Hierarchical Memory: Context Management in Agents https://youtube.com/watch?v=esY99nYXxR4 Sally-Ann Delucia from @arizeai spent a year building an AI agent that had to analyze the very trace data it was generating. The naive solution was truncation. The obvious solution was summarization. Neither worked. The talk covers the vicious loop, what actually held (head/tail preservation with a retrievable memory store), long session evals, and sub-agents for context that gets too heavy for one…