A Virtual User is an AI-powered assistant that interacts directly with customers - greeting the callers, capturing context parameters and handing the conversation result back to Nimbus Workflow.
Use Cases
Virtual Users enable responsive, scalable self-service bots that can detect caller intent and integrate with external systems before — or instead of — handing over to a human agent. The list below is non-exhaustive; pick the closest pattern and adapt it.
| Call triage | Captures the callers intent and routes to its downstream flow. Set up with Virtual User intents such as "Create ticket", "Check status", “Escalate” |
| Identification gate | Intents Identified, Not Verified, Fraud Suspected — personalized self-service vs. manual verification vs. priority security queue. |
| FAQ with escalation | Intents Answer Found, Low Confidence, User Requests Agent — answer in-bot, offer alternative handling, or hand straight to an agent. |
| Payment / transaction | Intents Successful, Failed, User Aborted — confirmation, retry, or graceful exit. |
| Password reset | Intents Reset Successful, Reset Failed, User Locked Out — confirmation, retry, or escalation to support desk. |
| Survey | Intents Completed, Partial Completion, Drop Off — thank-you message, follow-up, or callback workflow. |
| Card blocking | Intents Card Blocked, Identification Failed, User Cancelled — confirmation with audit log, high-priority escalation, or safe exit. |
INC AI and Virtual User Preconditions
PRECONDITIONS: AI Features, Bots and Virtual Users
Admin Consent: AI Features
✅ Nimbus Tenant Admin consent is required to enable the use of AI features. This is done in the Data Privacy Tenant Settings. AI use will require your Tenant data (e.g. caller information) to be processed by external services
💡Good to know - shared setup effort: Once consent is granted, both Admin Roles “Tenant Admins” and “OU Admins” are able to create various AI Configuration items in the Nimbus Admin Portal. This also includes:
- Access to Service Distribution Settings, e.g. to test workflows with your configured Virtual Users.
- Steer feature visibility via Companion Service Settings (e.g. when activities are supposed to happen unobtrusive in the background).
Virtual User Licensing
✅Nimbus License Management:
-
Contact Center Enterprise Routing service licenses are required to use AI-driven Virtual User functionality.
⮑With the license applied, corresponding Service Features (e.g. workflow activities, configuration tabs) are enabled. -
Individual Virtual User license requirement: Same as regular Nimbus users, each Virtual User requires a separate license. This license can be applied individually in the Virtual User configuration - or in bulk - via Admin > Licensing view.
⮑The license enables usage of the “Add Virtual User” Workflow Activity, without it the activity will be skipped over. For additional Virtual User licenses on your service, get in touch with your Customer Success representative.
Virtual User Bot Configuration
Virtual Users rely on Nimbus Configuration items:
✅ ALL: Virtual Users require Bots to be configured. Your bot choice also determines the underlying AI LLM into which the Nimbus Virtual User integrates. Your bot typ and profile should therefore be chosen with the intended use case in mind.
INC Language model comparison matrix
| Defined in Bots | Defined in Virtual Users | |
|
Type Nimbus managed or BYO |
Agent Type Underlying LLM |
Virtual User Profile Pre-built configurations to fulfill a certain use case |
| Nimbus AI Services | Azure OpenAI – (GPT Realtime)1 |
|
|
Custom AI Services
|
|
|
| M365 Copilot Direct Line 3.0 |
|
|
Notes
1 Due to Microsoft Azure AI foundry availability in limited regions, data processed by a Nimbus Virtual User “GPT”-Realtime" integration might temporality leave due to failover scenarios:
- Nimbus Cluster DE01, DE02, CH01, CH02, UK01, EU01, AU01 computation will be primarily performed in Sweden Central region.
- Nimbus Cluster US01 computation will be primarily performed in the US East region.
✅SPECIFIC AI services / Agent technologies (e.g. Microsoft Copilot) may require additional configuration items such as:
- Bot Response Templates, to map bot answers back into Nimbus workflow parameters.
- Speech Recognizers (Transcribers) to convert the Customer voice into text for the bot to process.
🔎For more details and specific configuration steps, refer to our AI Use Cases category and the specific Use Cases and pages linked above.
General Information
| 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 optional, just for identification within the Nimbus UI and will have no impact on the Bot behavior. |
Bot Configuration
✅Requires a “Organization Unit” to be selected.
The Bot dropdown drives a follow-up Profile dropdown. Based on the bot and profile choice, visible options change the configurable fields further down this page.
| Bot |
✅Pick a previously configured Bot. 🔎More details on the different Bot and Agent models can be found in the Preconditions above. 💡The Bot's service and underlying AI Agent model determine which Profile options become available. |
| Profile |
✅ Required (except for Copilot bots).
