ai-agents-for-beginners

ðŸŽĻ āļĢāļđāļ›āđāļšāļšāļāļēāļĢāļ­āļ­āļāđāļšāļšāđ€āļ­āđ€āļĒāđˆāļ™āļ•āđŒāļāļąāļš Azure OpenAI (Responses API) (.NET)

📋 āļ§āļąāļ•āļ–āļļāļ›āļĢāļ°āļŠāļ‡āļ„āđŒāļāļēāļĢāđ€āļĢāļĩāļĒāļ™āļĢāļđāđ‰

āļ•āļąāļ§āļ­āļĒāđˆāļēāļ‡āļ™āļĩāđ‰āđāļŠāļ”āļ‡āļĢāļđāļ›āđāļšāļšāļāļēāļĢāļ­āļ­āļāđāļšāļšāļĢāļ°āļ”āļąāļšāļ­āļ‡āļ„āđŒāļāļĢāļŠāļģāļŦāļĢāļąāļšāļāļēāļĢāļŠāļĢāđ‰āļēāļ‡āđ€āļ­āđ€āļĒāđˆāļ™āļ•āđŒāļ­āļąāļˆāļ‰āļĢāļīāļĒāļ°āđ‚āļ”āļĒāđƒāļŠāđ‰ Microsoft Agent Framework āđƒāļ™ .NET āļ—āļĩāđˆāļœāļŠāļēāļ™āļĢāļ§āļĄāļāļąāļš Azure OpenAI (Responses API) āļ„āļļāļ“āļˆāļ°āđ„āļ”āđ‰āđ€āļĢāļĩāļĒāļ™āļĢāļđāđ‰āļĢāļđāļ›āđāļšāļšāđāļĨāļ°āđāļ™āļ§āļ—āļēāļ‡āļŠāļ–āļēāļ›āļąāļ•āļĒāļāļĢāļĢāļĄāļĢāļ°āļ”āļąāļšāļĄāļ·āļ­āļ­āļēāļŠāļĩāļžāļ—āļĩāđˆāļ—āļģāđƒāļŦāđ‰āđ€āļ­āđ€āļĒāđˆāļ™āļ•āđŒāļžāļĢāđ‰āļ­āļĄāđƒāļŠāđ‰āļ‡āļēāļ™āđƒāļ™āļŠāļ āļēāļžāđāļ§āļ”āļĨāđ‰āļ­āļĄāļāļēāļĢāļœāļĨāļīāļ• āļ”āļđāđāļĨāļĢāļąāļāļĐāļēāļ‡āđˆāļēāļĒ āđāļĨāļ°āļ‚āļĒāļēāļĒāļ•āļąāļ§āđ„āļ”āđ‰

āļĢāļđāļ›āđāļšāļšāļāļēāļĢāļ­āļ­āļāđāļšāļšāļĢāļ°āļ”āļąāļšāļ­āļ‡āļ„āđŒāļāļĢ

ðŸŽŊ āļ›āļĢāļ°āđ‚āļĒāļŠāļ™āđŒāđ€āļ‰āļžāļēāļ°āļŠāļ–āļēāļ›āļąāļ•āļĒāļāļĢāļĢāļĄāđƒāļ™ .NET

āļ„āļļāļ“āļŠāļĄāļšāļąāļ•āļīāļĢāļ°āļ”āļąāļšāļ­āļ‡āļ„āđŒāļāļĢ

āļĢāļđāļ›āđāļšāļšāļžāļĢāđ‰āļ­āļĄāđƒāļŠāđ‰āļ‡āļēāļ™āđƒāļ™āļŠāļ āļēāļžāđāļ§āļ”āļĨāđ‰āļ­āļĄāļāļēāļĢāļœāļĨāļīāļ•

🔧 āļŠāļ–āļēāļ›āļąāļ•āļĒāļāļĢāļĢāļĄāļ—āļēāļ‡āđ€āļ—āļ„āļ™āļīāļ„

āļ­āļ‡āļ„āđŒāļ›āļĢāļ°āļāļ­āļšāļŦāļĨāļąāļāļ‚āļ­āļ‡ .NET

āļāļēāļĢāđƒāļŠāđ‰āļ‡āļēāļ™āļĢāļđāļ›āđāļšāļšāļāļēāļĢāļ­āļ­āļāđāļšāļš

graph LR
    A[IServiceCollection] --> B[āļ•āļąāļ§āļŠāļĢāđ‰āļēāļ‡ Agent]
    B --> C[āļāļēāļĢāļāļģāļŦāļ™āļ”āļ„āđˆāļē]
    C --> D[āļ—āļ°āđ€āļšāļĩāļĒāļ™āđ€āļ„āļĢāļ·āđˆāļ­āļ‡āļĄāļ·āļ­]
    D --> E[āļ•āļąāļ§āđāļ—āļ™ AI]

