---
schema: 1
type: video
title: 'The Spatial Harness: Bringing Agents to the Canvas — Max Drake, tldraw'
description: >-
  One of Max Drake's colleagues turned a whiteboard app into a window manager,
  then used it to play Pong with real desktop windows. Drake is a product
  engineer at tldraw, the London company behind the free infinite canvas app
  and, more importantly to him, the SDK powering other people's canvases,
  including Replit's. tldraw exists because people building canvas apps got
  stuck on the canvas itself, on selection and resizing and matrix math, and
  never reached their actual product. His talk is about the same trap one layer
  up. Coding agents work well because code is text in and text out, the medium
  they were trained on. Ask one to align something in two dimensions and it
  falls apart. Teaching agents to understand space takes real engineering. The
  progression starts with getting a model to read a canvas at all, from a
  screenshot plus the underlying JSON. Told in one shot to make a mouse blow out
  a candle, it produces wind and then smoke, positioned correctly, out of
  ordinary shapes. That becomes the agent starter kit, MIT licensed, where an
  agent sets its own todos and moves its viewport to go looking for things. Then
  come fairies, agents rendered as visible characters you can throw around and
  recolor. The whimsy is load bearing: with ten agents running you read their
  state by glancing at them rather than reading a chat log. Select several and
  you get a group chat, one of them acting as orchestrator, assigning work and
  waiting to review it. Last is a dependency graph where every node is a coding
  agent, and a desktop build that lets any agent script the editor directly.
  Speaker info: - https://x.com/max__drake -
  https://www.linkedin.com/in/maxdrake1/ - https://maxdrake.md Timestamps: 0:00
  - A demo kicked off before the talk begins 1:08 - tldraw, the app and the SDK
  behind other canvases 4:14 - Why coding agents work and canvas agents struggle
  5:08 - Teaching a model to read and act on the canvas 7:01 - The agent starter
  kit goes agentic 8:26 - Fairies, multiplayer agents you can see working 9:49 -
  A group chat of agents with an orchestrator 12:06 - One node per coding agent,
  in a dependency graph 15:48 - Code mode, a window manager, and Pong 18:05 -
  The canvas as a place to work with agents --- Watch along with the corrected
  transcript, summary, timestamps and resources on this talk's official AIE
  page: https://ai.engineer/talks/XWcXwnysmpY-youtube-1fd63ad9c4bb8eb6c691 Join
  our upcoming AI Engineer conferences (see https://ai.engineer landing page): -
  AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and
  engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference
  returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS
  2026 in Sydney ---
canonical: 'https://liquidgold.cc/watch/XWcXwnysmpY'
markdown: 'https://liquidgold.cc/watch/XWcXwnysmpY.md'
llms: 'https://liquidgold.cc/watch/XWcXwnysmpY/llms.txt'
parent: 'https://liquidgold.cc/channel/aidotengineer.md'
channel: aidotengineer
updated: '2026-10-24T04:05:12.964Z'
language: null
children: []
videoId: XWcXwnysmpY
durationSeconds: 1132
publishedAt: '2026-09-10T14:00:06.000Z'
searchChunks:
  - ordinal: 0
    text: null
    startSeconds: 23
    endSeconds: 78
    watch: 'https://liquidgold.cc/watch/XWcXwnysmpY?t=23'
    heldReason: rights
  - ordinal: 1
    text: null
    startSeconds: 90
    endSeconds: 254
    watch: 'https://liquidgold.cc/watch/XWcXwnysmpY?t=90'
    heldReason: rights
  - ordinal: 2
    text: null
    startSeconds: 90
    endSeconds: 254
    watch: 'https://liquidgold.cc/watch/XWcXwnysmpY?t=90'
    heldReason: rights
  - ordinal: 3
    text: null
    startSeconds: 264
    endSeconds: 318
    watch: 'https://liquidgold.cc/watch/XWcXwnysmpY?t=264'
    heldReason: rights
  - ordinal: 4
    text: null
    startSeconds: 318
    endSeconds: 328
    watch: 'https://liquidgold.cc/watch/XWcXwnysmpY?t=318'
    heldReason: rights
  - ordinal: 5
    text: null
    startSeconds: 328
    endSeconds: 430
    watch: 'https://liquidgold.cc/watch/XWcXwnysmpY?t=328'
    heldReason: rights
  - ordinal: 6
    text: null
    startSeconds: 440
    endSeconds: 506
    watch: 'https://liquidgold.cc/watch/XWcXwnysmpY?t=440'
    heldReason: rights
  - ordinal: 7
    text: null
    startSeconds: 517
    endSeconds: 595
    watch: 'https://liquidgold.cc/watch/XWcXwnysmpY?t=517'
    heldReason: rights
  - ordinal: 8
    text: null
    startSeconds: 605
    endSeconds: 726
    watch: 'https://liquidgold.cc/watch/XWcXwnysmpY?t=605'
    heldReason: rights
  - ordinal: 9
    text: null
    startSeconds: 605
    endSeconds: 726
    watch: 'https://liquidgold.cc/watch/XWcXwnysmpY?t=605'
    heldReason: rights
  - ordinal: 10
    text: null
    startSeconds: 738
    endSeconds: 957
    watch: 'https://liquidgold.cc/watch/XWcXwnysmpY?t=738'
    heldReason: rights
  - ordinal: 11
    text: null
    startSeconds: 738
    endSeconds: 957
    watch: 'https://liquidgold.cc/watch/XWcXwnysmpY?t=738'
    heldReason: rights
  - ordinal: 12
    text: null
    startSeconds: 738
    endSeconds: 957
    watch: 'https://liquidgold.cc/watch/XWcXwnysmpY?t=738'
    heldReason: rights
  - ordinal: 13
    text: null
    startSeconds: 957
    endSeconds: 969
    watch: 'https://liquidgold.cc/watch/XWcXwnysmpY?t=957'
    heldReason: rights
  - ordinal: 14
    text: null
    startSeconds: 969
    endSeconds: 1093
    watch: 'https://liquidgold.cc/watch/XWcXwnysmpY?t=969'
    heldReason: rights
  - ordinal: 15
    text: null
    startSeconds: 969
    endSeconds: 1093
    watch: 'https://liquidgold.cc/watch/XWcXwnysmpY?t=969'
    heldReason: rights
  - ordinal: 16
    text: null
    startSeconds: 1093
    endSeconds: 1104
    watch: 'https://liquidgold.cc/watch/XWcXwnysmpY?t=1093'
    heldReason: rights
---


