Google Labs introduced Tabletop on Wednesday an experimental AI-driven platform designed to transform group chat planning into interactive, shared applications.
By utilizing natural language prompts, users can generate custom itineraries, expense trackers, and decision-making tools without writing code, effectively moving collaborative logistics out of fragmented message threads.
Moving Beyond the Static Group Chat
The core friction in group coordination often stems from the transition between conversation and execution.
Users initiate the process by creating a workspace within the Tabletop experimental platform. Once a space is generated, participants can drop in files, links, or unstructured notes. By mentioning @tabletop, the system processes these inputs to build specific modules like tournament brackets or voting boards.
The resulting tools remain dynamic; if a group decides to shift a dinner reservation or add a new stop to a road trip, the AI can reconfigure the interface rules in real-time.
🚨 NEW LABS EXPERIMENT 🚨 Introducing Tabletop 🎲— our newest experiment built to get your crew from "we should totally do that" to "we’re actually doing this." Drop links and files into one shared space, add your crew, and ask Tabletop for whatever you need to create custom… pic.twitter.com/EHFLWOCwdk
Real-Time Collaboration Architecture
Google has designed Tabletop to function similarly to collaborative document editing. Once a user generates a tool, they share an invitation link directly into their preferred messaging app. This allows multiple participants to interact with the same data set simultaneously, mirroring the backend synchronization found in Google Docs or Sheets.
This release continues Google's research into generative AI-powered app construction. It builds upon previous experimental projects like Opal and Disco, which also explored low-code or no-code interfaces generated through LLM interactions. However, Tabletop shifts the focus toward multi-user utility rather than individual productivity.
Google Restricts Tool Access to US Users over 18
As of November 12, 2026, the tool remains in a restricted testing phase. According to the official Google Labs announcement, access is currently limited to users aged 18 and older located within the United States. Prospective users must request access through a waitlist system before they can begin building shared spaces.
The company has not disclosed a long-term monetization strategy or confirmed if these collaborative features will eventually migrate into the core Google Workspace suite. For now, the experiment serves as a sandbox for how LLMs can mediate social coordination, moving away from simple text-based responses toward structured, interactive data environments.
Underlying Models Map Data Onto Logic Templates
The platform relies on the ability of the underlying model to interpret disparate data types—ranging from simple text snippets to uploaded files—and map them onto pre-defined logic templates. This process minimizes the technical barrier for non-developers, allowing the group to focus on the outcome rather than the architecture of the tool itself.
While the initial templates include common use cases like expense splitters and seating charts, the flexibility of the @tabletop prompt suggests an intent to support more complex, user-defined rules. Whether this experiment will scale to handle enterprise-level project management or remain a consumer-focused tool for social planning remains an open question as the waitlist begins to roll out in the U.S.
Google Labs just launched Tabletop, an AI-powered shared space for group planning, today. Here's what you need to know. Tabletop is a new Google Labs experiment built to get your crew from "we should totally do that" to "we're actually doing this." Announced on November 11,… https://t.co/QXK3WceqSJ pic.twitter.com/ABd6ViXy07