⮑ The choice automatically changes the visible properties further below |
|
Bot Response Template (only for Copilot Bots). |
Bot Response Templates map the JSON response your Bots (external APIs) deliver, with the goal to use that response as criteria within your Workflows. |
AI Behavior
| Property | Description | Notes |
|---|---|---|
|
Verbosity (Open Profile Only) |
Short label describing how chatty the bot should be:
|
✅Only visible when “Open Profile” was selected as bot configuration |
|
Tone (Open Profile Only) |
Short label describing the desired conversational tone (e.g. "Friendly and professional", "Concise and factual"). Combined with Role and Verbosity to colour the bot's style. | |
|
Role (Open Profile only) |
Short label describing the persona the bot plays (e.g. "Customer service representative", "Pharmacy advisor"). Used as a building block of the system prompt so admins do not have to re-write the role into every System Instruction. | |
| System Instruction | Free-text prompt that defines the bot's persona, domain knowledge and rules. |
10,000 chars limit Supports Custom Parameters and System Parameters |
Conversation Messages
| Property | Description | Notes |
|---|---|---|
| Initial Message |
First thing the caller hears when the Virtual User joins.
Free-text prompt that defines the bot's persona, domain knowledge and rules. 💡When the Virtual User is invoked from Outbound Call with Workflow, this is the message played when the called party picks up. |
500 chars limit Supports Custom Parameters and System Parameters |
| Closing Message |
Final line the bot says before the activity exits.
💡Useful for handing the caller over politely ("Connecting you now…") or closing the loop on a self-service interaction. |
500 chars limit Supports Custom Parameters and System Parameters |
Voice & Language
| Property | Description | Notes |
|---|---|---|
| Language / Voice |
Optional spoken-language and voice selection. 💡Not available for Copilot Bots, which are configured via Speech Recognizers instead. |
Selection limited by Bot choice. |
Timeouts
| Property | Description | Notes |
|---|---|---|
| Session Timeout | Maximum total duration the Virtual User stays in the call. | seconds |
| Idle Timeout | How long the bot waits for caller input before taking the Idle Timeout exit. | seconds |
Tools
💡These settings allow to extend the Virtual User with external system capabilities: MCP Server and Web Requests. They can be selected independently and are both optional. Unselecting a tool keeps its stored configuration, so re-selecting it later restores everything you entered.
✅Precondition: Visible when “Nimbus AI Services - AI Workflow” Bot was selected as part of the previous “Bot Configuration”.
Flow Description
Describes how the conversation
| Property | Description |
|---|---|
| Flow Description |
A single free-text field on the Virtual User that tells the model…
|
💡How to write a good Flow Description
Keep it concrete and step-driven. The model performs best when it can read the description as a numbered playbook rather than as prose:
- Spell out the conversation phases (greet → identify → look up → confirm → close).
-
Name each tool by the exact label it has on the Virtual User — "call the
OrderLookupWeb Request", not "call the order system". -
The order of execution (e.g. FIRST validate
bank name,IBAN, THEN retrieveuser name,ONLY THEN answer theinquiry) -
Mandatory and optional steps with clear signal words (e.g.
these steps must be successful | this step can be optional) - Handle errors, outlining what to do if the tool fails or returns nothing.
- Avoid duplicating the system Instruction (role, tone, language). The Flow Description is about the technical information flow, not personality.
☝️Note: The following examples are reference points, not functionally verified.
Example 1 — Web-Request-only Virtual User (order status bot)
1. Greet the caller and ask for their order number.
2. Call the OrderLookup Web Request with the order number the caller provided.
3. If OrderLookup returns a result, read back the order status (shipped / processing / cancelled)
and the expected delivery date.
4. If OrderLookup returns no result or an error, apologise, offer to transfer to a human agent,
and end the conversation.
5. After confirming the status, ask whether there is anything else. If not, say goodbye and close.
Never invent an order status. Only state what OrderLookup returns.Example 2 — MCP-Server-only Virtual User (internal Jira helper)
1. Greet the caller and ask which Jira ticket they are calling about.
2. Use the JiraServer MCP Server to look up the ticket by ID.
- Prefer read-only tools first (get-issue, search-issues).
- Only use write tools (add-comment, transition-issue) if the caller explicitly asks for it
and confirms with "yes" before you make the change.
3. Summarise the ticket: title, status, assignee, last update.
4. If the caller asks for a change, perform it through the JiraServer, then read back what changed.
5. Close by confirming what was done and offering to do anything else with the same ticket.Example 3 — Mixed Web Requests + MCP Servers (concierge bot)
You handle two kinds of requests: account questions and ticket questions.
Account questions:
- Use the CustomerLookup Web Request to identify the caller by phone number.
