An AI that teaches on a whiteboard, inside the meeting
How a Mainroom agent explains a concept by drawing it by hand, step by step, while it talks: what it looks like, why it beats a slide, and how it plans a lesson in seconds.
Ask a Mainroom agent "how do bicycle gears work?" and it does what a good teacher does at a whiteboard: it says a sentence and draws the first piece, explains it with an example, draws the next, and keeps going until the picture is complete.
What it looks like
The board appears on the meeting's shared screen. Each step is drawn by hand while the agent talks: lines trace themselves on, shapes fill in, and labels write themselves out. A lesson is four to seven steps, each one a short spoken explanation over the part of the drawing it adds, so the picture and the words arrive together. It picks the visual form that fits the idea: a cog and a chain for gears, a timeline for a history, two columns for a comparison, a worked example for a formula.
Questions about the drawing are answered on the drawing: "which of those is the one attackers go after?" gets a ring around that part, not a paragraph.
Why a whiteboard and not a slide
A slide is a finished thing. It arrives all at once, and the room reads ahead of the speaker. A drawing grows at the pace of the explanation, so the picture and the words stay together. That is why people teach at whiteboards, and it is why an agent that only had slides felt like it was reading a document at you.
When the agent reaches for it
The agent treats "how does X work", "walk me through", "what's the difference between", "help me understand" and similar as teaching asks with structure to them, and answers on the board. It does not use the board for a plain list or a recap (that is a slide), for a one-line factual answer, or on a customer call unless its owner asks.
How it stays readable
- Big type: titles and labels are sized for a shared screen seen in a small meeting window.
- Short labels: a few words each, never paragraphs on the board.
- One idea per step: each step adds one part of the picture, explained before the next arrives.
- A question mid-lesson pauses it; "keep going" picks it back up where it left off.
What it is built on
When the agent decides to teach, one fast planning call writes the whole lesson at once: for each step, the sentence to say and the drawing to add, as plain vector shapes. The page the meeting bot shares draws each step stroke by stroke while the agent speaks that step's sentence. Planning everything up front is what lets the first drawing appear within seconds and the lesson flow without pauses between steps.
Try it: invite the demo agent at demo@mainroom.ai to a call and ask it to teach you something.
Frequently asked questions
Can I ask the agent to draw something specific?
Yes. "Teach me how OAuth works", "draw the flow", "circle the risky step", "clear the board and start over" all work. The agent also decides on its own when a question would be better answered with a drawing than with words.
Does the whiteboard work on Google Meet, Teams and Zoom?
Yes. The board is shared through the platform's screen share, so it works wherever the agent can share its screen.
How long does it take to start drawing?
The first drawing usually appears a few seconds after the ask. The whole lesson, typically four to seven steps, is planned in well under ten seconds, and each step is drawn as the agent explains it.