Visual essays, hands-on labs, and field notes for people building useful AI products. Learn the intuition, inspect the system, then take the idea into your own work.
A better way to learn
Every deep dive can combine explanation, diagrams, code walkthroughs, and small experiments in one focused reading flow.
Build the mental model
Concise narrative + diagrams
Change one variable
Interactive, visual feedback
Inspect the implementation
Step-by-step code walkthrough
Visual essays and practical explanations for building useful AI and product systems.
You've seen MCP servers mentioned in AI tool docs. You've wondered how Claude actually calls external functions. This is the guide that explains both — and by the end of this series you'll have a running, production-ready MCP server connected to Claude Desktop, built in Python.
An end-to-end edge device ML classification model
AIML academy
Guided concept paths with video, transcripts, grounded study notes, and knowledge checks.
Concept lab
Interactive blocks live inside an article, next to the explanation they support. Here is the first reusable lab.
Explore all labsChange the learning rate and iteration count. Watch the optimizer settle, oscillate, or overshoot the minimum.
The optimizer is moving efficiently.
Build log
Focused case studies about what was built, why the architecture took shape, and what changed after shipping.
AI/ML · In Progress
A multi-model AI life coach agent built with LangGraph that understands your voice, sees your images, and speaks back to you. Powered by open-source models Llama 3.3, Whisper and SD XL.
Python · Chainlit · LangGraph · Git · Langchain
The shelf
Templates, playbooks, and code kits created and maintained by the author of this publication.
The dispatch
Join 5,361 engineers already subscribed
