AI Architect
Become an AI Architect by building real AI systems on an enterprise .NET / Azure / SQL Server stack.
Sign in with your name + email to track your progress through the course — your friends can too, each with their own.
1
AI Fundamentals
Core concepts and how modern AI systems fit an enterprise.
5 lessons
2
Large Language Models
What LLMs are, how they behave, and where they fit.
4 lessons
3
Prompt Engineering
Designing reliable prompts and system instructions.
4 lessons
4
Embeddings
Representing meaning as vectors for search and retrieval.
4 lessons
5
Vector Databases
Storing and querying embeddings at scale (incl. SQL Server vectors).
5 lessons
6
RAG Architecture
Retrieval-augmented generation: grounding, citations, evaluation.
5 lessons
7
Tool Calling
Letting models invoke functions/APIs safely.
4 lessons
8
MCP Architecture
The Model Context Protocol and tool/server design.
4 lessons
9
Agent Design Patterns
Single-agent loops, planning, and control.
5 lessons
10
Multi-Agent Systems
Coordinating multiple agents and workflows.
4 lessons
11
AI Security
Prompt injection, data exfiltration, and defenses.
4 lessons
12
AI Governance
Policy, risk, model registries, and human-in-the-loop.
4 lessons
13
Monitoring and Observability
Tracing, evaluation logs, and AI telemetry.
4 lessons
14
Azure AI Services
Azure OpenAI and the managed-AI landscape.
4 lessons
15
Enterprise AI Architecture
End-to-end reference architectures for .NET shops.
4 lessons
16
AI Adoption Strategy
Rolling AI out across a public-sector organization.
4 lessons
17
Capstone Project
The AI Architecture Blueprint — five practical solutions.
4 lessons
18
AI-Ready Repositories
Preparing large codebases (esp. ASP.NET MVC) for AI-assisted development: docs, indexing, rules, and skills.
4 lessons
19
Machine Learning Foundations
Classical ML literacy: model types, training, evaluation metrics, and when not to use an LLM.
4 lessons
20
Model Customization
Prompting vs RAG vs fine-tuning: the adaptation spectrum and how to choose.
4 lessons
21
Data Architecture for AI
Pipelines, data quality, lineage, and privacy — feeding AI systems trustworthy data.
4 lessons
22
Multimodal AI and Cognitive Services
Vision, speech, documents, and translation — the managed-AI service landscape.
4 lessons
23
Evaluation, LLMOps and Cost
Golden sets, LLM-as-judge, release discipline, and token economics.
4 lessons
24
Design Exercises and Exam Readiness
Worked AI-architecture design scenarios and exam preparation.
4 lessons