Get started with generative AI and agents in Microsoft Foundry

Hi, I’m Anton.
I’ll be here to help you with hints and tips as you work through this lab, in which you’ll deploy a generative AI model and create an agent.

If you want more interactive help, you can chat with me in the Ask Anton app.

Ask Anton is a generative AI agent that can answer questions about AI concepts and Microsoft Foundry technologies. It's available in two versions at https://aka.ms/choose-anton:

Azure-based: Best experience (requires an Azure subscription and deployment of a model in a Foundry project).
Browser-based: Use a small language model in your browser (reduced functionality - may be slow or work only in "basic" mode in older/lower-spec devices).

Ask Anton is not a supported Microsoft product or a component of Microsoft Learn or AI Skills Navigator.

This lab should take approximately 35 minutes to complete.

Note: Many components of Microsoft Foundry, including the Microsoft Foundry portal, are subject to continual development. This reflects the fast-moving nature of artificial intelligence technology. Some elements of your user experience may differ from the images and descriptions in this exercise!

Create a Microsoft Foundry project

Microsoft Foundry uses projects to organize models, resources, data, and other assets used to develop an AI solution.

In a web browser, open Microsoft Foundry at https://ai.azure.com and start building; signing in using your Azure credentials. Close any tips or quick start panes that are opened the first time you sign in, and if necessary use the Foundry logo at the top left to navigate to the home page.
If it isn’t already enabled, in the tool bar the top of the page, enable the New Foundry option.
If you do not have any existing projects, you will be prompted to create one. Create a new project with a unique name; expanding the Advanced options area to specify the following settings for your project (or you can select an existing project if you have one!):
- Foundry resource: A valid name for your Foundry resource.
- Subscription: Your Azure subscription
- Resource group: Create or select a resource group
- Region: Select any of the AI Foundry recommended regions in this list
Tip: Depending on your permissions in the Azure subscription, you may need to clear the option to set up recommended resources.
Wait for your project to be created. It may take a few minutes. Then close any welcome dialogs that are displayed.

After creating or selecting a project in the new Foundry portal, it should open in a page similar to the following image:

Deploy a model

At the heart of every AI agent, there’s a large language model (LLM). Let’s find one in the Foundry models catalog.

Now you’re ready to explore models. On the Discover page, select the Models tab to view the Microsoft Foundry model catalog.

Microsoft Foundry provides a large collection of models from Microsoft, OpenAI, and other providers, that you can use in your AI apps and agents.
Search for and select the gpt-5-mini model, and view the page for this model, which describes its features and capabilities.
Use the Deploy button to deploy the model using the default settings. Deployment may take a minute or so.

Tip: If you already have a gpt model deployment, you can use it instead of deploying a new one. Model deployments are subject to regional quotas. If you don’t have enough quota to deploy a gpt-5-mini model in your project’s region, you can use a different gpt chat-capable model - such as gpt-5-nano, or gpt-5.4-mini. Alternatively, you can create a new project in a different region.
When the model has been deployed, view the model playground page that is opened, in which you can chat with the model.

Chat with the model

You can use the playground to explore the model by chatting with it.

Use the button at the bottom of the left navigation pane to hide it and give yourself more room to work with.
In the Chat pane, enter a prompt such as Who was Ada Lovelace?, and review the response.
Enter a follow-up prompt, such as Tell me more about her work with Charles Babbage. and review the response.

Tip: Generative AI chat applications often include the conversation history in the prompt; so the context of the conversation is retained between messages. In this case, “her” is interpreted as referring to Ada Lovelace.
In the model playground, at the top-right of the chat pane, use the New chat button to restart the conversation and remove the conversation history.

Let’s try asking about the same subject with a more specific prompt.
Enter the prompt List three facts about Ada Lovelace. and review the response.

The response should reflect the explicit instructions in the prompt.