- If CustomerLookup returns no match, ask the caller for their customer ID and try again.
Ticket questions:
- Use the JiraServer MCP Server for everything related to support tickets.
- Always look up the ticket first; never quote a status from memory.
General rules:
- Never expose internal IDs, URLs or raw tool output to the caller.
- If a tool fails twice in a row, apologise and offer to transfer to a human agent.
- Keep answers under three sentences unless the caller asks for detail.Extension Tools
Web Requests
Web Requests
A Web Request binding attaches a configured Web Request to the Virtual User, so the model can call it mid-conversation. Each binding has two fields on this page — the Web Request name itself, and an AI Description that tells the model when to call it.
✅Precondition: Requires at least one configured configured Web Requests from the same (or a parent) Organization Unit where your Virtual User lives in.
💡Use this when …
- … you want transparent definition and orchestration in Nimbus.
- … the validation logic must be auditable directly in Nimbus.
- … your called APIs are time-sensitive and tightly sequenced.
☝️Accounting for delays: Virtual User AI models are optimized for timely responses to a customer. A missing web request status code may be interpreted as “unresponsive”, which results in the “Failed” condition exit in Workflows being taken.
✅ Recommendation: When using AI-driven workflows, always enable “Wait for response” in your Web Requests > Response configuration. This is especially important when your AI workflow depends on the data being available.
💡Of course “Wait for response” also means that long-running requests may incur a delay that the customer will perceive as silence from the AI. (Expected) long-running requests should therefore be announced to the customer beforehand. Also, timeout exit codes are expected be sent by the target system so the AI knows when to move on.
| Property | Description |
|---|---|
|
Web Request (selection) |
Each Web Request:
☝️Flow Description dependency:
💡Example: Unlike MCPs more capability-based flow, Web Requests should have a clear order sequence to the flow, as information retrieved can be often co-dependent, specific and granular. An example Web Request-centric flow description could therefore look as follows: |
| AI Description |
This field tells the Virtual User how the Web Request is to be used. ☝ Note: The model does not see the Web Requests generic Description from its config page. Instead, use this AI Description to describe it to the model. 💡The AI Description should therefore also provide a precise description to the model, outlining the functional goals of the Web Request and necessary field descriptions to match with the customer conversation. |
MCP Server
MCP Server
An MCP Server attaches a Model Context Protocol endpoint to the Virtual User. Once attached, the server's tools are exposed to the model in real time during the call.
✅Precondition: Requires you to connect to a running, external MCP server, which offers more flexibility. The MCP server uses reusable Authentication configuration items — 🔎 also see Authentication in the property table row below.
💡Use this when…
- …you already operate or connect to existing MCP servers.
- …you want tools and capabilities to evolve independently of Nimbus, but constrain their usage.
- …you want long‑term flexibility with less UI configuration.
🔎Notes
- Scoped use: The AI model identifies each MCP Server by its Name and Description. The individual tools inside the server are advertised by the server itself over the MCP protocol — Nimbus does not rename or filter them. If you require scoped access, you should limit the capabilities server-side to prevent any unwanted tools from being (e.g only READ, not WRITE).
- 💡In the general → Flow Description, you should clearly define how MCP tools are to be used. The model will follow the order and logic you specify in the flow description, not the order in which the MCP servers were added into the Nimbus UI.
- Good to know: Nimbus Virtual User is compatible with MCP servers designed for OpenAI GPT‑Realtime, including remote MCP servers exposed over HTTP. More information can be found in the OpenAI MCP connector guide and Realtime API documentation.
| Property | Description |
|---|---|
| Name |
Each MCP server:
☝️The MCP Server “Name” Must be unique on the Virtual User. The model reads this name when deciding which server to call — use the same label inside the Flow Description (e.g. "use the |
| URL | The MCP Server's SSE endpoint (e.g. https://jira.example.com/mcp/sse). Nimbus opens a streaming connection to this URL for every Virtual User session that uses the server. |
| Description | Free-text summary of what the server is for and when the model should reach for it (e.g. "Internal Jira instance. Use for any ticket lookup, comment, or transition."). |
| Authentication |
✅Requires a (reusable) Authentication configuration to secure the connection to the MCP Server. 💡The dropdown lists the Authentications available in the Organization Unit of your Virtual User (and its parent units). Supported authentication types:
🔍 Notes:
|
☝️PLEASE TAKE NOTE:
- Failure Case handling: For both MCP and Web Request your flow description doesn't need to handle failure cases manually. This is done in the "Add Virtual User" Conversation Handling Activity. You can also define multiple “Intents” and treat them each like a different case.
- We highly recommend to limit and purpose-scope retrieved context via MCPs and Web Requests. If too many tools added, the Virtual User may slow down from tool usage or get the context wrong if too much data is provided. Also refer to our Best Practices - Virtual Users in Nimbus for further considerations.
