Edit

Share via

Quickstart: Use the chat playground in Azure AI Foundry portal

In this quickstart, you use Azure AI Foundry to deploy a chat model and use it in the chat playground in Azure AI Foundry portal.

For this quickstart, you can use either a hub-based project or a Azure AI Foundry project. For more information about the differences between these two project types, see Project types.

If you don't have an Azure subscription, create one for free.

First run experience

Use this fast path when you don't have any projects yet. Pick what you want to do and we create the project and get you into the right playground. It is suggested to start with an agent but you can also explore models through the Foundry portal or model catalog.

To start with an agent, use the following steps:

  1. In the top breadcrumb, select Azure AI Foundry, then select Create an agent.

  2. Enter a project name. Confirm your directory and subscription. Select Create.

    Screenshot of Agents playground showing a default agent loaded with GPT-4o deployed. Chat interface and agent details panel are visible.

  3. When prompted, choose a model. We recommend gpt-4o for best quality, or gpt-4o-mini for lower cost.

    Screenshot showing the model selection dialog during agent deployment.

  4. Select Deploy on the final confirmation page after selecting a deployment type, and you see the Agents playground with your agent ready to chat.

    Screenshot of Agents playground showing a default agent loaded with GPT-4o deployed. The chat interface and agent details panel are visible.

  5. You see the Agents playground with your agent ready to chat.

    Screenshot of the Agents playground using gpt-4o.

Chat in the playground without your data

In the Azure AI Foundry playground, you can observe how your model responds with and without your data. In this quickstart, you test your model without your data.

To chat with your deployed model in the chat playground, follow these steps:

  1. In the System message text box, provide this prompt to guide the assistant: "You're an AI assistant that helps people find information." You can tailor the prompt for your scenario.

  2. Optionally, add a safety system message by selecting the Add section button, then Safety system messages. Choose from the prebuilt messages, and then edit them to your needs.

  3. Select Apply changes to save your changes, and when prompted to see if you want to update the system message, select Continue.

  4. In the chat session pane, enter the following question: "How much do the TrailWalker hiking shoes cost?"

  5. Select the right arrow icon to send.

    Screenshot of the first chat question without grounding data.

  6. The assistant either replies that it doesn't know the answer or provides a generic response. For example, the assistant might say, "The price of TrailWalker hiking shoes can vary depending on the brand, model, and where you purchase them." The model doesn't have access to current product information about the TrailWalker hiking shoes.

Next, you can add your data to the model to help it answer questions about your products. Try the Deploy an enterprise chat web app tutorial to learn more.

Related content