Knowledge base
Explore by category
Five domains, each broken into focused subcategories and series.
Artificial Intelligence
Agents, reasoning systems, and the protocols that connect models to the world.
3 articles
Large Language Models
Training, fine-tuning, serving, and engineering with LLMs.
1 article
Machine Learning
From classical algorithms to modern training pipelines.
7 articles
Software Engineering
Systems, infrastructure, and craft for AI-era builders.
0 articles
Recently published
Synthetic Dataset Generator
Generate regression and multi-class classification datasets on the fly — linear, polynomial, moons, spirals, checkerboards — and export them as CSV.
Logistic Regression, Interactively
Build intuition for logistic regression by training one live in your browser — adjust the learning rate, watch the decision boundary move, no backend required.
Build an MCP Server From Scratch in Python
A hands-on tutorial: build a Model Context Protocol server with FastMCP that gives any AI client full CRUD over a todo list backed by a CSV file — then connect it to Claude.
What Is the Model Context Protocol?
MCP is the USB-C of AI applications — a single open protocol that lets any model talk to any tool or data source. Here's the mental model.
Build a RAG Pipeline From Scratch in Python
A complete, step-by-step tutorial: build a Retrieval-Augmented Generation system over your own documents using ChromaDB, sentence-transformers, and OpenAI — then measure its quality.
Prompting Foundations for Reliable Systems
Move past prompt 'tricks' to the durable principles that make LLM-powered systems predictable: structure, constraints, and evaluation.