Intents
An Intent represents an outcome the Virtual User can detect during a conversation. Instead of relying on a single Success outcome, you define multiple, intent-driven results and decide how each one continues in the Workflow.
✅Preconditions
🔎"Intent" feature availability: Intents are available for the following Bots: Intent Analyzer, AI Workflow and Open Profile, using either “Nimbus AI Services” and OpenAI GPT-Realtime models.
-
☝️Migration: Previous “Virtual User” activities: Previous Virtual User workflow activities had AI exits created on the workflow level (Audio Intent Analyzer) or hard-wired "Success" exits (AI Workflow, Open Profile) in the element. With the introduction of flexible intents, manual migration is necessary to avoid any disruptions and configuration errors.
- Simply replace the “Add Virtual User” activity with a new one to leverage flexible intents.
- Define at least one exit intent on the Virtual User configuration page, and map the exit intent on the workflow level. With no exit intent configured, the workflow will take the “AI Fallback” exit.
- 💡No migration required for Copilot bots: Copilot uses its own exit handling1. Copilot "Topics”, of which the outputs are then mapped into Bot Response Templates.
1 Depending on selected bot mode, the“Add Virtual User" Conversation Handling Activity is changing available configuration and exit properties.
| Property | Description |
|---|---|
| Name |
Mandatory, unique name for the intent — this is the label you later select on the “Add Virtual User” activity when mapping it to a Workflow exit. 💡Keep it to one word and avoid special characters (e.g. create_ticket) so the AI model detects it reliably. |
| Description | Mandatory free-text that tells the Virtual User when to assign this intent (e.g. “The caller wants to create a new support ticket”). |
| “This intent triggers an exit” toggle |
Steers the behavior of this intent during the activity:
|
| Parameters | Optionally attach up to 10 Parameters per intent for storing customer-provided data. The AI decides which conversation data to write into them. 💡The AI can immediately return the parameter contents back to the customer, e.g. to verify if it has correctly understood the instructions. |
☝️Good to know
- An already used (exit) intent cannot be deleted while it is already used in any Workflow — the delete option is disabled to avoid breaking the Workflow.
- At least one exit intent must be mapped on the “Add Virtual User” activity before that activity can be saved.
Modalities
| Property | 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:
|
Licenses
| Property | Description |
|---|---|
| Licenses |
✅You may need to store and re-open your Virtual User configuration before you can re-apply a license. ✅In order to take action within a workflow, every individual Virtual User needs a license applied. You may freely (re-)assign licenses from your License Management. If you require additional licenses, get in touch with Luware Customer Success. |
Follow-up Steps
✅Follow-Up:
- In order to take effect, Virtual Users must be added as “Add Virtual User” activity to your Audio/Video workflows.
- We highly recommend to do test-calls to your service and thoroughly test every Virtual User change.
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.
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.
Microsoft Copilot Limitations
- Expect processing delays: Processing AI answers takes a few seconds for voice-to-text-transcription, followed by AI processing and then the same 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 this 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 AI Services - Profile: Intent Analyzer
🔎By design (not a limitation or reportable issue):
- The Nimbus Intent analyzer Bot runs on pre-defined prompts. Any usage outside of the descriptions specified under Use Case - Setting up a Nimbus Virtual User for Intent Analysis is not supported.
-
Fallback handling: If a workflow uses exits with multiple parameters, e.g. to collect
customer nameandinvoice number, and only one parameter can be retrieved, the fallback exit is taken.
Nimbus / Custom AI Services - Profile: AI Workflow
🔎By design (not a limitation or reportable issue):
- Failed condition: If either a Web Request connection or MCP server connection fails, the “Failed” workflow activity exit will be taken immediately. Also applies for any other Nimbus-internal or technical error.
- Fallback condition: Any “Fallback” parameters will be updated with the response generated by the AI when a case cannot be handled.
☝️Current limitations, coming with a later update:
- For this profile there currently are no custom exits in the “Add Virtual User” Conversation Handling Activity. You only have Success, Fallback, Failed, Idle timeout.
- There is currently no support for custom Parameters in “Add Virtual User” Conversation Handling Activity.
Custom AI Services - Profile: Open Profile
☝️Current limitations, coming with a later update:
- The use of Extensions Tools (either Web Request or MCP Server) is currently mandatory in this profile. 💡This will be improved in a future update to allow for no tools to be used.
- For this profile there currently there are no custom exits in the “Add Virtual User” Conversation Handling Activity. You only have Success, Fallback, Failed, Idle timeout.
- There is currently no support for custom Parameters in “Add Virtual User” Conversation Handling Activity.