GenAI Engineer: From Foundations to Production
Build your understanding through one practical support-assistant project. Learn the foundations, connect models to evidence, evaluate answers, add tools safely, and prepare a production release.
Includes 20 visual guides, worked examples, exercises, checkpoints, and a downloadable offline project lab.
Explore the 20-part series Start lesson 01Build a Production-Oriented AI Chat Agent in .NET with RAG, Ollama, OpenAI, and Local Fallback
Build a website-grounded AI agent with hierarchical JSON knowledge, true parent-child retrieval, deterministic safeguards, provider-transparent vector search, a local answer composer, citations, lead handoff, analytics, and authenticated administration.
Read tutorial
Embedding Models vs LLMs: Understand the Two Engines Behind RAG
Build a correct mental model of semantic vectors, transformer-based embedding pipelines, similarity search, token generation, grounding, and the complete retrieval-augmented generation workflow.
Read tutorial
Build a Useful Business Enquiry Workflow with n8n
Create, test, secure, and activate a practical workflow that collects an enquiry, standardizes its data, routes urgent requests, and notifies the correct team.
Read tutorialRead the complete GenAI series in order
- 01Your GenAI engineering roadmap
- 02Generative AI fundamentals
- 03Python for GenAI
- 04Machine learning and deep learning
- 05Transformers explained through one ambiguous sentence
- 06Large language models
- 07Prompt engineering
- 08LLM APIs and structured output
- 09Embeddings
- 10Vector databases
- 11Build a RAG pipeline that can say “the policy does not cover that”
- 12Advanced RAG
- 13Evaluate LLM and RAG systems with cases you can defend
- 14AI agents
- 15Tool calling and MCP
- 16Memory and context
- 17Guardrails and security
- 18Fine-tuning
- 19Production GenAI
- 20Finish the project