🏗ïļ āļĢāļđāļ›āđāļšāļšāļĢāļ°āļ”āļąāļšāļ­āļ‡āļ„āđŒāļāļĢāļ—āļĩāđˆāđāļŠāļ”āļ‡āđƒāļ™āļ•āļąāļ§āļ­āļĒāđˆāļēāļ‡

1. āļĢāļđāļ›āđāļšāļšāļŠāļĢāđ‰āļēāļ‡ (Creational Patterns)

2. āļĢāļđāļ›āđāļšāļšāļžāļĪāļ•āļīāļāļĢāļĢāļĄ (Behavioral Patterns)

3. āļĢāļđāļ›āđāļšāļšāđ‚āļ„āļĢāļ‡āļŠāļĢāđ‰āļēāļ‡ (Structural Patterns)

📚 āļŦāļĨāļąāļāļāļēāļĢāļ­āļ­āļāđāļšāļš .NET

āļŦāļĨāļąāļāļāļēāļĢ SOLID

āļŠāļ–āļēāļ›āļąāļ•āļĒāļāļĢāļĢāļĄāļŠāļ°āļ­āļēāļ” (Clean Architecture)

🔒 āļāļēāļĢāļžāļīāļˆāļēāļĢāļ“āļēāļŠāļģāļŦāļĢāļąāļšāļ­āļ‡āļ„āđŒāļāļĢ

āļ„āļ§āļēāļĄāļ›āļĨāļ­āļ”āļ āļąāļĒ

āļ›āļĢāļ°āļŠāļīāļ—āļ˜āļīāļ āļēāļž

āļāļēāļĢāļ›āļĢāļąāļšāļ‚āļ™āļēāļ”

🚀 āļāļēāļĢāļ›āļĢāļąāļšāđƒāļŠāđ‰āđƒāļ™āļŠāļ āļēāļžāđāļ§āļ”āļĨāđ‰āļ­āļĄāļāļēāļĢāļœāļĨāļīāļ•

āļžāļĢāđ‰āļ­āļĄāļŠāļĢāđ‰āļēāļ‡āđ€āļ­āđ€āļĒāđˆāļ™āļ•āđŒāļ­āļąāļˆāļ‰āļĢāļīāļĒāļ°āļĢāļ°āļ”āļąāļšāļ­āļ‡āļ„āđŒāļāļĢāļāļąāļš .NET āđāļĨāđ‰āļ§āļŦāļĢāļ·āļ­āļĒāļąāļ‡? āļĄāļēāļŠāļĢāđ‰āļēāļ‡āļŠāļ–āļēāļ›āļąāļ•āļĒāļāļĢāļĢāļĄāļ—āļĩāđˆāļĄāļąāđˆāļ™āļ„āļ‡āļāļąāļ™āđ€āļ–āļ­āļ°! ðŸĒâœĻ

🚀 āđ€āļĢāļīāđˆāļĄāļ•āđ‰āļ™

āļŠāļīāđˆāļ‡āļ—āļĩāđˆāļ•āđ‰āļ­āļ‡āđ€āļ•āļĢāļĩāļĒāļĄ

āļ•āļąāļ§āđāļ›āļĢāļŠāļ āļēāļžāđāļ§āļ”āļĨāđ‰āļ­āļĄāļ—āļĩāđˆāļ•āđ‰āļ­āļ‡āļ•āļąāđ‰āļ‡āļ„āđˆāļē

# zsh/bash
export AZURE_OPENAI_ENDPOINT=https://<your-resource>.openai.azure.com
export AZURE_OPENAI_DEPLOYMENT=gpt-5-mini
# āļˆāļēāļāļ™āļąāđ‰āļ™āļĨāļ‡āļŠāļ·āđˆāļ­āđ€āļ‚āđ‰āļēāđƒāļŠāđ‰āđ€āļžāļ·āđˆāļ­āđƒāļŦāđ‰ AzureCliCredential āļŠāļēāļĄāļēāļĢāļ–āļĢāļąāļšāđ‚āļ—āđ€āļ„āđ‡āļ™āđ„āļ”āđ‰
az login
# PowerShell
$env:AZURE_OPENAI_ENDPOINT = "https://<your-resource>.openai.azure.com"
$env:AZURE_OPENAI_DEPLOYMENT = "gpt-5-mini"
# āļˆāļēāļāļ™āļąāđ‰āļ™āđ€āļ‚āđ‰āļēāļŠāļđāđˆāļĢāļ°āļšāļšāđ€āļžāļ·āđˆāļ­āđƒāļŦāđ‰ AzureCliCredential āļŠāļēāļĄāļēāļĢāļ–āļĢāļąāļšāđ‚āļ—āđ€āļ„āđ‡āļ™āđ„āļ”āđ‰
az login

