---
title: "Slides: Your Agent Is Wasting Tokens and You Don't Know It - Erik Hanchett, AWS"
category: "slides"
video_id: "uiP88SpCi1Q"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

# Slides: Your Agent Is Wasting Tokens and You Don't Know It - Erik Hanchett, AWS

## Source Video
[Your Agent Is Wasting Tokens and You Don't Know It - Erik Hanchett, AWS](https://www.youtube.com/watch?v=uiP88SpCi1Q)

## 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/uiP88SpCi1Q/slide-001.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/uiP88SpCi1Q/slide-001.html)
- AI slide classifier: `title_card` confidence `0.97`
- Text source: agent_vision.

Slide text:

> Costing Too Much

![[assets/slides/uiP88SpCi1Q/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/uiP88SpCi1Q/slide-002.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: advanced OCR `rapidocr-live/bright-screen/opencv-adaptive`.
- OCR decision: ready — Code slide with dense small text; OCR is better suited than manual transcription.

Slide text:

> FIX 01 Cache the System Prompt
> 000 agent = Agent( model=BedrockModel( model_id="claude-sonnet" cache prompt-+default". # cache static prefix
> System-prompt=BIG-SYSTEM PROMPT
> 04 0 86

![[assets/slides/uiP88SpCi1Q/slide-003.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/uiP88SpCi1Q/slide-003.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: advanced OCR `rapidocr-live/bright-screen/opencv-adaptive`.
- OCR decision: ready — Code slide with dense small text; OCR is better suited than manual transcription.

Slide text:

> pix 03 Ofload Big Tool Results
> Otool. def fetch-report(id: str) stre 00O Geturn summarize(data, key) data e api-get(id) key store:put(data) 0 10k tokens. B summary + ref # offLoad

![[assets/slides/uiP88SpCi1Q/slide-004.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/uiP88SpCi1Q/slide-004.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> Same Agent. Smaller Bill.
> Cache the System Prompt
> Route by Difficulty
> Offload Big Tool Results
> Cap Your Tool Loops
> Trim the History

![[assets/slides/uiP88SpCi1Q/slide-005.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/uiP88SpCi1Q/slide-005.html)
- AI slide classifier: `title_card` confidence `0.95`
- Text source: agent_vision.

Slide text:

> Thanks!
> Go Deeper
> Erik Hanchett
> Social Media
> ErikCH
> Site
> programwitherik.com


Classification audit: `raw/sources/slide-ai-classification/slides/uiP88SpCi1Q/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.