---
title: "Slides: Teaching Coding Agents to do Spreadsheets - Nuno Campos, Witan Labs"
category: "slides"
video_id: "HEFSExa0xl0"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

# Slides: Teaching Coding Agents to do Spreadsheets - Nuno Campos, Witan Labs

## Source Video
[Teaching Coding Agents to do Spreadsheets - Nuno Campos, Witan Labs](https://www.youtube.com/watch?v=HEFSExa0xl0)

## 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/HEFSExa0xl0/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/HEFSExa0xl0/slide-002.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> 50% → 92%
> - 4 months, multiple architectures, and many dead ends
> - What mattered most: replacing 15 discrete tools with one REPL

![[assets/slides/HEFSExa0xl0/slide-003.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/HEFSExa0xl0/slide-003.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.
- OCR decision: ready — dense table/small text and formula-like content

Slide text:

> The problem

![[assets/slides/HEFSExa0xl0/slide-004.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/HEFSExa0xl0/slide-004.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: agent_vision.

Slide text:

> One dead end
> Three specialized agents:
> 1. Block discovery – identifies workbook structure
> 2. Edit agent – 5-step process: disambiguate, define end state, plan, execute, verify
> 3. Question agent – answers questions
> Key finding: Rigid architectures don't win

![[assets/slides/HEFSExa0xl0/slide-005.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/HEFSExa0xl0/slide-005.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: agent_vision.
- OCR decision: ready — table layout with small text across multiple rows

Slide text:

> More dead ends

![[assets/slides/HEFSExa0xl0/slide-006.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/HEFSExa0xl0/slide-006.html)
- AI slide classifier: `content_slide` confidence `0.96`
- Text source: agent_vision.
- OCR decision: ready — code snippets and small before/after tool-call text

Slide text:

> Before vs. After

![[assets/slides/HEFSExa0xl0/slide-007.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/HEFSExa0xl0/slide-007.html)
- AI slide classifier: `content_slide` confidence `0.95`
- Text source: agent_vision.
- OCR decision: ready — paragraph text plus code snippet on slide

Slide text:

> Code mode vs. REPL

![[assets/slides/HEFSExa0xl0/slide-008.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/HEFSExa0xl0/slide-008.html)
- AI slide classifier: `content_slide` confidence `0.94`
- Text source: agent_vision.
- OCR decision: ready — diagram and small explanatory text are better suited to OCR

Slide text:

> The verification loop

![[assets/slides/HEFSExa0xl0/slide-009.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/HEFSExa0xl0/slide-009.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> Interface vs. engines
> 
> The REPL is an interface — the best one today, because coding is where models are strongest.
> 
> The engines — formula calculation, rendering, linting — are the more durable part. They're what close the verification loop, and they compound with each new model.
> 
> If for instance agents become as capable at computer use as they are at coding, the interface might change. The engines won't.

![[assets/slides/HEFSExa0xl0/slide-010.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/HEFSExa0xl0/slide-010.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.

Slide text:

> Domain knowledge outlived every tool
> 
> — We changed tools four times in four months
> — The financial domain knowledge improved results on every one of them
> 
> Structured as a composable prompt component:
> 
> — How to interpret margins, profitability, revenue cascades
> — Model type recognition (DCF, LBO, three-statement)
> — Communication conventions ($1.2M not $1,234,567.89)
> — "Never calculate in your head what the spreadsheet can calculate for you"
> 
> It was the most reused component in the system.

![[assets/slides/HEFSExa0xl0/slide-011.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/HEFSExa0xl0/slide-011.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: none.
- OCR decision: ready — Dense two-column table with small text is better handled by OCR.

### Hidden Non-Slide Evidence
- [`slide-001.jpg`](/assets/slides/HEFSExa0xl0/slide-001.jpg) — `speaker_stage` confidence `0.99`; Speaker on stage with a cropped projected slide; not a readable presentation frame.

Classification audit: `raw/sources/slide-ai-classification/slides/HEFSExa0xl0/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.