chore: import upstream snapshot with attribution

dotnet/samples/02-agents/Evaluation/Evaluation_ExpectedOutputs/Evaluation_ExpectedOutputs.csproj

@@ -0,0 +1,15 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFrameworks>net10.0</TargetFrameworks>
+
+    <Nullable>enable</Nullable>
+    <ImplicitUsings>enable</ImplicitUsings>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.Foundry\Microsoft.Agents.AI.Foundry.csproj" />
+  </ItemGroup>
+
+</Project>

dotnet/samples/02-agents/Evaluation/Evaluation_ExpectedOutputs/Program.cs

@@ -0,0 +1,54 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+// This sample demonstrates evaluating agent responses against expected outputs.
+
+using Azure.AI.Projects;
+using Azure.Identity;
+using Microsoft.Agents.AI;
+
+string endpoint = Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT") ?? throw new InvalidOperationException("FOUNDRY_PROJECT_ENDPOINT is not set.");
+string deploymentName = Environment.GetEnvironmentVariable("FOUNDRY_MODEL") ?? "gpt-4o-mini";
+
+// Create a math tutor agent.
+// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
+// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
+// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
+AIAgent agent = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential())
+    .AsAIAgent(
+        model: deploymentName,
+        instructions: "You are a math tutor. Answer concisely with the numeric result.",
+        name: "MathTutor");
+
+// Combine built-in checks.
+LocalEvaluator localEvaluator = new(
+    EvalChecks.ContainsExpected(),   // response must contain the expected answer
+    EvalChecks.NonEmpty());          // response must not be empty
+
+// Queries and expected outputs.
+string[] queries = ["What is 2 + 2?", "What is the square root of 144?"];
+string[] expectedOutputs = ["4", "12"];
+
+// Run the agent and evaluate with expected outputs.
+AgentEvaluationResults results = await agent.EvaluateAsync(
+    queries,
+    localEvaluator,
+    expectedOutput: expectedOutputs);
+
+// Print results.
+Console.WriteLine($"Evaluation: {results.ProviderName}");
+Console.WriteLine($"  Passed: {results.Passed}/{results.Total}");
+Console.WriteLine($"  All passed: {results.AllPassed}");
+Console.WriteLine();
+
+for (int i = 0; i < results.Items.Count; i++)
+{
+    Console.WriteLine($"Query: {queries[i]}  |  Expected: {expectedOutputs[i]}");
+    Console.WriteLine($"Response: {(results.InputItems?[i].Response is { } resp ? resp.Substring(0, Math.Min(50, resp.Length)) : "N/A")}");
+    foreach (var metric in results.Items[i].Metrics)
+    {
+        string status = metric.Value.Interpretation?.Failed == true ? "FAIL" : "PASS";
+        Console.WriteLine($"  [{status}] {metric.Key}: {metric.Value.Interpretation?.Reason}");
+    }
+
+    Console.WriteLine();
+}

dotnet/samples/02-agents/Evaluation/Evaluation_ExpectedOutputs/README.md

@@ -0,0 +1,34 @@
+# Evaluation - Expected Outputs
+
+This sample demonstrates evaluating agent responses against expected outputs using built-in checks.
+
+## What this sample demonstrates
+
+- Using `EvalChecks.ContainsExpected` for ground-truth comparison
+- Using `EvalChecks.NonEmpty` for basic response validation
+- Passing `expectedOutput` to `agent.EvaluateAsync()` so checks can access ground truth
+
+## Prerequisites
+
+- .NET 10 SDK or later
+- Azure CLI installed and authenticated (`az login`)
+
+Set the following environment variables:
+
+```powershell
+$env:FOUNDRY_PROJECT_ENDPOINT="https://your-foundry-service.services.ai.azure.com/api/projects/your-foundry-project"
+$env:FOUNDRY_MODEL="gpt-4o-mini"
+```
+
+## Run the sample
+
+```powershell
+cd dotnet/samples/02-agents/Evaluation
+dotnet run --project .\Evaluation_ExpectedOutputs
+```
+
+## See also
+
+- [Evaluation_SimpleEval](../Evaluation_SimpleEval/) — Simplest evaluation with built-in and custom checks
+- [Evaluation_FoundryQuality](../../../05-end-to-end/Evaluation/Evaluation_FoundryQuality/) — Cloud-based quality evaluation with Foundry evaluators
+- [Evaluation_FoundryRubric](../../../05-end-to-end/Evaluation/Evaluation_FoundryRubric/) — Rubric (adaptive) evaluators with per-dimension scores