Microsoft Agent Framework with Ollama Tutorial

Foundations — AI & Agents

1 Introduction to AI 8 min 2 Introduction to LLMs 8 min 3 Generative AI Basics 8 min 4 Open Source AI Ecosystem 8 min 5 Why Run AI Locally 8 min 6 What Is an AI Agent 8 min 7 Agent vs Chatbot 8 min 8 Tools and Function Calling 8 min 9 Multi-Step Reasoning 8 min 10 LocalAIDesk Project Overview 8 min

Ollama — Local Models

11 Ollama Installation 8 min 12 Ollama CLI Essentials 8 min 13 Ollama REST API 8 min 14 Pulling and Listing Models 8 min 15 Running DeepSeek Locally 8 min 16 Running Phi Locally 8 min 17 Running Llama Locally 8 min 18 Running Mistral Locally 8 min 19 Running Qwen Locally 8 min 20 Choosing a Model for Your Agent 8 min

ASP.NET Core + Ollama

21 ASP.NET Core AI Project Setup 8 min 22 Calling Ollama from C# 8 min 23 HttpClient and Ollama Chat API 8 min 24 Streaming Tokens to the Browser 8 min 25 SignalR Live AI Replies 8 min 26 AI Options with IOptions 8 min 27 Dependency Injection for AI Services 8 min 28 Securing AI Endpoints 8 min 29 Request Timeouts and Retries 8 min 30 Building a Minimal Chat API 8 min

Semantic Kernel & Agents

31 Semantic Kernel Basics 8 min 32 Connecting Kernel to Ollama 8 min 33 Kernel Plugins 8 min 34 Native Functions as Tools 8 min 35 Prompt Functions 8 min 36 Chat History and Memory 8 min 37 Planner-Style Tool Loops 8 min 38 AutoGen-Style Multi-Agent Basics 8 min 39 Agent Collaboration Patterns 8 min 40 Enterprise Agent Guardrails 8 min

RAG & Vector Search

41 RAG Fundamentals 8 min 42 Embeddings Explained 8 min 43 Chunking Documents 8 min 44 Semantic Search Flow 8 min 45 Using Qdrant with .NET 8 min 46 Using ChromaDB 8 min 47 Using pgvector 8 min 48 Pinecone Overview 8 min 49 Hybrid Keyword Plus Vector Search 8 min 50 Building a Local RAG Service 8 min

Security & Observability

51 Prompt Injection Basics 8 min 52 Jailbreak Risks 8 min 53 Preventing Data Leakage 8 min 54 Authorizing AI Features 8 min 55 Auditing AI Calls 8 min 56 Structured AI Logging 8 min 57 Monitoring Latency and Errors 8 min 58 Tracing Agent Steps 8 min 59 Simple AI Analytics 8 min 60 Security Checklist for Local Agents 8 min

DevOps & Infrastructure

61 Dockerizing Ollama Apps 8 min 62 Kubernetes Notes for AI Workloads 8 min 63 GPU vs CPU for Local Models 8 min 64 Scaling Chat Workers 8 min 65 CI/CD for Agent Apps 8 min 66 Infrastructure Checklist 8 min 67 Edge and Offline AI 8 min 68 Observability at Scale 8 min 69 Cost and Hardware Budgets 8 min 70 Production Readiness Gate 8 min

Product Use Cases

71 AI SaaS Product Shape 8 min 72 Multi-Tenant AI Isolation 8 min 73 ERP Assistant Use Case 8 min 74 CRM Copilot Use Case 8 min 75 Healthcare Assistant Constraints 8 min 76 Automation Platform Patterns 8 min 77 Workflow Agents 8 min 78 Analytics Copilot 8 min 79 Enterprise Platform Layers 8 min 80 Cloud-Native Plus Local Hybrid 8 min

System Design

81 AI System Design Basics 8 min 82 Scalability for Agents 8 min 83 Distributed Agent Workers 8 min 84 Queues for Long Jobs 8 min 85 Caching Model Responses 8 min 86 Event-Driven Agent Pipelines 8 min 87 High Availability for AI APIs 8 min 88 Backup and Model Artifact DR 8 min 89 Reference Architecture LocalAIDesk 8 min 90 Global Rollout Considerations 8 min

Capstone Projects

91 CRM Copilot Mini Project 8 min 92 ERP Assistant Mini Project 8 min 93 Hospital Triage Helper Project 8 min 94 Analytics Q&A Project 8 min 95 Coding Assistant Project 8 min 96 Workflow Automation Project 8 min 97 Research Summarizer Project 8 min 98 Multi-Agent Desk Project 8 min 99 Enterprise SaaS Shell Project 8 min 100 LocalAIDesk Capstone 8 min