instruction set. 💡Note that these fields need fallbacks and / or working flows: Parameters may rely on external systems (e.g. a CRM) to retrieve customer details via Flow Actions. A possible instruction could be as follows: |
| Initial Message to Bot |
✅ Preconditions:
The “Initial Message” acts as your "Topic” or “Query” for your bot. This field can also be used to force a bot response in case it is not configured to send an initial message by itself. 💡Note that this field is optional in Nimbus: Depending on your Bot configuration, underlying AI may already engage with the customer automatically. Optionally, you can also use this message to go directly into specific Conversation Topics3, e.g. by adding Nimbus Custom Parameters or System Fields right with the first inquiry. A possible example of an Initial Message could be to look up your customer details and have the Virtual User address them personally: |
2 🔎Also see: MSFT Learn Documentation | Use system topics to learn more.
INC Azure Billing Cognitive Services
Disclaimer: Support for Azure Billing & Cognitive Services
☝ The usage of Microsoft Azure AI Services for Speech1 and AI2 will cause additional costs outside your Nimbus subscription, which are exclusively determined by Microsoft.
Please note:
- Nimbus Support does not cover pricing discussions or make recommendations on Microsoft Azure Services. → Please inform yourself via the references below on pricing models.
- Nimbus Support can not provide any technical help, insights or solutions on Azure Cognitive Service related technical problems.
1 Azure Speech Services: https://azure.microsoft.com/en-us/pricing/details/cognitive-services/speech-services/
2 Generative AI Services (Copilot Studio):
Modalities
| Field | Description |
|---|---|
| Modalities |
Enables the bot to handle and react to Audio/Video (calls). 💡Further modalities will be made available in the near future. |
| Speech Recognizer |
✅Preconditions:
|
Follow-up Steps
Follow-up Steps
- ✅Licenses: In order to take action within a workflow, every Virtual User needs a license applied. You may freely (re-)assign licenses from your Licenses Tenant Settings. If you require additional licenses, get in touch with Luware Customer Success.
- ✅Workflow Updates: Once done with the configuration, update your Workflows. In order to take effect, Virtual Users must be applied within Audio/Video workflows an “Add Virtual User” activity.
Limitations
INC AI and Virtual User Limitations
General note on AI-driven interactions
AI driven replies are not deterministic and depend highly on what the Customer is saying. For example, if the Customer is saying “I have trouble with my internet” it is not necessarily given that the Bot will associate “Router, Modem” as your workflow routing exit, unless specifically handled in your Virtual User integration. In this specific example, AI instructions should also cover alternative wordings like “Router, Internet”, to be handled in topics accordingly.
🔎Refer to our Best Practices - Virtual Users in Nimbus for some considerations and risks when using Virtual Users instead of Human interaction.
Microsoft Copilot Limitations
- Expect processing delays: Processing AI answers takes a few seconds for voice-to-text-transcription, followed by AI processing and a transcription back into a voiced response. Luware is trying to minimize the delay on Nimbus call infrastructure, but the dependency on external APIs will always incur a delay. The Customer will hear silence during this processing and no audio feedback / silence detection.
-
Ensure you have no ambiguity in your topics. For instance, the word “
Service” may be too generic if you want to transfer to different services. Rather usehealthcare|medical|emergencyas identifiers or use more complex Regular Expressions to identify replies.
Nimbus Audio Intent Analyzer
- The Nimbus Audio Intent analyzer Bot runs on hard-coded bot instructions. Any usage outside of the descriptions specified under Use Case - Setting up a Nimbus Virtual User for Intent Analysis is not supported.
Azure Open AI - Open GPT Realtime limitations
- This feature is not yet ready for productive use and only enabled for selected customers. We will make further adjustments and update Use Case - Setting up a Nimbus Virtual User using OpenAI GPT Realtime accordingly in an upcoming Nimbus release.
General Virtual User limitations
The current Nimbus implementation with AI-driven bots underlies the following limitations:
- Supported Modalities: Virtual Users (Bots) are currently available for Audio/Video modality tasks.
- Virtual User Reporting: Sessions involving Virtual Users are not reflected as dedicated User Session. Virtual User session reporting is planned for a later point this year.