Markdown source

Everyone talks about document search, but what about results?

Conference Context

Session Description

Search is usually treated as the end of the document pipeline: parse, chunk, retrieve, and hand them to the model. But long-running agents need something more durable than one-off retrieval. They need reusable work: structured outputs, citations, extracted entities, prior decisions, and file-system-like context they can return to across tasks. At scale, context management is where most agent systems fall apart. Without the right harness, agents lose track of what they've retrieved, bloat their context windows, and stall. In this talk, we'll look at why the document pipeline needs a stateful layer beyond the index — one that turns one-off retrieval into reusable, agent-ready context. We'll see how LlamaIndex thinks about transforming messy documents to make this possible, and why the future of document intelligence belongs to results that compound over time, not just better search.

Media Evidence

No related AI Engineer channel video found yet.

Evidence Graph

This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

Media Signals

No linked video, transcript, or slide source has been attached yet.

Agent Reading Notes

Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

Transcript Status

No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

People

Notes

Synthesis

Synthesized Breakdown

Everyone talks about document search, but what about results? ## Conference Context - Date/time: 2026-07-01 · 1:55pm-2:15pm - Track/room: track TBD · Expo Stage 4 SE - Speaker(s): George He - Session type/status: session · confirmed - Track: track TBD - Room: Expo Stage 4 SE - Session type: session - Status: confirmed ## Session Description Search is usually treated as the end of the document pipeline: parse, chunk, retrieve, and hand them to the model. But long-running agents need something more durable than one-off retrieval. They need reusable work: structured outputs, citations, extracted entities, prior decisions, and file-system-like context they can return to across tasks.

Speaker And Company Context

Topics Covered

Derived Links And Source Material

Novel Concepts / Clever Methods

Evidence Boundary

This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.