RAG, Memory & Knowledge SystemsComing
Agentic Memory Foundations
How modern AI agents remember — the architecture of semantic, episodic, and procedural memory, and the retrieval pipelines that keep an agent's knowledge accurate over time. You leave able to design a memory layer that stays fresh instead of silently rotting.
What you'll learn
- Name the three canonical memory types — semantic, episodic, and procedural — and say what each one stores, where it lives, and when it is read.
- Trace a retrieval pipeline end to end: embed a query, search a vector index, re-rank candidates, and inject the survivors into the prompt as grounded context.
- Explain why naive RAG drifts toward stale answers, and what a freshness layer (last-verified dates, change detection, re-validation) adds on top.
- Sketch a namespace-scoped memory store so that a fact learned for one user, task, or community is not accidentally surfaced to another.
Want something you can start today? The catalog lists every track that is open right now.
Explore the catalog