Tutorials

These hands-on tutorials guide you through customizing and extending the Interview Coach application. Work through them sequentially to build understanding.

Prerequisites

Before starting:

Complete the Getting Started setup
Get the app running locally
Skim the architecture overview
Basic familiarity with C# and .NET

Tutorial 1: Understanding the Interview Flow

Goal: Trace how the interview process works from user input to agent response.

Duration: 20 minutes

Step 1: Read the Agent Instructions

Open src/InterviewCoach.Agent/AgentDelegateFactory.cs and find the CreateSingleAgent method:

instructions: """
    You are an AI Interview Coach designed to help users prepare for job interviews.
    ...
    Here's the overall process you should follow:
    01. Start by fetching an existing interview session...
    02. If there's no existing session, create a new interview session...
    ...
    """

Exercise: Identify the key steps in the interview process. Notice:

Session management comes first
Resume/JD collection is optional
Behavioral questions before technical
User can stop at any time

Step 2: Trace Tool Usage

The agent is configured with tools from two MCP servers:

var markitdownTools = markitdown.ListToolsAsync().GetAwaiter().GetResult();
var interviewDataTools = interviewData.ListToolsAsync().GetAwaiter().GetResult();

var agent = CreateProviderAgent(
    services: sp,
    name: key,
    description: "Runs the complete interview coaching process.",
    instructions: """ ... """,
    tools: [ .. markitdownTools, .. interviewDataTools ]
);

Exercise:

Start the application
Open Aspire Dashboard (the URL appears in terminal)
Navigate to Agent logs
Start an interview conversation
Watch the logs to see when tools are called

You should see entries like:

info: Calling tool: add_interview_session
info: Tool response: {"id": "..."}

Step 3: Examine Session State

The agent maintains state through the InterviewData MCP server:

Open src/InterviewCoach.Mcp.InterviewData/InterviewSessionTool.cs
Find the UpdateInterviewSessionAsync method
See how it stores resume, job description, and transcript

Exercise:

Complete a short interview
Check the database using the Cosmos DB emulator's Data Explorer
Find your session record
Examine the stored transcript JSON

Step 4: Modify the Interview Flow

Let's add a warmup message before behavioral questions.

Edit src/InterviewCoach.Agent/AgentDelegateFactory.cs:

Find this line:

07. Once you have updated the session record with the information, begin the interview by asking behavioral questions first.

Change to:

07. Once you have updated the session record with the information, first provide a brief warmup message encouraging the user, then begin the interview by asking behavioral questions first.

Test:

Restart the application
Start a new interview
Notice the warmup message before questions begin

Reflection: How does changing instructions affect agent behavior without code changes?

Tutorial 2: Creating a Custom MCP Server

Goal: Build a simple MCP server that provides interview tips.

Duration: 45 minutes

Step 1: Create New Project

cd src
dotnet new web -n InterviewCoach.Mcp.Tips
cd InterviewCoach.Mcp.Tips
dotnet add package ModelContextProtocol.Server
dotnet add package Microsoft.Extensions.Hosting

Step 2: Create a Simple Tool

Create InterviewTipsTool.cs:

using System.ComponentModel;
using ModelContextProtocol.Server;

[McpServerToolType]
public class InterviewTipsTool
{
    private static readonly Dictionary<string, string> Tips = new()
    {
        ["behavioral"] = "Use the STAR method: Situation, Task, Action, Result",
        ["technical"] = "Think out loud. Explain your reasoning as you solve problems",
        ["general"] = "Prepare questions for the interviewer. Show genuine interest"
    };

    [McpServerTool(Name = "get_interview_tip", Title = "Get an interview tip")]
    [Description("Get a helpful interview tip by category (behavioral, technical, or general).")]
    public string GetInterviewTip(
        [Description("Tip category: behavioral, technical, or general")] string category
    )
    {
        return Tips.GetValueOrDefault(category, Tips["general"]);
    }
}

Step 3: Setup Program.cs

using System.Reflection;

var builder = WebApplication.CreateBuilder(args);

builder.Services.AddMcpServer()
                .WithHttpTransport(o => o.Stateless = true)
                .WithToolsFromAssembly(Assembly.GetEntryAssembly());

var app = builder.Build();

app.MapMcp("/mcp");

await app.RunAsync();

