Actively collaborating with the scientific community
Google Labs is bringing its early science experiments together in one shared workbench built around provenance, lab collaboration, and steerable compute.
Announcing our Early Access Program
Google Labs is bringing its early science experiments together in one shared workbench built around provenance, lab collaboration, and steerable compute.
Co-Scientist Workbench
Inviting the scientific community to help us answer our open questions about the future of AI in science.
“Its been great testing the iterations in inline attribution on scientific claims in Co-Scientist Workbench. Using AI for experimental science comes with its own unique hurdles, and I am excited to keep working with the Google Labs team on provenance and more.”
“Research begins with a hypothesis that connects ideas across disciplines. Google’s Co-Scientist Workbench offers a powerful opportunity to help researchers make those connections, generate new hypotheses, and explore ways to test them.”
“This is the tool I have been looking for.”
Join us to stress-test and co-design provenance features which help you verify AI-interpreted claims.
Invite your colleagues into a shared project with a steerable agent, and help us define how research teams might collaboratively audit and verify AI outputs.
Test Co-Scientist Workbench across both your quick daily checks and deep investigations, and work with us to design the right controls for balancing speed, rigor, and cost.
A collection of experiments exploring the future of AI-powered scientific discovery
Comprehensive literature search to find relevant papers, structure results in a data table, and create high-fidelity artifacts like reports, slide decks, infographics, and more.
Generate novel research ideas through a multi-agent system that simulates the scientific method to help identify knowledge gaps and propose testable research plans.
Discover models and algorithms with an agentic research engine that generates and scores code variations based on your optimization metrics.
Comprehensive literature search to find relevant papers, structure results in a data table, and create high-fidelity artifacts like reports, slide decks, infographics, and more.
Generate novel research ideas through a multi-agent system that simulates the scientific method to help identify knowledge gaps and propose testable research plans.
Discover models and algorithms with an agentic research engine that generates and scores code variations based on your optimization metrics.