---
title: "Slides: RAG is dead, right?? — Kuba Rogut, Turbopuffer"
category: "slides"
video_id: "UM6sFg_jdlE"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

# Slides: RAG is dead, right?? — Kuba Rogut, Turbopuffer

## Source Video
[RAG is dead, right?? — Kuba Rogut, Turbopuffer](https://www.youtube.com/watch?v=UM6sFg_jdlE)

## 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/UM6sFg_jdlE/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/UM6sFg_jdlE/slide-002.html)
- AI slide classifier: `title_card` confidence `0.95`
- Text source: agent_vision.

Slide text:

> Rag is dead, right??
> How hybrid, tool-rich retrieval is becoming the default for serious agentic search
> Kuba Rogut
> Deployed Engineer
> April 9, 2026
> Engineering the future of AI

![[assets/slides/UM6sFg_jdlE/slide-003.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/UM6sFg_jdlE/slide-003.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: advanced OCR `rapidocr-live/full`.
- OCR decision: ready — Content slide with a dense embedded product/chart screenshot and small UI text; OCR is likely better than manual transcription.

Slide text:

> "RAGisdead"？ turbopuffer
> Retrieval Aug onted Ge
> Mar 1, 2021- Feb 27, 2026
> AIE
> lnterest over time
> AIEngineer
> EUROPE

![[assets/slides/UM6sFg_jdlE/slide-004.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/UM6sFg_jdlE/slide-004.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: advanced OCR `rapidocr-live/border-trim/opencv-adaptive`.
- OCR decision: ready — Content slide with a dense comparison diagram and an embedded social/media screenshot; OCR is likely the efficient way to capture the body text.

Slide text:

> from RAG to agentic retrieval turbopuffer
> pattern Google Jeff Oean says bigger context windows alone are not enough Haldr. O - Hslow devrlope! tuyqns
> ★ + ★ AIE ★ From RAG - Agentic Rctrieval old -Stuff the prompt. Cross fingers - Retrieve once new -Search as needed - Reason in steps - Fetch what is useful Wmat matters is staged retrieval: lightweight mechanisms that narrow 3 trillion tokens down to 10 million, then to the mition you actually nood you don't need a trillion ot once, you noed the right mlion* Oelow_develops!
> Retrieval is now iterative with tools
> AlEngineer
> EUROPE


### Hidden Non-Slide Evidence
- [`slide-001.jpg`](/assets/slides/UM6sFg_jdlE/slide-001.jpg) — `speaker_stage` confidence `0.98`; Speaker standing at podium with audience visible; this is a stage shot, not a clean presentation slide frame.

Classification audit: `raw/sources/slide-ai-classification/slides/UM6sFg_jdlE/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.