Training course · AI Agent Development · C# & .NET

AI Agent Development for C# and .NET Developers

Build AI agents professionally: architectures, tool use, agent SDKs, LangGraph, memory, evals, guardrails and deployment.

Duration
2 days (14 hrs)
Format
Online or on-site
Language
German or English
Participants
open dates or exclusive for your team
Certificate
Certificate of attendance

Overview

“AI Agent Development for C# and .NET Developers” is a hands-on course for roles such as C# developers working with ASP.NET Core, Blazor or WPF, Teams migrating applications from .NET Framework to modern .NET and Software architects for .NET and Azure solutions. Rather than learning AI Agent Development in the abstract, you work on tasks from your daily routine – with examples, exercises and templates from C# & .NET.

AI agents go beyond conventional chatbots: they break tasks down, call tools and APIs, evaluate the results and keep iterating until a goal is met. In this two-day course you learn to build such systems so that they work reliably, transparently and safely in day-to-day business. You compare architectural patterns ranging from simple workflows through the agent loop to multi-agent systems, and you implement them hands-on with the Claude Agent SDK, the OpenAI Agents SDK and LangGraph.

The focus is not on a quick demo but on the path to production. You design tool interfaces and context deliberately, connect tools via the Model Context Protocol, plan short-term and long-term memory and build evaluations that surface regressions early. On top of that come guardrails against prompt injection and harmful actions, human-in-the-loop approvals, tracing, cost control and deployment. By the end you can judge when an agent is worthwhile, when a deterministic workflow is enough and which framework fits your project.

C# and .NET are firmly established in many organisations: ASP.NET Core APIs, Blazor and WPF front ends, Azure services and line-of-business applications dating back to the .NET Framework era. Migrating from the classic .NET Framework to modern cross-platform .NET in particular ties up significant capacity. AI coding assistants and agents take over much of the mechanical work here: converting project files to SDK style, identifying WCF or Web Forms dependencies, writing xUnit or NUnit tests, optimising Entity Framework Core queries and introducing nullable reference types. To do this well, they need context on solution structure, analyser rules and architectural guidelines. This course shows you how to use agents in Visual Studio, VS Code or Rider and on the command line.

The course is delivered live – either online in a virtual classroom or on-site in our training rooms in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart and Kaiserslautern. We can also run it exclusively for your team.

Who is this course for?

  • C# developers working with ASP.NET Core, Blazor or WPF
  • Teams migrating applications from .NET Framework to modern .NET
  • Software architects for .NET and Azure solutions
  • Developers of line-of-business applications in industry and SMEs

Typical challenges we address

  • Costly migration of .NET Framework applications built on WCF, Web Forms or ageing NuGet packages
  • Large solutions with many projects, circular dependencies and little test coverage
  • Performance issues caused by inefficient Entity Framework queries
  • Inconsistent handling of nullability, async/await and dependency injection

What you will be able to do

  • You choose the right pattern for a task, from a fixed workflow to an autonomous agent.
  • You design tools and context so that agents work reliably and cost-effectively.
  • You implement agents with the Claude Agent SDK, the OpenAI Agents SDK or LangGraph.
  • You set up evaluations and tracing to measure quality and detect regressions.
  • Use AI agents for .NET migrations, refactorings and test generation across large solutions.
  • Optimise Entity Framework Core data access and ASP.NET Core APIs with AI support.
  • Define analyser rules, conventions and review criteria that generated C# code meets reliably.

Course outline

Day 1

Module 1 Agent architectures and design patterns
  • Workflows versus agents: prompt chaining, routing, parallelisation, orchestrator-worker
  • The agent loop: plan, act, observe, reflect
  • Multi-agent systems, subagents and handoffs between agents
  • Criteria for choosing model, framework and level of autonomy
Module 2 Tool use and context engineering
  • Function calling and structured outputs with JSON Schema
  • Designing good tools: granularity, naming, error messages, idempotency
  • Connecting and reusing tools via MCP servers
  • Managing the context window: summarisation, compaction, retrieval and prompt caching
Module 3 Frameworks in practice
  • Claude Agent SDK: agent loop, tools, subagents, permissions and hooks
  • OpenAI Agents SDK: agents, handoffs, guardrails and tracing
  • LangGraph: stateful graphs, checkpointing and human-in-the-loop
  • Side-by-side comparison on the same task and criteria for choosing a framework
Module 4 Memory, evals and observability
  • Short-term and long-term memory, storage strategies and forgetting
  • Evaluation datasets, LLM-as-a-judge and task-based success metrics
  • Tracing tool calls, token usage and latency
  • Regression testing when prompts, models or tools change

Day 2

Module 5 Guardrails, security and deployment
  • Protecting against prompt injection, data exfiltration and over-privileged tools
  • Input and output checks, approval steps and sandboxing
  • Deploying as a service, asynchronous execution, retries and cost limits
  • Governance, audit logging and requirements under GDPR and the EU AI Act
Module 6 Practice lab: C# & .NET
  • Migrating to modern .NET
  • Writing xUnit and NUnit tests
  • Optimising Entity Framework Core
  • Introducing nullable reference types
  • Building ASP.NET Core APIs
  • Code analysis and refactoring
Module 7 Data protection, quality & transfer to daily work
  • Clarify whether source code may be sent to cloud models and which tenant or region settings apply, and keep connection strings and secrets from User Secrets or Key Vault out of prompts. New NuGet packages should be checked for licence, provenance and vulnerabilities – not least in view of the obligations under the Cyber Resilience Act.
  • Ground rules for safe AI use in your team
  • Checking results: facts, sources, tests and the four-eyes principle
  • Personal action plan for the next 30 days
  • Open questions, outlook and resources for further learning

Practical scenarios from your field

Migrating to modern .NET

The agent analyses projects using the upgrade tooling and compiler output, converts csproj files to SDK style, replaces incompatible APIs and proposes alternatives to WCF or System.Web until the solution builds and tests pass.