Tip: The difference in the response illustrates a key feature of using an LLM. LLM responses are generated dynamically by the model - not looked up in a static data source. On the one hand, this makes LLMs more flexible; but on the other hand it means that the response generated may not be grounded in authoritative facts. Later, we’ll explore how to add a knowledge source to ground generative AI responses.

Specify instructions

To support specific use cases, you should use a system prompt to provide the model with instructions that guide its responses. You can use the system prompt to give the model a specific focus or role, and provide guidelines about format, style, and constraints about what the model should and shouldn’t include in its responses.

In the model playground, at the top right of the chat pane, use the New chat button to restart the conversation and remove the conversation history.

In the pane on the left, in the Instructions text area, change the system prompt to:

You are an expert in the history of computing and AI. You only answer questions about significant people and events in the development of computing, and about notable vintage computers. Do not engage in conversations on any topic that is unrelated to computing history.

Enter a new prompt, such as Tell me about ELIZA. and view the response.
Continue the conversation with prompts such as How does it compare with modern LLMs?.
Try asking an “off-topic” question, such as What's the capital of Spain?; and view the response.

Add a web_search tool

So far, the model has answered questions based on the data with which it was trained. While this is useful, that leaves out a lot of current information on the web; which might help the model give more relevant answers.

We can use tools to give models access to external data sources, and to perform custom tasks. Let’s add a tool that enables the model to search the Web for up-to-date information.

In the pane on the left, under the instructions, expand the Tools section if it isn’t already expanded.
In the Add drop-down list, enable Web search. Then read the information about the tool.
In the model playground, at the top right of the chat pane, use the New chat button to restart the conversation.
With the web_search tool listed in the pane on the left, in the chat pane, enter the prompt Find a vintage computer store near Seattle (or your local city!) and review the response.

The model should have searched the Web for vintage computer stores near the specific city.

Add knowledge

The combination of the model’s training data and a tool to search the web can often be enough to support a comprehensive, general-purpose chat agent. However, often an agent needs to work in the context of a particular business or scenario, in which there’s specialized or proprietary information that it needs to reason over when responding.

In this exercise, we’ll give the model a file search tool with access to information about common manufacturer serial numbers that might be found on the printed circuit boards (PCBs) of vintage computers.

Open a new browser tab, and view the vintage_computer_identifiers.docx at https://microsoftlearning.github.io/mslearn-ai-fundamentals/data/vintage_computer_identifiers.docx. We’ll use this to provide a knowledge source that the agent can use to identify computers based on serial numbers, product IDs, and other common printed details.
Download vintage_computer_identifiers.docx to your local computer.
Return to the tab containing the agent playground, and in the pane on the left, in the Tools section, upload the vintage_computer_identifiers.docx file, creating a new index with the default index name. When the index has been created, attach it to the agent.
In the model playground, at the top right of the chat pane, use the New chat button to restart the conversation.
In the Chat tab, enter the prompt I have a printed circuit board with the "ASSY 250425" on it. What can you tell me about it? and view the response.

This time the response should be informed by the information in the expenses data source.
Try a few more prompts - for example, What kind of computer does a PCB with "820-001A" come from? or What about "i386"?.

When there’s relevant information in the file, the model will use it to answer. If no information is found, the model will use its own training knowledge or the web_search tool.

Save the model configuration as an agent

While you can implement generative AI apps using a standalone model, to create a fully agentic AI experience, you need to encapsulate the model, its instructions, and its tool configuration in an agent. By encapsulating the instructions and tools in an agent, you can connect client applications to its endpoint without any need for them to specify a system prompt or implement their own retrieval augmented generation (RAG) logic to add contextual knowledge.

In the model playground, at the top right select Save as agent. Then, when prompted, name your new agent computing-historian.

When the agent is created, it opens in a new playground specifically for working with agents.

