LLM Wikis: How AI Agents Build a Second Brain That Never Forgets

Most agent memory just retrieves. RAG, file search, and chat history pull back what's relevant, but the agent never organizes or improves what it knows.

LLM Wikis are different. Instead of only retrieving chunks, the agent reconciles and rewrites its own knowledge base.
Join Izma Aziz, Senior Software Engineer in Generative AI and LLMs at Data Science Dojo, for a live build using LangGraph.

What You'll Learn
🔹 What LLM Wikis are, and how an agent maintains its own knowledge base
🔹 How they differ from RAG, file search, and chat memory
🔹 Where they pay off: fewer tokens, lower cost, cleaner knowledge
🔹 How knowledge gets created and updated, in a live build
🔹 What makes agent memory reliable in production

Why This Matters
As agents take on longer, more autonomous tasks, the cost of forgetting compounds. Re-deriving context on every call burns tokens, adds latency, and risks acting on stale information. LLM Wikis give agents a persistent, self-organizing knowledge base that separates what's true now from what used to be true — instead of piling up conflicting fragments.

Who Should Come?
This session is built for AI/ML engineers, backend developers working on agent infrastructure, and technical leads evaluating memory architectures for production systems. Some familiarity with LLM agents, RAG, LangChain, or LangGraph will help — but the live build is designed to be followed even if you've never touched Deep Agents before.

Bring your questions — we'll leave time for live Q&A.