// Track

Agent Memory 101

Why Your AI Forgets — and How to Fix It

Every AI user has felt it: the model forgets everything between sessions. This track explains the problem plainly and walks you from context windows to a personal knowledge OS — RAG vs. structured facts, trust scores, the query-first habit, and memory hygiene.

8 lessons~69 min total

Lessons are shown in recommended order. Complete them in sequence for the best experience — or jump to any lesson.

Lesson 344·7 min read

Why Your AI Forgets Everything

Every time you open a new chat, your AI starts with a blank slate — and understanding exactly why is the first step to fixing it.

Lesson 345·8 min read

Context Windows: The Short-Term Memory Ceiling

The context window is your AI's working memory — it holds everything, but it is finite, and when it fills, the oldest content falls off the edge.

Lesson 346·9 min read

RAG vs Structured Facts: Two Kinds of Memory

Vector search and key-value stores are both 'memory,' but they solve fundamentally different problems — knowing which to reach for changes the quality of every AI system you build.

Lesson 347·8 min read

The Query-First Habit: Recall Before You Act

The single most powerful memory discipline is not what you store — it is querying what you have before you take the first step on any task.

Lesson 348·9 min read

Trust Scores and Contradiction Detection

Not every stored memory deserves equal weight — assigning confidence scores and detecting contradictions is what separates a reliable knowledge store from a confusing pile of facts.

Lesson 349·8 min read

Writing Good Memories: The One-Fact Rule

A memory store full of transcript dumps is worse than useless — the one-fact rule is the discipline that makes every entry searchable, actionable, and durable.

Lesson 350·8 min read

Pruning: When Forgetting Is a Feature

A memory store that never forgets anything slowly becomes a trap — stale facts and superseded decisions poison every query until pruning becomes the most valuable maintenance task you have.

Lesson 351·12 min read

Building Your Own Personal Knowledge OS

Seven lessons of memory theory converge here: a beginner-accessible architecture for a personal knowledge OS that makes every AI session smarter than the last.