---
title: "Slides: How we taught agents to use good retrieval - Hanna Lichtenberg, Mixedbread AI"
category: "slides"
video_id: "1IdzkRVmWAA"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

# Slides: How we taught agents to use good retrieval - Hanna Lichtenberg, Mixedbread AI

## Source Video
[How we taught agents to use good retrieval - Hanna Lichtenberg, Mixedbread AI](https://www.youtube.com/watch?v=1IdzkRVmWAA)

## Relationship To World's Fair 2026
These slides are extracted from a public AI Engineer YouTube video connected to World's Fair 2026. Speaker-matched clips are supporting context unless later confirmed as exact session recordings; official livestream recordings are day-level/event-level source material.

## Related Scheduled Sessions
- No individual scheduled session mapping has been assigned yet; treat this as an event livestream deck.

## Extracted Slides
![[assets/slides/1IdzkRVmWAA/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/1IdzkRVmWAA/slide-002.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: none.
- OCR decision: ready — diagram slide with small labels and axis text
![[assets/slides/1IdzkRVmWAA/slide-003.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/1IdzkRVmWAA/slide-003.html)
- AI slide classifier: `content_slide` confidence `0.93`
- Text source: none.
- OCR decision: ready — dense quote and bullet text
![[assets/slides/1IdzkRVmWAA/slide-004.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/1IdzkRVmWAA/slide-004.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.
- OCR decision: ready — timeline graphic with small table text

Slide text:

> Agent trajectories - timeline

![[assets/slides/1IdzkRVmWAA/slide-005.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/1IdzkRVmWAA/slide-005.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.
- OCR decision: ready — tool-call table and nested UI text are small

Slide text:

> Agent trajectories - tool calls


### Hidden Non-Slide Evidence
- [`slide-001.jpg`](/assets/slides/1IdzkRVmWAA/slide-001.jpg) — `title_card` confidence `0.97`; speaker intro card with headshots and names

Classification audit: `raw/sources/slide-ai-classification/slides/1IdzkRVmWAA/audit.json`

## Slide-Derived Subjects To Review
Subject extraction uses video title, related session titles/descriptions, transcript context, and OCR text when available. OCR is best-effort and should be reviewed against the embedded slide images.