Writing xUnit and NUnit tests

Services, controllers and domain logic get unit tests with Moq or NSubstitute plus integration tests using WebApplicationFactory. The AI covers edge cases and sticks to your existing test conventions.

Optimising Entity Framework Core

The AI analyses generated SQL, spots N+1 problems, missing AsNoTracking calls or awkward Includes, and creates migrations and projections for faster queries. Every change is backed by the resulting SQL.

Introducing nullable reference types

Nullable is enabled project by project while the AI works through compiler warnings, adds guard clauses and annotations and makes implicit assumptions in the code explicit.

Building ASP.NET Core APIs

Specifications become minimal APIs or controllers with validation, ProblemDetails error handling, authentication and OpenAPI documentation, consistent with your existing layered architecture. Integration tests safeguard each new endpoint.

Code analysis and refactoring

Roslyn analyser findings are fixed systematically, oversized classes split, async anti-patterns such as .Result removed and dependency injection registrations made consistent. Build, analysers and existing tests confirm that behaviour is unchanged.

Possible hands-on projects

Minimal API service

An ASP.NET Core service using minimal APIs, EF Core, health checks, structured logging and integration tests, built end to end by an AI agent from a specification.

Migration inventory

A console tool that scans a solution, lists target frameworks, NuGet packages and incompatible APIs, and produces a prioritised migration plan.

Blazor admin UI

A small Blazor application for managing master data, with form validation, filterable tables and integration with an existing REST API.

Prerequisites

Solid programming skills in Python or TypeScript, experience with REST APIs and some hands-on experience with LLM APIs or AI assistants. Good C# skills, experience with ASP.NET Core or .NET desktop development, and familiarity with Visual Studio, Rider or VS Code and Git.

Technical requirements

A laptop with Python or Node.js, Git and a code editor, plus API access to at least one LLM provider such as Anthropic or OpenAI. Credentials for the exercises can be provided if needed.

Data protection & compliance

Clarify whether source code may be sent to cloud models and which tenant or region settings apply, and keep connection strings and secrets from User Secrets or Key Vault out of prompts. New NuGet packages should be checked for licence, provenance and vulnerabilities – not least in view of the obligations under the Cyber Resilience Act.

Suggested dates

All dates are suggestions – your preferred date is always possible.

  • Mon, 23 November 2026 – Tue, 24 November 2026 Online Request
  • Mon, 30 November 2026 – Tue, 1 December 2026 Kaiserslautern Request
  • Wed, 9 December 2026 – Thu, 10 December 2026 Online Request
  • Mon, 11 January 2027 – Tue, 12 January 2027 Augsburg Request
  • Thu, 21 January 2027 – Fri, 22 January 2027 Online Request
  • Tue, 26 January 2027 – Wed, 27 January 2027 Salzburg Request

Frequently asked questions

Which agent framework should we use?

It depends on your model strategy, the level of control you need and your team’s skills. Vendor SDKs offer a lean start with tightly integrated features, while LangGraph gives you finer control over state and flow. In the course you solve the same task with several frameworks and derive clear selection criteria for your own project.

How do you stop an agent from taking wrong or dangerous actions?

With several layers of protection: narrowly scoped tools with minimal permissions, input and output validation, approval steps for critical actions, sandboxing and continuous evaluation. Prompt injection via external content is treated as a realistic threat. You practise these measures directly on your own agent.

Does every automation need an agent?

No. Many tasks are handled more reliably, cheaply and transparently by a fixed workflow of a few LLM calls. Agents pay off when the solution path cannot be planned in advance and the system must react flexibly to intermediate results. We train exactly this trade-off using practical examples.

Does AI really help with migrating from .NET Framework?

Yes, especially with the mechanical work: converting project files, finding incompatible APIs, suggesting replacement libraries and fixing build errors iteratively. Fundamental architecture decisions, such as replacing WCF with gRPC or REST, remain with the team. On the course you practise breaking such migrations into small, verifiable steps.

Do AI agents work with Visual Studio?

Many AI assistants integrate directly with Visual Studio, VS Code or Rider, while others run in the terminal alongside the dotnet CLI. The methods taught are tool-neutral: you learn to provide context, scope tasks and safeguard results through builds, analysers and tests, regardless of your IDE.

How much does “AI Agent Development for C# and .NET Developers” cost?

The course costs a flat €949 plus VAT per participant – whether online or on-site. This includes 2 training day(s) with a live trainer, course materials, a lab environment and a certificate of attendance.

Can I suggest my own date?

Yes. Our suggested dates are just a guide. In the request form you can always describe your preferred date or period in free text – we check availability and confirm within one working day.

Is the course online or on-site?

Both are possible: live online in a virtual classroom or on-site in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart or Kaiserslautern. We can also run the course exclusively for your team.

More courses for C# and .NET Developers

More AI Agent Development courses

All 30 AI Agent Development courses

AI Agent Development · MunichAI Agent Development · SalzburgAI Agent Development · BerlinAI Agent Development · AugsburgAI Agent Development · HanoverAI Agent Development · BremenAI Agent Development · StuttgartAI Agent Development · KaiserslauternAI Agent Development · Online