Building customized knowledge bases using Markdown
Participants will build a structured, AI-ready knowledge base in plain Markdown, starting from scratch. You’ll learn how to organize files with a taxonomy and naming convention that fit how you think, write frontmatter that keeps notes findable, and apply information types (concept, principle, process, task, reference) so both you and an AI can locate the right piece. We’ll spend half the time on live demonstration—querying, drafting, and pulling across my own knowledge base in Claude Cowork—so you leave with a working mental model and a step-by-step outline to build your own.
Lance Cummings is a professor of English in the Professional Writing program at the University of North Carolina Wilmington, where he studies how content and information get built across different technological and cultural settings. His recent work pairs classical rhetoric with structured content to build knowledge bases and custom AI systems that behave reliably, and he shares those experiments in his newsletter, Cyborgs Writing. He has also led student groups through Kraków more than once, so he’s glad to have a reason to come back.