Step 4: Register in AppHost

Add the new project to the file-based AppHost directives at the top of apphost.cs:

#:project ./src/InterviewCoach.Mcp.Tips/InterviewCoach.Mcp.Tips.csproj

Then register the project in apphost.cs:

Add after other MCP servers:

var mcpTips = builder.AddProject<Projects.InterviewCoach_Mcp_Tips>("mcp-tips")
                     .WithExternalHttpEndpoints();

Update agent reference:

var agent = builder.AddProject<Projects.InterviewCoach_Agent>(ResourceConstants.Agent)
                   .WithExternalHttpEndpoints()
                   .WithLlmReference(config, args)
                   .WithReference(mcpMarkItDown.GetEndpoint("http"))
                   .WithReference(mcpInterviewData)
                   .WithReference(mcpTips)  // Add this line
                   .WaitFor(mcpMarkItDown)
                   .WaitFor(mcpInterviewData)
                   .WaitFor(mcpTips);  // Add this line

Step 5: Connect from Agent

Edit src/InterviewCoach.Agent/Program.cs:

Add HTTP client:

builder.Services.AddHttpClient("mcp-tips", client =>
{
    client.BaseAddress = new Uri("https+http://mcp-tips");
});

Add MCP client:

builder.Services.AddKeyedSingleton<McpClient>("mcp-tips", (sp, obj) =>
{
    var loggerFactory = sp.GetRequiredService<ILoggerFactory>();
    var httpClient = sp.GetRequiredService<IHttpClientFactory>().CreateClient("mcp-tips");
    
    var clientTransportOptions = new HttpClientTransportOptions()
    {
        Endpoint = new Uri($"{httpClient.BaseAddress!.ToString().Replace("+http", string.Empty).TrimEnd('/')}/mcp")
    };
    var clientTransport = new HttpClientTransport(clientTransportOptions, httpClient, loggerFactory);
    
    var clientOptions = new McpClientOptions()
    {
        ClientInfo = new Implementation()
        {
            Name = "MCP Tips Client",
            Version = "1.0.0",
        }
    };
    
    return McpClient.CreateAsync(clientTransport, clientOptions, loggerFactory).GetAwaiter().GetResult();
});

var markitdown = sp.GetRequiredKeyedService<McpClient>("mcp-markitdown");
var interviewData = sp.GetRequiredKeyedService<McpClient>("mcp-interview-data");
var tips = sp.GetRequiredKeyedService<McpClient>("mcp-tips");  // Add this

var markitdownTools = markitdown.ListToolsAsync().GetAwaiter().GetResult();
var interviewDataTools = interviewData.ListToolsAsync().GetAwaiter().GetResult();
var tipsTools = tips.ListToolsAsync().GetAwaiter().GetResult();  // Add this

var agent = CreateProviderAgent(
    services: sp,
    name: key,
    description: "Runs the complete interview coaching process.",
    instructions: """ ... """,
    tools: [ .. markitdownTools, .. interviewDataTools, .. tipsTools ]  // Add tipsTools
);

Step 6: Update Agent Instructions

Add to the agent instructions:

instructions: """
    You are an AI Interview Coach...
    ...
    Use the provided tools to manage interview sessions, capture resume and job description, 
    ask questions, analyze responses, provide interview tips when appropriate, and generate summaries.
    ...
    """

Step 7: Test

Restart the application
During an interview, ask: "Can you give me a tip for behavioral questions?"
The agent should call get_interview_tip with category "behavioral"

Challenge: Add more tips to the dictionary and enhance the tool to return multiple tips.

Tutorial 3: Customizing the Agent

Goal: Modify agent behavior to focus on a specific job type.

