Build AI systems that survive production
Architectural patterns, design decisions, and failure modes — from a working AI Implementation Architect. Not tutorials. Not commentary. The patterns that hold up under real load.
AI Implementation Architect's Playbook
A free Notion template plus PDF — the framework I use to architect AI systems for solo operators and product builders. Includes the 5 design patterns and 7 failure modes from the MCP pillar, plus everything not yet published.
Send me the playbookPillars
Deep architectural guides for AI builders. Each pillar anchors a cluster of supporting articles and connects to a course.
MCP Architecture for Builders
Model Context Protocol turned ad-hoc AI tool integration into a standard. Here's how to architect MCP servers that actually scale — five des...
Personal AI Knowledge OS
AI Agents Architecture for Solo Operators
AI Workflow Automation Design Patterns
Recent encyclopedia entries
Foundations and definitions. Read these before the pillars if you're new to a topic.
-
LLM (Large Language Model): How They Work and What They Are Good For
A large language model is a transformer-based neural network trained on massive text corpora to predict the next token. The mechanism, what it can and cannot do, and how to choose the right model.
foundations -
RAG (Retrieval-Augmented Generation): How LLMs Use External Knowledge
Retrieval-Augmented Generation lets large language models cite up-to-date sources by retrieving relevant documents before generating answers. The architecture, trade-offs, and when to use RAG over fine-tuning.
techniques