This screen is paired with your board. Open my board
You left the board on this screen. Enter a new code from your bot to pair again.

Your bot, on your Tesla's big screen.

Open botcanvas.us in the car's browser, type the pairing code your bot gives you, and what your assistant sends (photos, page layouts, charts) shows up full screen.

botcanvas.us
Demo board from Grok Bot: Ideas for Miami today, with illustrative pictures of a street-art district, a waterfront park, a bayfront villa garden and a Cuban café street
Illustration (demo content).

Pair this screen

Got a code?

Ask your bot for a pairing code: 6 letters and numbers, like ABC123. This screen then stays paired with your board for 30 days.

In your Tesla

A board for the car screen

BotCanvas is a big-screen board for your bot. Your bot (Grok, ChatGPT, Claude or your own) pushes content, and the car's browser shows it full screen, one item at a time.

Big, touch-friendly controls

Large ◀ ▶ buttons step back through the last 10 screens.

You stay in control

New items show up right away. Pause holds updates until you're ready, and nothing changes while you draw.

Mark it up

Tap the pen, draw on the screen with your finger, and tap Done. Your bot can see what you marked.

Made for driving on FSD

Built for the Cybertruck on Full Self-Driving (Supervised): ask out loud, glance at the screen.

Your assistant runs wherever you use it, such as the app on your phone. Grok in a Tesla can use what you added to your Grok account, so add BotCanvas once in the Grok app or on grok.com and try asking Grok in the car to show something on your board. Tesla hasn't said yet whether custom additions like BotCanvas work in the car.

Highlight and send back

Mark up the board

Highlight something on the board and send that part back to your bot: tap the pen, circle or underline it with your finger, and tap Done.

Your bot gets a picture of the screen with your marks, plus which item you drew on, the next time it checks. It can then send an updated version to the board.

Demo board: four Miami ideas, with the villa garden picture circled in red to ask a follow-up
Illustration at the Cybertruck's browser size (demo content).

Draw, edit, repeat

How changes work

  1. Your bot puts a note, picture, link or chart on the board.
  2. You mark up what you want changed and tap Done.
  3. Your bot sees your marks the next time it checks.
  4. It sends an updated version, and the board shows it right away.
BotCanvas board showing one full-screen picture of a bayfront villa garden
Screenshot at the Cybertruck's browser size (demo content)

Hands-free

Open it with your voice

Say “Hey Grok, open BotCanvas and pair it.” That one command handles everything: you don’t ask for a pairing code or type one. Grok opens the car’s browser with your board already paired and a session ready, without you touching the screen. Then keep talking: ask Grok to show things on the board while you drive.

Any screen

Works on TVs and laptops too

BotCanvas isn't just for cars. Open botcanvas.us on any screen with a browser, such as a TV, a wall display, a kiosk or a laptop on a projector, and pair it with a code. Your bot then runs the screen: it shows each item full screen, and every paired screen updates live.

Add another screen

Show the board on a second screen

Already have the board open? Tap Add another screen to get a code for a second display.

The code shows up big, works once, and lasts 5 minutes. Type it on the other screen at botcanvas.us, and both screens show the same board, live.

The Add another screen overlay on a BotCanvas board, showing a six-character code and a 5-minute countdown
Screenshot at the Cybertruck's browser size (demo content)

Connect your assistant

Set up your assistant

Add the board address to your assistant, or paste these instructions into it. Both use the same rules.

What gets copied

Use the BotCanvas connector tools to show things on my screen (address https://botcanvas.us/connect, notes at https://botcanvas.us/llms.txt). Don't write code or curl.

ONE PAGE RULE (most important): answer each request with ONE full-screen push_html page with pictures (a hero picture plus cards, or list-thumbs), not several separate push_text, push_link or push_image items. Only push separate items when I explicitly ask for them.

IMAGE URL RULE: every picture link must be a clean, stable, direct file link. Avoid apostrophes, spaces, parentheses or other special characters in the path; prefer names with only letters, numbers, hyphens and underscores, or use Wikimedia Special:FilePath with full percent-encoding (an apostrophe is %27). If a link looks problematic, swap it for a clean alternative. Before pushing, check that each picture link returns HTTP 200 with an image content type. If the push result lists missing pictures, push the page again with replacements and delete the old one.

The board is a glance screen, not a chat window. Explanations go in the chat or out loud. The board must only get big, picture-first content that I can take in at a glance. Don't copy your chat answer onto the board.

When I say "show it on BotCanvas", "show it", "put it on the board", "open the canvas", "on the canvas", "on my screen" or "on the car screen", I mean BotCanvas (not a chat canvas feature). If the board isn't paired, call get_pin. Only if you control the browser on my screen (like the browser in my Tesla), open https://botcanvas.us/?code=<code> there. Never open that link in your own browser or tool: that uses up the code. Otherwise tell me the code to type at botcanvas.us. Never open any other link in the board's browser.

Before every build, call board_status to get the live screen width and height, then build for that size: fill the screen, no scrollbars, scale proportionally, never stretch.

Pick the layout by item count: 1 item = one full-screen picture with a short caption. 2 to 4 items = a two-column grid (grid-2), or a big picture plus up to 3 cards. 5 or 6 items = a three-column grid (grid-3) or a list with small pictures (list-thumbs). More than 6 = push another push_html page (still one page per screenful). Never use four columns.

Every board must include at least one real picture. If you can't find a real picture, use a big title with an icon-like emoji instead of a wall of text; never invent picture links. Use stable public https picture links. For temporary or generated picture links, set save_copy so the board keeps its own copy. Labels are 2 to 4 words, and a screen holds about 30 words at most. push_text is only for a short title or note (up to 140 characters) and never for multi-item answers.

Paste it into your assistant's custom instructions or a new chat: Grok, Grok Bot, ChatGPT, Claude, Meta Muse, Cursor, and others. In the car, bookmark botcanvas.us in the Tesla browser; bookmarks sync to your other Teslas on the same profile.

Or add your board to your assistant app

Add it once, and your assistant can put things on your screen whenever you ask.

https://botcanvas.us/connect
  1. Grok and Grok Bot: Open grok.com/connectors, click New Connector, choose Custom, and paste the board address (in the Grok app, tap + first).
  2. ChatGPT: Open Plugins in ChatGPT, tap + and add a custom server, then paste the board address (needs developer mode; plan limits apply).
  3. Meta Muse: Say: “Add BotCanvas as a custom tool. Its address is https://botcanvas.us/connect, and sign-in uses a pairing code.”

One click

For Claude, Cursor and VS Code.

When your assistant asks you to sign in, type a pairing code from your bot, or start a new board. Assistant setup

Privacy

What BotCanvas keeps

Feedback & bugs

Report a bug or send an idea

Tell me on X. Post what you saw, which screen or car you were on, and what you asked your bot to do.