Duration: 30 minutes

Scenario: Technical Interview for Backend Developers

Step 1: Update Agent Instructions

Edit src/InterviewCoach.Agent/AgentDelegateFactory.cs:

Find the CreateSingleAgent method and change the opening:

instructions: """
    You are an AI Interview Coach specializing in backend software engineering positions.
    You will guide users through technical interview preparation with a focus on:
    - System design and architecture
    - API design and REST principles
    - Database modeling and optimization
    - Microservices and distributed systems
    - Algorithm and data structure fundamentals
    
    ...
    """

Step 2: Modify Question Types

Change the question flow in AgentDelegateFactory.cs:

07. Once you have updated the session record with the information, begin the interview with 
    system design questions first (2-3 questions).
08. After system design, move to algorithm and data structures questions (2-3 questions).
09. Finally, ask about specific backend technologies mentioned in the job description.
10. Before switching categories, ask the user if they want to continue to the next section.

Step 3: Add Domain Expertise

Include specific context:

When asking system design questions, focus on:
- Scalability patterns (load balancing, caching, sharding)
- Data consistency models (CAP theorem, eventual consistency)
- API versioning strategies
- Authentication/authorization patterns

When asking algorithm questions:
- Start with problem clarification
- Encourage the user to explain their approach
- Ask about time and space complexity
- Discuss optimization opportunities

Step 4: Test

Restart the application
Start an interview with a backend job description
Notice the changed question types and focus

Extension: Create different agent profiles for frontend, data science, or DevOps roles.

Tutorial 4: Extending the handoff workflow

Goal: Add another specialist to the existing multi-agent workflow.

Duration: 30 minutes

The application already implements a handoff workflow in CreateHandOffWorkflow. It uses Triage as the entry point, then moves through Receptionist, Behavioural Interviewer, Technical Interviewer, and Summariser.

Step 1: Create the specialist

Add a role-specific agent in CreateHandOffWorkflow:

var systemDesignAgent = CreateProviderAgent(
    services: sp,
    name: "system_design_interviewer",
    description: "Conducts a system design interview and provides feedback.",
    instructions: """
        You are the System Design Interviewer.
        Ask one architecture question at a time.
        Discuss requirements, trade-offs, reliability, and scalability.
        Store each question, answer, and assessment in the interview session.
        When this phase is complete, hand off to "summariser".
        """,
    tools: [.. interviewDataTools]);

Using CreateProviderAgent keeps the specialist compatible with both Microsoft Foundry and GitHub Copilot.

Step 2: Update routing instructions

Add the new phase to the Triage sequence and tell the Technical Interviewer to hand off to system_design_interviewer instead of directly to summariser.

Step 3: Connect the handoffs

Add the agent to the workflow graph:

var workflow = AgentWorkflowBuilder
    .CreateHandoffBuilderWith(triageAgent)
    .WithHandoffs(triageAgent,
        [receptionistAgent, behaviouralAgent, technicalAgent, systemDesignAgent, summariserAgent])
    .WithHandoffs(receptionistAgent, [behaviouralAgent, triageAgent])
    .WithHandoffs(behaviouralAgent, [technicalAgent, triageAgent])
    .WithHandoffs(technicalAgent, [systemDesignAgent, triageAgent])
    .WithHandoffs(systemDesignAgent, [summariserAgent, triageAgent])
    .WithHandoff(summariserAgent, triageAgent)
    .Build();

Step 4: Test both providers

Run the workflow with Microsoft Foundry, then GitHub Copilot:

aspire start --apphost ./apphost.cs -- --provider MicrosoftFoundry --mode HandOff
aspire start --apphost ./apphost.cs -- --provider GitHubCopilot --mode HandOff

Confirm that Triage can select the new agent and that the normal sequence reaches it after the technical interview.

See Microsoft Agent Framework handoff orchestration for the underlying workflow API.

Tutorial 5: Adding Evaluation and Feedback

Goal: Enhance the agent to provide structured feedback scoring.

