What shipped
2026
SQL essentials for keeping state
A new tutorial on the SQL skills needed to keep state in AI apps is now available. It covers modeling a chat assistant's state with tables and constraints, answering operational questions with joins and aggregates, and querying Postgres safely from Python.
Docker basics for AI apps
A new tutorial on the Docker concepts needed to run AI services is now available. It covers images, containers, multistage builds, and composing a stack of services with one command.
Plan-and-execute agent
A new tutorial on how to build a financial research agent that plans multi-step analysis upfront, executes each step through a tool registry, and replans when findings change is now available.
Build an MCP agent
A new tutorial on how to build an MCP agent is now available. It covers the fundamentals of MCP and how to build an agent that can execute trades through the protocol.
Vectorless RAG
A new tutorial on how to build a vectorless RAG system is now available. It covers the fundamentals of building a RAG system without using embeddings.
Rewrite of the Foundations module
The Foundations module is now rewritten. It covers the fundamentals of Python, math, and PyTorch for AI engineers.
Workflows vs agents
A new tutorial on how to build a workflow vs an agent is now available. It covers the fundamentals of both and when to use each.
New modules: Setup and Toolkit, and Context Engineering
The new Setup and Toolkit and Context Engineering modules are now available. They cover the fundamentals of building an AI engineer's toolkit and how to use it to build a production-ready RAG system.
2025
LLMOps: deploying and monitoring a vLLM service
A new tutorial on how to deploy and monitor a vLLM service is now available. It covers the fundamentals of deploying and monitoring a vLLM service and how to use it for inference in production.
Agentic RAG: building a research agent team
A new tutorial on how to build an agentic RAG system for financial analysis is now available. It covers the fundamentals of agentic RAG and how to build a multi-agent system with LangGraph.
Train your model: fine-tuning an LLM
A new tutorial on how to fine-tune an open-source LLM into a specialized expert for your specific task is now available. It covers the fundamentals of fine-tuning and how to use it to build a specialized model.
No more manual tweaking: automated prompt engineering
A new tutorial on how to use DSPy to automate the prompt engineering process is now available. It covers the fundamentals of DSPy and how to use it to optimize prompts for your specific use case.
Beyond benchmarks: evaluating LLMs
A complete rewrite on how to evaluate LLMs for your specific use case is now available. It covers the fundamentals of evaluating LLMs and how to build a private evaluation pipeline.
Build your own dataset
A new tutorial on how to build your own dataset using knowledge distillation is now available. It covers the fundamentals of knowledge distillation and how to use an existing LLM to build a custom dataset for model evaluation or training.
Getting started with LangGraph
A new tutorial on LangGraph is now available. It covers the fundamentals of LangGraph and how to use it to build workflows and agents.
Advanced retrieval
A new tutorial on advanced retrieval is now available. It covers the fundamentals of advanced retrieval and how to use it to build a semantic search engine for your RAG system.
Embeddings and vector databases
A new tutorial on embeddings and vector databases is now available. It covers the fundamentals of embeddings and how to use them to build a semantic search engine for your RAG system.
Local AI quickstart
A new tutorial on how to run AI models locally with Ollama is now available. It covers the basics of installing Ollama, downloading a model, and interacting with it through the command line and Python.
Chunking strategies
A new tutorial on chunking strategies is now available. It covers the fundamentals of chunking and what chunking strategies are best for different types of documents.
Python Essentials rewrite
The Python Essentials module is now updated in line with the rest of the academy. It's now more focused on the practical skills you'll need as an AI engineer.
Setup and Toolkit module
The first module of the academy is now complete. It covers the basics of setting up your development environment, including the command-line toolkit, Python project setup, and IDE (VScode/Cursor) configuration.
What is RAG?
A new tutorial on Retrieval-Augmented Generation (RAG) is now available. It covers the fundamentals of RAG and how to build a simple RAG system from scratch to production-ready API with FastAPI and Docker.
Document processing with a VLM
Add a section on how to use a Vision Language Model (VLM) to extract text from images in a document. Using Docling and Ollama (Nanonets-OCR-s).
Prompt engineering rewrite
Use the latest Anthropic and OpenAI guidelines for prompt engineering along with a new example.
RAG and MCP AI agent tutorials
Added RAG and MCP AI agent tutorials to the academy. These tutorials have associated GitHub project repositories.
Want something shipped? Suggestions land in my inbox: venelin@mlexpert.io.