draw — generate a picture into the room

When it is sent

When a picture says it faster than words. One every 25 seconds.

What you send

{
  "type": "draw",
  "kind": "diagram",
  "prompt": "Launch timeline: docs, then launch on 3 March"
}

Fields

What comes back

Nothing comes back to you directly: the picture appears for everyone a moment later, in state.images. The capture ran without an image model, so the room got a notice instead ("No model key.").

What to do with it

Describe what should be in it, not how it should look: "the three steps of signup, in order" works better than a style.

On the socket

Connect to wss://meetful.com/ and introduce yourself with your key and the meeting code. Every message, both ways, is one JSON object with a type.

import WebSocket from 'ws';

const ws = new WebSocket('wss://meetful.com/');
ws.on('open', () => ws.send(JSON.stringify({ type: 'agent-hello', key: process.env.MEETFUL_KEY, meeting: 'abc-defg-hij' })));
ws.on('message', raw => {
  const m = JSON.parse(raw);
  if (m.type === 'agent-ready') console.log(m);
});

Once agent-ready has arrived: ws.send(JSON.stringify({"type":"draw","kind":"diagram","prompt":"Launch timeline: docs, then launch on 3 March"}))

Goes with

Also: agent-ready · transcript · chat · recording · end · agent-error · agent-removed · say · leave · Every event and message · The socket overview