Configure AI nodes

Use the AI nodes in Dialogue Studio for standardize AI actions like summarize, entity extractions, action detection, and more.

Prerequisites

• Administrator access to the UCC A Unified Contact Center, or UCC, is a queue of interactions (voice, email, IM, etc.) that are handled by Agents. Each UCC has its own settings, IVR menus and Agents. Agents can belong to one or several UCCs and can have multiple skills (competencies). A UCC can be visualized as a contact center “micro service”. Customers can utilize one UCC (e.g. a global helpdesk), a few UCC’s (e.g. for each department or regional office) or hundreds of UCC’s (e.g. for each bed at a hospital). They are interconnected and can all be managed from one central location. Config SharePoint site.
• An Azure OpenAI resource in your Azure subscription.
  If you need to create one, follow Microsoft’s guidance, and then return here.
• The Azure OpenAI API key, endpoint, and model deployment name, for example gpt‑4o‑mini.

Add Azure OpenAI Config to Dialogue Studio

AI nodes use the any-ai-azure-openai-config configuration node. You can reuse one configuration node across multiple AI nodes, or create multiple configuration nodes if you want to use different models.

1. Open Azure AI Studio and select your Azure OpenAI resource.

2. Copy the Endpoint value, which ends with .openai.azure.com/.

3. Create or copy an API key.

4. Under Deployments, copy the deployment name that you want to use, for example gpt‑4o‑mini.

5. Open your Dialogue Studio application.

6. Drag any AI node into the canvas, and then click + to add an Azure OpenAI Config.

7. Enter the following information:

   1. Name (optional) - A label to identify this configuration instance, for example the model name.

   2. Azure OpenAI endpoint - Paste the endpoint URL.

      For example: https://<resource>.openai.azure.com/openai/v1/responses.

   3. Model Name - Your Azure deployment or model name, for example o1-mini, gpt-5-nano, or gpt-4o-mini. This is the name you copied from Deployments.

   4. Model Type - Reasoning models, such as o1 and GPT-5, add reasoning: { effort: "low" } and text: { verbosity: "low" }. Standard models, such as GPT-4o, omit these settings and use classic parameters such as top_p and penalties, as configured per node.

   5. API Key - Your Azure OpenAI API key. This is stored in the credentials store.

   6. Timeout (ms) - The request timeout in milliseconds. The default is 10000. Allowed values are clamped between 1000 and 60000.

   7. Max Retries - The number of retry attempts for transient errors or timeouts. The default is 2, and the maximum is 10. Retries use exponential backoff.

   8. Input Token Cap - The maximum estimated number of input tokens before truncation. The default is 20000, which is approximately 80,000 characters. When the cap is exceeded, the oldest content is removed first.