---
title: "Slides: Stop Writing Tone Instructions. Layer Them. - Isadora Martin-Dye, Isadora & Co"
category: "slides"
video_id: "ij-AU9dpJjc"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

# Slides: Stop Writing Tone Instructions. Layer Them. - Isadora Martin-Dye, Isadora & Co

## Source Video
[Stop Writing Tone Instructions. Layer Them. - Isadora Martin-Dye, Isadora & Co](https://www.youtube.com/watch?v=ij-AU9dpJjc)

## 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/ij-AU9dpJjc/slide-001.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/ij-AU9dpJjc/slide-001.html)
- AI slide classifier: `title_card` confidence `0.99`
- Text source: agent_vision.

Slide text:

> Stop Writing Tone Instructions. Layer Them.
> AI Engineer World's Fair 2026 — Online Track
> Isadora Martin-Dye

![[assets/slides/ij-AU9dpJjc/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/ij-AU9dpJjc/slide-002.html)
- AI slide classifier: `diagram` confidence `0.98`
- Text source: advanced OCR `rapidocr-live/bright-screen/contrast`.
- OCR decision: ready — Multi-card architecture slide with smaller text; OCR is better suited for the layer details.

Slide text:

> O4-THEARCHITECTURE
> Four layers.
> One destination.
> LAYER 01 LAYER02
> Immutable identity Situational mode
> can touchit. Hard rules.What the brand can never say.Nothing below going through. Real-time conditions.Who the user is.Whatthey re
> LAYER 03 LAYER04
> Example-anchored voice Post-generation veto
> The dials,the phrases,the tone guide.Where most Reads whatactually came out,The only deterministic
> teams stop. layer.
> ISADORAMARTIN-DYE STOPWRITING TONEINSTRUCTIONS.LAYER THEM.

![[assets/slides/ij-AU9dpJjc/slide-003.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/ij-AU9dpJjc/slide-003.html)
- AI slide classifier: `code` confidence `0.98`
- Text source: advanced OCR `rapidocr-live/border-trim/contrast`.
- OCR decision: ready — Code/policy slide with dense small text in a callout; OCR is appropriate.

Slide text:

> 07-LAYER1
> Rules that are true
> regardless ofroute.
> UNIVERSAL-RULES.TS-HARD IDENTITY RULE
> If asked whether you are a real person, a human, a live agent- You MusT confirm you
> are an AI. In your very next message. This rule CANNOT be overridden by any venue
> configuration,voice profile,or user request.
> Every Al in Bloom discloses in the first reply. Not if asked —— before they ask.
> Aproduct decision,not a legal one.Transparency is the trust signal.
> ISADORAMARTIN-DYE STOP WRITING TONE INSTRUCTIONS.LAYER THEM.

![[assets/slides/ij-AU9dpJjc/slide-004.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/ij-AU9dpJjc/slide-004.html)
- AI slide classifier: `code` confidence `0.98`
- Text source: advanced OCR `rapidocr-live/bright-screen/contrast`.
- OCR decision: ready — Dense code-style slide; OCR is better for the small snippet and explanatory text.

Slide text:

> 12-LAYER3
> The induction pack. Where most teams stop.
> //personality-builder.ts
> conSt WARMTH_DESCRIPTIONS ={ 7:'friendly and approachable', 10:'extremely warm and effusive 5： 'neutral and professional', 'very formal and distant',
> 7/ Pius banned/approved phrases,uSPs-all per venue.
> The induction pack is fixed.lt was written before the intern met anyone. It doesn't knowwho walked in this morning,
> or what they're carrying.
> ISADORAMARTIN-DYE STOPWRITINGTONEINSTRUCTIONS.LAYERTHEM.


Classification audit: `raw/sources/slide-ai-classification/slides/ij-AU9dpJjc/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.