A living research map of AI systems, tools, and operating models.
This wiki is my structured long-term memory for the expert topics I am exploring: enterprise AI, agentic workflows, recommendation systems, AI operating systems, knowledge infrastructure, and the practical tooling behind modern AI work.
Why this exists
The wiki follows the LLM wiki pattern: structured, interlinked pages that an AI assistant can read directly, update over time, and use as durable memory. It is also public proof that I do not just consume AI research. I build infrastructure to make that research compounding and usable.
Start here
LLM wiki pattern
The knowledge-base architecture behind this system.
Proof-of-concept first
A useful concept for understanding why many AI efforts fail to become production systems.
Agentic workflows
How multi-step AI systems move from prompt responses to operational workflows.
LLM wiki vs semantic RAG
A comparison of lightweight knowledge bases and embedding-based retrieval systems.
Source quality
The knowledge base is built mostly from YouTube transcripts and public resources from authoritative practitioners and researchers, with bookmarks and web clippings added over time. Public pages are designed to be readable as standalone knowledge assets; private summaries stay private when they are raw research material.
Keep reading from this thread
From 491 indexed pages and articles.
- Insight Insights Essays and executive notes on enterprise AI in production, recommendation systems, ecommerce AI, measurement, and AI operating models Related by enterprise
- Insight AI Beyond POCs How enterprise AI moves beyond proofs of concept through ownership, governance, measurement, adoption, and production operating models Readers have engaged with this next
- Wiki concept LLM Knowledge Bases (Karpathy pattern) A practical guide to LLM knowledge bases, the Karpathy markdown wiki pattern, and what it teaches production AI teams about durable memory and governance Readers have engaged with this next