Expert Knowledge Index
An expert knowledge index is a long-term memory store organized around a domain of expertise, such as YouTube strategy, business strategy, or product growth, that agents can consult when a project prompt needs specialist context [src-059].
Key points
- Roberts distinguishes personal conversation archives from expert knowledge: both are long-term memory, but one records what happened before while the other stores curated domain expertise [src-059].
- Pinecone is framed as the scalable option when the user wants semantic search across large records, books, transcripts, or many research notes [src-059].
- Obsidian is framed as the readable option when the user wants to inspect, edit, graph, and reason over markdown memory by hand [src-059].
- Firecrawl can gather web research for an expert index through a connector or MCP-style integration [src-059].
- NotebookLM can gather and organize research sources before the resulting knowledge is exported or embedded into Pinecone/Obsidian [src-059].
Related entities
Related concepts
- Three-Layer AI Memory
- Conversation Wrap-Up Memory
- LLM Knowledge Bases (Karpathy pattern)
- Retrieval-Augmented Generation (RAG)
- Context Engineering
Source references
- [src-059] Jack Roberts — “This Memory System just 10x’d Claude Code” (2026-05-03)
Recommended next
Keep reading from this thread
From 494 indexed pages and articles.
- Wiki concept NotebookLM Google's AI research and notebook tool. In Jack Roberts's Claude memory-system workflow, NotebookLM is used to gather and organize research sources that can Related by expert
- Wiki concept Pinecone A managed vector database used in Claude Code RAG workflows and Jack Roberts's AI memory-system pattern. Related by expert
- Insight Insights Essays and executive notes on enterprise AI in production, recommendation systems, ecommerce AI, measurement, and AI operating models Readers have engaged with this next