āļ•āļąāļ§āļ­āļĒāđˆāļēāļ‡āđ‚āļ„āđ‰āļ”

āđ€āļžāļ·āđˆāļ­āļĢāļąāļ™āļ•āļąāļ§āļ­āļĒāđˆāļēāļ‡āđ‚āļ„āđ‰āļ”,

# zsh/bash
chmod +x ./03-dotnet-agent-framework.cs
./03-dotnet-agent-framework.cs

āļŦāļĢāļ·āļ­āđƒāļŠāđ‰ dotnet CLI:

dotnet run ./03-dotnet-agent-framework.cs

āļ”āļđ 03-dotnet-agent-framework.cs āļŠāļģāļŦāļĢāļąāļšāđ‚āļ„āđ‰āļ”āļ—āļąāđ‰āļ‡āļŦāļĄāļ”

#!/usr/bin/dotnet run

#:package Microsoft.Extensions.AI@10.*
#:package Microsoft.Agents.AI.OpenAI@1.*-*
#:package Azure.AI.OpenAI@2.1.0
#:package Azure.Identity@1.13.1

using System.ComponentModel;

using Microsoft.Agents.AI;
using Microsoft.Extensions.AI;

using Azure.AI.OpenAI;
using Azure.Identity;

// Tool Function: Random Destination Generator
// This static method will be available to the agent as a callable tool
// The [Description] attribute helps the AI understand when to use this function
// This demonstrates how to create custom tools for AI agents
[Description("Provides a random vacation destination.")]
static string GetRandomDestination()
{
    // List of popular vacation destinations around the world
    // The agent will randomly select from these options
    var destinations = new List<string>
    {
        "Paris, France",
        "Tokyo, Japan",
        "New York City, USA",
        "Sydney, Australia",
        "Rome, Italy",
        "Barcelona, Spain",
        "Cape Town, South Africa",
        "Rio de Janeiro, Brazil",
        "Bangkok, Thailand",
        "Vancouver, Canada"
    };

    // Generate random index and return selected destination
    // Uses System.Random for simple random selection
    var random = new Random();
    int index = random.Next(destinations.Count);
    return destinations[index];
}

// Azure OpenAI with the Responses API (stable v1 endpoint). Sign in with `az login`.
var azureEndpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT")
    ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
var deployment = Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT") ?? "gpt-5-mini";

var azureClient = new AzureOpenAIClient(new Uri(azureEndpoint), new AzureCliCredential());

// Define Agent Identity and Comprehensive Instructions
// Agent name for identification and logging purposes
var AGENT_NAME = "TravelAgent";

// Detailed instructions that define the agent's personality, capabilities, and behavior
// This system prompt shapes how the agent responds and interacts with users
var AGENT_INSTRUCTIONS = """
You are a helpful AI Agent that can help plan vacations for customers.

Important: When users specify a destination, always plan for that location. Only suggest random destinations when the user hasn't specified a preference.

When the conversation begins, introduce yourself with this message:
"Hello! I'm your TravelAgent assistant. I can help plan vacations and suggest interesting destinations for you. Here are some things you can ask me:
1. Plan a day trip to a specific location
2. Suggest a random vacation destination
3. Find destinations with specific features (beaches, mountains, historical sites, etc.)
4. Plan an alternative trip if you don't like my first suggestion

What kind of trip would you like me to help you plan today?"

