Tag
Boris Cherny released a 7-page PDF on Graph Engineering, showing how to use four Claude prompts to replace trained ML models by building a persistent knowledge graph for agents, with steps for extraction, resolution, summarization, and querying.
Explores a method where AI agents traverse their memory instead of performing traditional querying, potentially offering efficiency or reasoning benefits.
The post suggests using Claude Code with Filesystem MCP to query an Obsidian vault, turning it from a managed filing system into a queryable knowledge base.