Simple Agent QuickStart (Java Copilot SDK)

A simple AI agent built with the GitHub Copilot SDK for Java, running as an Azure Function.

Looking for TypeScript, Python, or C#?

Prerequisites

• Java 17+
• Maven 3.8+
• Azure Functions Core Tools
• Azure Developer CLI (azd) (only needed for deploying Microsoft Foundry resources)
• Access to an AI model via one of:
  • GitHub Copilot subscription — models are available automatically
  • Bring Your Own Key (BYOK) — use an API key from Microsoft Foundry (see BYOK docs)

Quickstart

Want to use your own models? See Deploy Microsoft Foundry Resources below to provision a Microsoft Foundry project instead of using GitHub Copilot models.

1. Clone the repository

2. Build the project:

   mvn clean package -DskipTests

3. Run the function locally:

   func start

4. Test the agent (in a new terminal):

   # Interactive chat client
   mvn exec:java -Dexec.mainClass="com.function.Chat"
   
   # Or use curl directly
   curl -X POST http://localhost:7071/api/ask -d "what are the laws"

   To chat with a deployed instance, grab the URL and function key from your azd environment:

   export AGENT_URL=$(azd env get-value SERVICE_API_URI)
   export FUNCTION_KEY=$(az functionapp keys list \
     -n $(azd env get-value AZURE_FUNCTION_APP_NAME) \
     -g $(azd env get-value RESOURCE_GROUP) \
     --query "functionKeys.default" -o tsv)
   
   mvn exec:java -Dexec.mainClass="com.function.Chat"

Source Code

The agent logic is in src/main/java/com/function/Ask.java. It creates a CopilotClient, configures a session with a system message (Asimov's Three Laws of Robotics), and exposes an HTTP endpoint (/api/ask) that accepts a prompt and returns the agent's response.

src/main/java/com/function/Chat.java is a lightweight console client that POSTs messages to the function in a loop, giving you an interactive chat experience. It defaults to http://localhost:7071 but can be pointed at a deployed instance via the AGENT_URL environment variable.

Deploy Microsoft Foundry Resources

If you prefer to use your own models via BYOK and don't already have a Microsoft Foundry project with a model deployed:

azd auth login
azd up

This provisions all resources and configures local development automatically.

What Gets Deployed

• Microsoft Foundry project with GPT-5-mini model
• Azure Functions app (Java 17, Flex Consumption plan)
• Storage, monitoring, and all necessary RBAC role assignments
• Optional: Search for vector store (disabled by default)
• Optional: Cosmos DB for agent thread storage (disabled by default)

Using Microsoft Foundry (BYOK)

By default the agent uses GitHub Copilot's models. To use your own model from Microsoft Foundry instead, set these environment variables:

export AZURE_OPENAI_ENDPOINT="https://<your-ai-services>.openai.azure.com/"
export AZURE_OPENAI_API_KEY="<your-api-key>"
export AZURE_OPENAI_MODEL="gpt-5-mini"  # optional, defaults to gpt-5-mini

Getting these values:

• If you ran azd up, the endpoint is already in your environment — run azd env get-values | grep AZURE_OPENAI_ENDPOINT
• For the API key, go to Azure Portal → your AI Services resource → Keys and Endpoint → select the Azure OpenAI tab
• Or find both in the Microsoft Foundry portal under your project settings

See the BYOK docs for details.

Learn More

• GitHub Copilot SDK for Java
• GitHub Copilot SDK
• BYOK (Bring Your Own Key)
• Azure Developer CLI