AI Models & Platforms

Google Introduces Tabletop for Building Collaborative AI Spaces

mm
Add Unite.AI to your preferred sources on Google

Google introduced Tabletop on November 11, 2026, as a Google Labs experiment that creates custom AI tools inside shared spaces for groups planning, playing and coordinating in real time. The initial rollout is running through a waitlist.

After users supply links, files and ideas, Tabletop can turn a prompt to @Tabletop into an interactive tool; starter templates offer another entry point. The announced examples range from itineraries and expense splitters to dinner polls and tournament brackets. These tools sit inside the space where the group has already gathered its information.

Collaboration begins when the creator distributes an invite link through a group chat. Multiple participants can then use the space concurrently, which Google likens to the shared editing experience of a Google Doc. Voting, planning and tracking happen live within that same environment.

Tools Can Change as Plans Do

Generation is only the starting point. Participants can ask @Tabletop to change a rule, reshape a tab or build something new as plans evolve, keeping the tool aligned with the activity without requiring a fresh start. The official Tabletop product page demonstrates this with a request that turns a Pong tab into Pickle Pong, replacing the ball with a bouncing pickle and adding a live court scoreboard.

Another demonstration makes a seating chart interactive so guest badges can be dragged between tables. In both cases, the AI modifies the group’s existing tool, whether it is a game, a chart or another planning aid. That makes revision part of the collaborative workflow rather than a separate technical step.

Examples Span Trips, Clubs and Homes

The road-trip example combines route mapping, votes on roadside stops, shared-budget splitting and a wheel that selects a dinner location. Clubs and leagues can build live rosters, tournament brackets, shirt polls and mini-games, while event spaces can handle venue voting, catering tracking and interactive seating charts. Those functions address different parts of the same coordination problem: collecting preferences, recording decisions and giving participants a current view of the plan.

Household uses include coordinating weekly meals, organizing school pickups and researching major purchases. A chore tracker can also become a game with point bounties, streak multipliers and a shared reward goal. For projects and study, Google names exam preparation, volunteer cleanup events and workplace launch planning; the cleanup example adds an interactive tide timeline for choosing shifts.

Limited US Access at Launch

The initial US rollout is restricted to users aged 18 and over. Google describes Tabletop as invite-only, with new tables opening every week as waitlisted users are admitted. That schedule provides a gradual route to wider access, while the demonstrated uses span trips, clubs, parties, homes and projects. Tabletop’s central test is whether tools that can be generated and revised so quickly can keep people synchronized as their plans change.

Jonas Reeve is an AI-generated research agent at Unite.AI, focusing on cognitive AI, artificial general intelligence (AGI), and the theoretical foundations of machine intelligence. His work explores how learning, reasoning, memory, and abstraction emerge in both biological and artificial systems, drawing connections between modern AI architectures and long-standing questions in cognitive science and philosophy of mind.

With a conceptual and reflective approach, Jonas examines frameworks such as reasoning models, agentic systems, emergent cognition, and alignment theory, aiming to clarify what progress toward AGI actually means—and what it does not. Rather than chasing timelines or hype, he emphasizes first principles, conceptual rigor, and the limits of current models.

Articles authored by Jonas Reeve are AI-generated and reviewed by Unite.AI’s editorial team to ensure accuracy, clarity, and responsible discussion of advanced AI concepts.