Introduction to AI Engineering
Why it matters if you work with C# and .NET: The complete frame: LLMs, APIs, RAG, agents, evaluation and security, so you make informed decisions before installing the first package.
.NET has lined up behind AI: an official OpenAI library for .NET, an official Anthropic SDK for C#, Microsoft.Extensions.AI as a common abstraction, Semantic Kernel for orchestration and an official C# SDK for the Model Context Protocol. For a C# developer the tools are not the problem. None of the courses here is written in C#: their examples are mostly Python. They are on this page because they teach how a language model behaves in production, which is the part the NuGet packages do not give you.
In the order in which they matter, each with the reason it matters if you work with C# and .NET. Untick what you already know: the subscription and the price update.
What a model can and cannot do, how you talk to it and how a production integration is built. Language-independent, with the examples mostly in Python.
Why it matters if you work with C# and .NET: The complete frame: LLMs, APIs, RAG, agents, evaluation and security, so you make informed decisions before installing the first package.
Why it matters if you work with C# and .NET: Prompt engineering for code, for agents and for business, plus prompt security: the base for any prompt you will put into a .NET service.
Why it matters if you work with C# and .NET: Streaming, error handling, function calling, multi-model orchestration and productionization: the layer that abstractions such as Microsoft.Extensions.AI sit on top of, and that you have to understand in order to operate it. It also shows authentication to Azure OpenAI with managed identity, in a Python example.
The components you will build with Semantic Kernel or with the SDKs, and the practices that keep them in production. What transfers is the design; the examples stay in Python.
Why it matters if you work with C# and .NET: RAG end to end, from chunking to advanced architectures and evaluation. The module on tools and frameworks has a section on Semantic Kernel as the Microsoft approach, with its example in Python.
Why it matters if you work with C# and .NET: Memory, state, tools, design patterns, guardrails and observability for agents. The frameworks module presents Semantic Kernel, with a Python example, and says when a .NET-centric organisation should choose it.
Why it matters if you work with C# and .NET: Protocol architecture, transports, authentication, enterprise patterns and security. The example servers are in Python and TypeScript; the protocol is language-agnostic, so the design carries to the C# SDK.
Why it matters if you work with C# and .NET: Golden datasets, LLM-as-a-judge and regression tests in CI/CD: answer quality becomes a release criterion in whatever pipeline you already run.
Why it matters if you work with C# and .NET: Attacks, layered defences, guardrails, data protection and compliance with GDPR and the EU AI Act: the requirements you will get from security and compliance.
Why it matters if you work with C# and .NET: Agentic coding on large codebases, the git workflow, deterministic hooks and CI. None of it is tied to a language, so it applies to .NET solutions as to any other repository.
Not sure what you can skip? Take the free level assessment
The course in the track that ends with a capstone project, from their real modules.
It opens next to the lesson and starts from it. You type or talk to it, and you can listen to the answer.
Included in every plan and in single-course access, within a fair-use limit. It is an artificial intelligence system, not a human teacher; its answers may contain errors. Details in the Terms.
The professor opens next to the lesson, on the section you have reached, with four ways to start: a summary, applying it to your job, mistakes to avoid, or a test.
You select a passage and ask for an explanation. The answer starts from the lesson, and you can listen to it, copy it or save it to your notes.
The ideas of the lesson, point by point, when you ask for them. You can listen to the summary or send it to your notes.
3, 5 or 10 new questions from the lesson you are reading, with an explanation for every answer.
Flashcards made from the lesson: you flip the card and mark what you already knew.
Screenshots from the app, taken in the demo lesson, with prepared answers.
The position of the language, what changes in your work, the tools and what you will be able to do at the end.
The .NET applications inside companies, ERPs, portals and internal services, are where assistants over documents, agent automations and tools exposed to copilots are being asked for. A C# developer who understands RAG, tool use, evaluation and security is the person who can deliver them in the ecosystem the company already lives in.
