Opening the library
A technical publishing studio for AI
AI internals,explained conversationally.
We open up the models, agents, and tools behind modern AI and walk through what is going on inside: the moving parts, the tradeoffs, and why things ended up this way, all in plain, conversational language. Written to be understood, whether you are just getting started or already building in production.
Why this exists
Most explanations of AI either stay on the surface or vanish into the math. Real understanding lives in between, and that is the space we write for: deep enough to be genuinely true, plain enough to actually land. We explain it the way you would to a curious friend, because that is how ideas stick. Every piece is free to read, and there is a lot of it.
Latest
Recently published
Protocols14 min read
The MCP Ecosystem: What's Worth Using
A guided tour of the servers, registries, and patterns that survived the hype.
Read the pieceRecent work
All articles
Protocols12 min
MCP Security: The Attack Surface You Just Installed
Explainers12 min
Multimodal Agents: When Vision Meets Action
Explainers13 min
Document AI: How Models Read PDFs, Tables, and Receipts
Explainers10 min
Video Models: Why Motion Is So Much Harder
Deep Dives11 min
Local Inference: Running Models on Your Own Machine
Deep Dives10 min