AI-Enhanced Development in .NET with Semantic Kernel
Description
In this training, participants will learn how to integrate Large Language Models (LLMs) into ASP.NET Core applications, design structured prompts, and orchestrate AI workflows using plugins, memory, and Retrieval-Augmented Generation (RAG). The course emphasizes real-world architecture patterns, including API design, AI service abstraction, and secure, scalable deployment.
Indicative Duration: 20 training hours
*Duration is adjusted based on the final scope and the target audience.
Scope
|
1. AI in .NET and prompting
|
• What are LLMs and how they work • Role of Microsoft Semantic Kernel • Comparison with traditional APIs • Connecting to Azure OpenAI • Configuration best practicesHands-on: Build AI endpoint in ASP.NET Core |
|
| • Structured prompts • Prompt templates • Input/output control • Avoiding hallucinationsHands-on: Build reusable prompt templates |
||
|
2. Plugins, Function Calling,
Memory & RAG |
• Native functions (C#) • Tool calling • Plugin architectureHands-on: Build a plugin (e.g., customer lookup, weather API) |
|
| • Embeddings • Vector databases • Retrieval-Augmented Generation (RAG)Hands-on: Build document Q&A system |
||
| 3. Building a Full AI Web API | • API design patterns • AI service abstraction • Dependency injection with SKHands-on: Build full backend (chat + plugins + RAG) |
|
| 4. Frontend Integration | • Connecting frontend to AI API • Chat UI patterns • Streaming responsesHands-on: Simple Angular chat interface |
|
| 5. Security & Responsible AI | • Prompt injection • Data leakage risks • Guardrails • Compliance considerations |
|
| 6. Observability & Optimization | • Logging prompts/responses • Token cost control • Performance tuning |
|
| 7. Agents & Automation | • Planner patterns • Multi-step workflows • Agent architectures (Planner-Executor-Validator) |
|
| 8. Intelligent automation systems | Hands-on: Build AI agent • Banking assistant • Customer support copilot • Document Q&A system • AI-powered analytics assistant |
|
Learning Objectives
Upon completion of the course participants will be able to:
- Design and implement AI-powered Web APIs using .NET and Semantic Kernel
- Build and use plugins to connect AI with real business logic and systems
- Develop end-to-end applications with frontend interaction (chat-based or task-driven)
- Apply security best practices (prompt injection protection, data handling)
- Monitor and optimize AI performance (latency, token usage, cost)
Target Audience
- Roles: .NET developers transitioning into AI-enabled applications
- Seniority: Junior to Mid-Level Professionals or Senior Professionals exploring AI in enterprise environments
Prerequisite Knowledge
- Intermediate knowledge of C# and .NET (ASP.NET Core)
- Understanding of REST APIs
- Basic familiarity with cloud concepts (preferably Azure)
Delivery Method
Sessions can be delivered via the following formats:
- Live Online – Interactive virtual sessions via video conferencing
- On-Site – At your organization’s premises
- In-Person – At Code.Hub’s training center
- Hybrid – A combination of online and in-person sessions