Always prioritize user preferences. If they mention a specific destination like "Bali" or "Paris," focus your planning on that location rather than suggesting alternatives.
""";

// Create AI Agent with Advanced Travel Planning Capabilities
// Get the Responses client for the deployment and create the AI agent
// Configure agent with name, detailed instructions, and available tools
// This demonstrates the .NET agent creation pattern with full configuration
AIAgent agent = azureClient
    .GetChatClient(deployment)
    .AsAIAgent(
        name: AGENT_NAME,
        instructions: AGENT_INSTRUCTIONS,
        tools: [AIFunctionFactory.Create(GetRandomDestination)]
    );

// Create New Conversation Session for Context Management
// Initialize a new conversation session to maintain context across multiple interactions
// Sessions enable the agent to remember previous exchanges and maintain conversational state
// This is essential for multi-turn conversations and contextual understanding
var session = await agent.CreateSessionAsync();

// Execute Agent: First Travel Planning Request
// Run the agent with an initial request that will likely trigger the random destination tool
// The agent will analyze the request, use the GetRandomDestination tool, and create an itinerary
// Using the session parameter maintains conversation context for subsequent interactions
await foreach (var update in agent.RunStreamingAsync("Plan me a day trip", session))
{
    await Task.Delay(10);
    Console.Write(update);
}

Console.WriteLine();

// Execute Agent: Follow-up Request with Context Awareness
// Demonstrate contextual conversation by referencing the previous response
// The agent remembers the previous destination suggestion and will provide an alternative
// This showcases the power of conversation sessions and contextual understanding in .NET agents
await foreach (var update in agent.RunStreamingAsync("I don't like that destination. Plan me another vacation.", session))
{
    await Task.Delay(10);
    Console.Write(update);
}

āļ›āļāļīāđ€āļŠāļ˜āļ„āļ§āļēāļĄāļĢāļąāļšāļœāļīāļ”āļŠāļ­āļš: āđ€āļ­āļāļŠāļēāļĢāļ™āļĩāđ‰āđ„āļ”āđ‰āļĢāļąāļšāļāļēāļĢāđāļ›āļĨāđ‚āļ”āļĒāđƒāļŠāđ‰āļšāļĢāļīāļāļēāļĢāđāļ›āļĨāļ āļēāļĐāļē AI Co-op Translator āļ‚āļ“āļ°āļ—āļĩāđˆāđ€āļĢāļēāļžāļĒāļēāļĒāļēāļĄāđƒāļŦāđ‰āļ„āļ§āļēāļĄāļ–āļđāļāļ•āđ‰āļ­āļ‡ āđ‚āļ›āļĢāļ”āļ—āļĢāļēāļšāļ§āđˆāļēāļāļēāļĢāđāļ›āļĨāđ‚āļ”āļĒāļ­āļąāļ•āđ‚āļ™āļĄāļąāļ•āļīāļ­āļēāļˆāļĄāļĩāļ‚āđ‰āļ­āļœāļīāļ”āļžāļĨāļēāļ”āļŦāļĢāļ·āļ­āļ„āļ§āļēāļĄāđ„āļĄāđˆāļ–āļđāļāļ•āđ‰āļ­āļ‡ āđ€āļ­āļāļŠāļēāļĢāļ•āđ‰āļ™āļ‰āļšāļąāļšāđƒāļ™āļ āļēāļĐāļēāļ•āđ‰āļ™āļ—āļēāļ‡āļ„āļ§āļĢāļ–āļđāļāļžāļīāļˆāļēāļĢāļ“āļēāđ€āļ›āđ‡āļ™āđāļŦāļĨāđˆāļ‡āļ‚āđ‰āļ­āļĄāļđāļĨāļ—āļĩāđˆāđ€āļŠāļ·āđˆāļ­āļ–āļ·āļ­āđ„āļ”āđ‰ āļŠāļģāļŦāļĢāļąāļšāļ‚āđ‰āļ­āļĄāļđāļĨāļ—āļĩāđˆāļŠāļģāļ„āļąāļ āđāļ™āļ°āļ™āļģāđƒāļŦāđ‰āđƒāļŠāđ‰āļāļēāļĢāđāļ›āļĨāđ‚āļ”āļĒāļĄāļ™āļļāļĐāļĒāđŒāļĄāļ·āļ­āļ­āļēāļŠāļĩāļž āđ€āļĢāļēāđ„āļĄāđˆāļĢāļąāļšāļœāļīāļ”āļŠāļ­āļšāļ•āđˆāļ­āļ„āļ§āļēāļĄāđ€āļ‚āđ‰āļēāđƒāļˆāļœāļīāļ”āļŦāļĢāļ·āļ­āļāļēāļĢāļ•āļĩāļ„āļ§āļēāļĄāļ—āļĩāđˆāļœāļīāļ”āļžāļĨāļēāļ”āļ—āļĩāđˆāđ€āļāļīāļ”āļ‚āļķāđ‰āļ™āļˆāļēāļāļāļēāļĢāđƒāļŠāđ‰āļāļēāļĢāđāļ›āļĨāļ™āļĩāđ‰