Every speaker discovers, sooner or later, that giving a presentation is mostly a question of survival. This cockpit is the closest thing yet to a Babel fish strapped to your slide deck: speak, and titles materialise. Pause, and The Guide whispers the quote, the data point, the counter-argument you almost remembered. One shareable link throws the same talk on every screen in the room. The Guide is definitive. Reality is frequently inaccurate. Mostly harmless.
You don't read from a script — the model drives every slide title via tool calls in real time. Drop any markdown — a half-finished outline, raw notes, a fully-written keynote — and it gets attached as planning context so the model can anticipate topic shifts and pick titles that match the arc you had in mind. No formatting required. Frontmatter and slide markers buy you a side-pane reference and a talk timer; everything else is bonus.
The cockpit listens to you over WebRTC and asks GPT-realtime to drive slide titles via function calls. A separate long-context agent (gpt-5.4, a million tokens deep) watches the same transcript and surfaces quotes, data points, and counter-arguments into The Guide — never coaching, only substance the speaker can defend. The audience tab is a read-only Stage you can throw on a TV; viewers can also type the four-letter code at /join. Time is an illusion. Slide-prep time, doubly so.