Duration: 30 minutes

Step 1: Create Evaluation Schema

Create src/InterviewCoach.Mcp.InterviewData/Models/Evaluation.cs:

public class InterviewEvaluation
{
    public string SessionId { get; set; } = string.Empty;
    public int CommunicationScore { get; set; }  // 1-10
    public int TechnicalScore { get; set; }      // 1-10
    public int ProblemSolvingScore { get; set; } // 1-10
    public List<string> Strengths { get; set; } = new();
    public List<string> AreasForImprovement { get; set; } = new();
    public string OverallRecommendation { get; set; } = string.Empty;
}

Step 2: Add Evaluation Tool to MCP Server

using System.ComponentModel;
using ModelContextProtocol.Server;

[McpServerToolType]
public class EvaluationTool(IInterviewSessionRepository repository)
{
    [McpServerTool(Name = "save_interview_evaluation", Title = "Save interview evaluation")]
    [Description("Save structured evaluation scores and feedback for an interview session.")]
    public async Task<InterviewEvaluation> SaveEvaluationAsync(
        [Description("The evaluation data")] InterviewEvaluation evaluation
    )
    {
        await repository.SaveEvaluationAsync(evaluation);
        return evaluation;
    }
}

Step 3: Update Agent Instructions

11. After the interview is complete, generate a comprehensive evaluation including:
    - Communication score (1-10)
    - Technical score (1-10)
    - Problem-solving score (1-10)
    - List of strengths (3-5 items)
    - Areas for improvement (3-5 items)
    - Overall hiring recommendation
12. Save the evaluation using the save_interview_evaluation tool.
13. Present the evaluation to the user in a friendly, encouraging format.

Next Steps

After these tutorials you should be able to:

Change agent behavior by editing instructions
Build a custom MCP server with tools
Understand multi-agent handoff patterns
Add structured evaluation logic

More things to try

Voice input — integrate speech-to-text for realistic practice
Timer — add an MCP tool to track time per question
Question bank — MCP server with curated questions by role/level
Video analysis — MCP server for facial expression feedback (advanced)
Session comparison — diff multiple interview sessions

Resources

Microsoft Agent Framework

If you build something interesting on top of this, open a PR or start a discussion on GitHub.

Navigation Menu

Uh oh!

Tutorials

Prerequisites

Tutorial 1: Understanding the Interview Flow

Step 1: Read the Agent Instructions

Step 2: Trace Tool Usage

Step 3: Examine Session State

Step 4: Modify the Interview Flow

Tutorial 2: Creating a Custom MCP Server

Step 1: Create New Project

Step 2: Create a Simple Tool

Step 3: Setup Program.cs

Step 4: Register in AppHost

Step 5: Connect from Agent

Step 6: Update Agent Instructions

Step 7: Test

Tutorial 3: Customizing the Agent

Scenario: Technical Interview for Backend Developers

Step 1: Update Agent Instructions

Step 2: Modify Question Types

Step 3: Add Domain Expertise

Step 4: Test

Tutorial 4: Extending the handoff workflow

Step 1: Create the specialist

Step 2: Update routing instructions

Step 3: Connect the handoffs

Step 4: Test both providers

Tutorial 5: Adding Evaluation and Feedback

Step 1: Create Evaluation Schema

Step 2: Add Evaluation Tool to MCP Server

Step 3: Update Agent Instructions

Next Steps

More things to try

Resources

Uh oh!

FilesExpand file tree

TUTORIALS.md

Latest commit

History

TUTORIALS.md

File metadata and controls

Tutorials

Prerequisites

Tutorial 1: Understanding the Interview Flow

Step 1: Read the Agent Instructions

Step 2: Trace Tool Usage

Step 3: Examine Session State

Step 4: Modify the Interview Flow

Tutorial 2: Creating a Custom MCP Server

Step 1: Create New Project

Step 2: Create a Simple Tool

Step 3: Setup Program.cs

Step 4: Register in AppHost

Step 5: Connect from Agent

Step 6: Update Agent Instructions

Step 7: Test

Tutorial 3: Customizing the Agent

Scenario: Technical Interview for Backend Developers

Step 1: Update Agent Instructions

Step 2: Modify Question Types

Step 3: Add Domain Expertise

Step 4: Test

Tutorial 4: Extending the handoff workflow

Step 1: Create the specialist

Step 2: Update routing instructions

Step 3: Connect the handoffs

Step 4: Test both providers

Tutorial 5: Adding Evaluation and Feedback

Step 1: Create Evaluation Schema

Step 2: Add Evaluation Tool to MCP Server

Step 3: Update Agent Instructions

Next Steps

More things to try

Resources