A Bot is the connection between Nimbus and the AI service that drives a Virtual User. The Bot holds the reference to the service, the agent technology and — for customer-provided services — the endpoint and credentials.
✅Please note that Bots only work in conjunction with Virtual Users, so the same preconditions apply.
Configuring Bots
A Bot is described by two co-dependent fields: a Bot / Service Type (who hosts the AI) and an AI Service (which underlying model or channel the bot uses). The Profile (Intent Analyzer / AI Workflow / Open Profile) is selected on the Virtual User, not on the Bot.
Bots for Nimbus AI Services can also be created or updated with the Virtual User Configuration Assistant in Companion:
- Enter a name and select the Organization Unit from a form, so no object IDs need to be pasted, and Companion creates or updates the bot only after your confirmation.
- Bots of type Custom AI Services (with endpoint and API key) still need to be configured manually on this page.
💡Note that only users with sufficient permissions can create or update bots this way.
Choosing a Bot type
The Type / AI Service (combination decides which Profile options become available on a Virtual User) that references this Bot. Refer to the comparison below:
The Bot configuration in Nimbus is built to be as flexible as possible, so common concepts can be re-used. Each Bot configuration consists of the following properties, depending on the “Type” selection.
Common Properties
✅These properties are shared for Nimbus AI Service and Custom AI Services
| Property | Description |
|---|---|
| Name | Name of the Bot, as it appears in Nimbus lists and selections. |
| Organization Unit | Determines where the Bot will be available for selection within Nimbus UIs. |
| Type |
Decides who hosts the AI. Two values:
☝️ This choice gates the rest of the form: Custom AI Service unlocks Endpoint, Authentication Type and API Key; Nimbus AI Service hides them. The choice also filters the available AI Service options. |
| AI Service |
Co-dependent on Type. Selects the underlying agent that handles the conversation: For Type = Nimbus AI Services → Azure OpenAI GPT Realtime (default)
⮑ Related settings: The AI Service selection determines and filters the Profile / Prompt Preset dropdown on the Virtual Users configuration page. |
Custom AI Service Properties
✅These properties are defined for Custom AI Services only. External APIs require a sign-up and configuration outside of Nimbus.
💡Nimbus native AI services do not require further API configuration. The corresponding fields are not shown, you can directly “Create” your bot.
| Field | Description | ||||
|---|---|---|---|---|---|
| Authentication Type | API Key (current default) | ||||
| API Key |
The API key for your external API access. 💡The bot uses the authentication to leverage API features. Specific permissions are granted in the 3rd-party UI. |
||||
| Endpoint |
The Endpoint of the API your bot should use. 💡This is the API address where the bot can send Request and get Responses. This depends on what you want the bot to do (e.g., send a message, get weather data, etc.). M365 Copilot Direct Line 3.0Copilot Endpoints
1 ☝A request might fail if you use the global base URI for a regional bot, as some requests could go beyond geographical boundaries. The URLs are maintained by Microsoft and retrieved from the Learn | Direct Line documentation. We advise to test performance and stability. 🧠Don't forget: Note down the endpoint for later use, e.g. for the Bots configuration of your Nimbus Virtual Users. Azure OpenAI GPT RealtimeOpenAI GPT Realtime EndpointsCustomers have to set up their own model within Azure foundry. This provides the Target URI (Endpoint) and API Key. |
🔎Note: Shared bot resource utilization
💡A single Bot resource (and underlying API) can be shared across all Virtual Users that reference it. A single Bot can therefore serve multiple Virtual User configurations (e.g. one for Intent Analyzer, one for AI Workflow).
☝️Bots and related 3rd party API are subject to external licensing and rate limits. When utilized by many services simultaneously, rate limits may be exceeded quickly and a bot may cease operation.