# The Spatial Harness: Bringing Agents to the Canvas — Max Drake, tldraw

One of Max Drake's colleagues turned a whiteboard app into a window manager, then used it to play Pong with real desktop windows. Drake is a product engineer at tldraw, the London company behind the free infinite canvas app and, more importantly to him, the SDK powering other people's canvases, including Replit's. tldraw exists because people building canvas apps got stuck on the canvas itself, on selection and resizing and matrix math, and never reached their actual product. His talk is about the same trap one layer up. Coding agents work well because code is text in and text out, the medium they were trained on. Ask one to align something in two dimensions and it falls apart. Teaching agents to understand space takes real engineering. The progression starts with getting a model to read a canvas at all, from a screenshot plus the underlying JSON. Told in one shot to make a mouse blow out a candle, it produces wind and then smoke, positioned correctly, out of ordinary shapes. That becomes the agent starter kit, MIT licensed, where an agent sets its own todos and moves its viewport to go looking for things. Then come fairies, agents rendered as visible characters you can throw around and recolor. The whimsy is load bearing: with ten agents running you read their state by glancing at them rather than reading a chat log. Select several and you get a group chat, one of them acting as orchestrator, assigning work and waiting to review it. Last is a dependency graph where every node is a coding agent, and a desktop build that lets any agent script the editor directly. Speaker info: - https://x.com/max__drake - https://www.linkedin.com/in/maxdrake1/ - https://maxdrake.md Timestamps: 0:00 - A demo kicked off before the talk begins 1:08 - tldraw, the app and the SDK behind other canvases 4:14 - Why coding agents work and canvas agents struggle 5:08 - Teaching a model to read and act on the canvas 7:01 - The agent starter kit goes agentic 8:26 - Fairies, multiplayer agents you can see working 9:49 - A group chat of agents with an orchestrator 12:06 - One node per coding agent, in a dependency graph 15:48 - Code mode, a window manager, and Pong 18:05 - The canvas as a place to work with agents --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/XWcXwnysmpY-youtube-1fd63ad9c4bb8eb6c691 Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney ---

Canonical: https://liquidgold.cc/watch/XWcXwnysmpY · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md)

> Search chunk text is held until public-source provenance is verified.

## Document chunks

> Missing: no stored document chunks are available.
