Build an LLM Wiki for Agent Long-Term Memory
Build a compounding knowledge engine - Paul Iusztin
Imagine giving your AI agents a true long-term memory where every piece of information they learn builds on the last. Instead of starting from scratch every session, your agents can rely on a structured, self-updating knowledge base that makes them faster, smarter, and remarkably cost-effective.
Join us for this hands-on coding workshop where we’ll build an LLM Wiki: an agent-maintained Second Brain that synthesizes domain knowledge once and compounds its value over time. Together, we’ll build an end-to-end system that elevates scattered notes, GitHub repos, and transcripts into a clean, cross-referenced memory layer that transforms how your agents reason and retain information.
We’ll cover the following steps:
Design a structured markdown hierarchy with index.md files and automatic cross-links to organize core agent memory.
Create automated workflows that instantly convert scattered sources into clean, synthesized knowledge artifacts.
Equip your agents with specialized skills to continuously summarize, categorize, and reason over complex topics.
Build efficient retrieval and auto-update loops to keep your agent's wiki naturally fresh as new data arrives.
By the end of this workshop, you’ll be able to deploy a local, persistent AI Research OS that equips your agents with long-term memory, unlocking continuous learning and building a personal knowledge engine that gets smarter with every single session.
About the Speaker:
Paul Iustin is the author of the bestseller LLM Engineer’s Handbook, lead instructor of the Agentic AI Engineering course, founding AI Engineer of a San Francisco start-up, and obsessed with making knowledge accessible through AI.
With over 10 years of experience and 20 apps shipped, he teaches AI Engineering as he wanted to at the beginning of his career. End-to-end. From idea to production. From data collection to deploying, monitoring, and evaluation. With a focus on AI principles, software patterns, and infrastructure systems that will thrive in a future dominated by AI coding tools.
His ultimate goal is to help other engineers escape PoC purgatory and 10x their AI Engineering skills.
DataTalks.Club is the place to talk about data. Join our Slack community!