The difference from "we added a chat" is measurable: retrieval with document-level permissions, agents with guardrails and a human in the loop, evals in the release pipeline, cost per client under control. The courses below are chosen for these skills; you apply them with Semantic Kernel or directly with the SDKs, in C#.
Microsoft.Extensions.AI makes the chat client and the embedding generator injectable dependencies, like any other service. The model becomes part of the application architecture, with everything that implies: testing, telemetry, resilience.
Semantic Kernel lets you compose tools, memory and plans in C#. What decides success is the production design patterns, the guardrails and the evaluation, not the framework.
Your services become tools for assistants and agents, with authentication and least-privilege permissions, through the official C# SDK for MCP.
Coding agents work on large .NET solutions as well. Whoever gives them the right context and verifies them in CI ships faster without losing control.
These are the skills you practise in the courses of the track; results depend on the time you invest and on your previous experience.
Start the C# and .NET trackThe whole C# and .NET track fits in a subscription of 10 courses: €319 a month, VAT included. You pick the courses and can change them at every renewal.
Pay for the tier, then pick the courses in your account. You can change them at every renewal.
€99 a course
€99a month €990a year, 12 months of access
under €67 a course
€199a month €1,990a year, 12 months of access
under €52 a course
€259a month €2,590a year, 12 months of access
under €32 a course
€319a month €3,190a year, 12 months of access
under €24 a course
€359a month €3,590a year, 12 months of access
under €16 a course
€399a month €3,990a year, 12 months of access
under €10 a course, across all 50
€499a month €4,990a year, 12 months of access
Total prices, VAT included. Move up anytime and pay only the difference for the days left; move down at renewal. Renews automatically, you stop it anytime from your account; your progress and certificates stay.
Payments are processed by Stripe, a PCI DSS Level 1 certified provider, with 3-D Secure for payer authentication. The connection to this site is TLS-encrypted.
Compare all the subscriptions · The team library, priced per member · Give a month of access as a gift
When you finish the lessons of a course with an average of at least 70% on its quizzes, you issue the PDF certificate from your account, at no extra cost.
A private attestation of course completion. It is NOT a diploma or a state-recognised qualification under Romanian Laws 198/2023, 199/2023 or Government Ordinance 129/2000; employers may take it into account at their own discretion.
The same skills, seen from each ecosystem. The languages close to C# and .NET are highlighted.
No. The examples are mostly in Python, and the MCP course also has a module in TypeScript. The courses are chosen for architecture, production practices and evaluation, which you then apply in C# with Microsoft.Extensions.AI, Semantic Kernel or the official SDKs. That is also why this track has two stages instead of three: it lists only the courses whose substance does not depend on the language.
Yes. The integration, RAG, agents and evaluation courses are not tied to one provider, and the LLM integration course shows authentication to Azure OpenAI with managed identity.
A coding assistant helps you write code faster. The courses here teach you to build products with AI components: retrieval, agents, MCP tools, evaluation, security. The first is personal productivity; the second is a design skill.
All the courses recommended here are IT courses. You pick them in a subscription by number of courses: usually 3, 5 or 10 courses a month for one language and stack; there are also 15 and 25 courses, a single course and the full catalog. You pick the courses and can change them at every renewal. The subscription renews automatically, and you can stop the renewal anytime from your account. Every price, VAT included, is shown below and on the pricing page. Every course has a free preview of its first lesson, readable without an account.
9 courses, ~227 hours, in a subscription of 10 courses: €319 per month, VAT included. You can change them at every renewal.
The courses are for educational purposes only: they are not professional advice, and completing them is not a diploma or a state-recognised qualification. The names of languages, tools and products belong to their owners and are mentioned for identification only. Details in the Terms & Conditions.
ChatGPT, OpenAI, Claude, Anthropic, Gemini, Google, Microsoft 365 Copilot, Cursor, Midjourney and the other product and company names mentioned are trademarks or trade names of their respective owners. Cursuri AI is an independent training provider and is not sponsored or endorsed by any of them; our membership in Anthropic's Claude for Startups program does not mean that Anthropic endorses our courses.