Model

Available agent types

When creating an agent, you must select an agent type.

An agent type determines:

• The AI provider (OpenAI or Azure AI)

• The model or deployment

• The available properties and behavior of the agent

IMPORTANT!

• For OpenAI, the selected agent type directly determines the model

• For Azure AI, additional configuration is required in the Model section

This means that for Azure, the selected agent type must match your configured deployment

---

OpenAI

OpenAI uses direct model selection.

Connection

Select your OpenAI API key connection.

Model

Choose a model directly:

• GPT-5 models – Recommended for advanced use cases and production agents

• Transcription models – For audio-to-text workflows

---

Azure AI

Azure uses resource name and deployments instead of direct model names.

Connection

Select your Azure API key connection.

Resource name

The name of your Azure AI resource -> this can be found in the Azure portal.

Deployment name

The name of the deployed model in Azure.

⚠️ Important:

• This is not the model name

• This is the deployment name you created in Azure

---

Common issues

• Incorrect resource name

• Incorrect deployment name

• Using a model name instead of a deployment name

If the agent does not respond, verify these values first.

---

Next steps

Once the model is configured:

• Continue with Settings

• Define Instruction

• Configure Input and Output