In the pane on the right, view the YAML tab, which contains the definition for your agent. Note that its definition includes the model, its parameter settings, and the instructions you specified - similar to this:

 metadata:
   logo: Avatar_Default.svg
   microsoft.voice-live.enabled: "false"
 object: agent.version
 id: computing-historian:1
 name: computing-historian
 version: "1"
 description: ""
 created_at: 1784419039
 definition:
   kind: prompt
   model: gpt-5-mini
   instructions: You are an expert in the history of computing and AI. You only answer questions about significant people and events in the development of computing, and about notable vintage computers. Do not engage in conversations on any topic that is unrelated to computing history.
   tools:
     - type: web_search
     - type: file_search
       vector_store_ids:
         - vs_qpRG020jZSewWHPI7B06q2V4
 status: active
 instance_identity:
   principal_id: 0000000-0000000-000000000
   client_id: 0000000-0000000-000000000
 blueprint:
   principal_id: 0000000-0000000-000000000
   client_id: 0000000-0000000-000000000
 blueprint_reference:
   type: ManagedAgentIdentityBlueprint
   blueprint_id: computing-historian-c9996
 agent_guid: c0000000-0000000-000000000

Switch back to the Chat tab, and enter the prompt Who are you?

The response should indicate that the agent is “aware” of its role as a computing historian.

Preview the agent

Now you have a working agent, you can preview it in a basic web chat application.

At the top of the chat pane, in the Publish drop-down list, select Preview web app.

A preview chat interface is opened in a new browser tab.
Enter a prompt, such as What can you tell me about the Altair 8800? and view the response from your agent.

View client code to access the agent in your project

The agent is defined within your Foundry project, and there’s a convenient way to develop apps that connect to it there; allowing you to iteratively refine both the agent and the client app to create the solution you need.

In the agent playground, switch from the Chat tab to the Call agent tab, and view the sample code for consuming the agent; which should be similar to this:
```
 # Before running the sample:
 # pip install azure-ai-projects>=2.1.0
    
 from azure.identity import DefaultAzureCredential
 from azure.ai.projects import AIProjectClient
    
 endpoint = "https://ai-resrce.services.ai.azure.com/api/projects/ai-project"
    
 project_client = AIProjectClient(
     endpoint=endpoint,
     credential=DefaultAzureCredential(),
 )
    
 my_agent = "computing-historian"
 my_version = "1"
    
 openai_client = project_client.get_openai_client()
    
 # Reference the agent to get a response
    
 response = openai_client.responses.create(
     input=[{"role": "user", "content": "Tell me what you can help with."}],
     extra_body={"agent_reference": {"name": my_agent, "version": my_version, "type": "agent_reference"}},
 )
    
 print(f"Response output: {response.output_text}")
```
The code to connect to your agent uses the Azure.AI.Projects library to create an AIProjectClient object connected to your Foundry project. Since this involves connecting to a project, which may contain privileged resources, key-based authentication is not supported, and the application must use an Entra ID identity to be authenticated.

After connecting to the project, the code uses the project client’s get_openai_client method to retrieve an OpenAI client object; with which it can submit prompts to the agent using the same Responses API we previously saw being used to chat with a model. Since a project can contain multiple agents and models, the specific agent details are specified as extra_body in the responses.create method.

Summary

In this exercise, you explored how to deploy and chat with a generative AI model in Microsoft Foundry portal. You then saved the model as an agent with instructions and tools.

The agent explored in this exercise is a simple example that demonstrates how quickly and easily you can get started with generative AI app and agent development using Microsoft Foundry. From this foundation, you could build a comprehensive agentic solution in which agents use tools to find information and automate tasks, and collaborate with one another to perform complex workflows.

Clean Up

If you have finished exploring Microsoft Foundry, you should delete the resources created in this exercise to avoid unnecessary utilization charges.

Open the Azure portal at https://portal.azure.com and view the contents of the resource group where you deployed the project used in this exercise.
On the toolbar, select Delete resource group.
Enter the resource group name and confirm that you want to delete it.

If you used the Ask Anton app during this lab, we’d love you to tell us about your experience with it!