Science experimental tools

A collection of experiments exploring the future of AI-powered scientific discovery

Built with Google NotebookLM

Literature Insights

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.

Built with Co-Scientist

Hypothesis Generation

Generate novel research ideas through a multi-agent system that simulates the scientific method to help identify knowledge gaps and propose testable research plans.

Built with AlphaEvolve and Empirical Research Assistance (ERA)

Computational Discovery

Discover models and algorithms with an agentic research engine that generates and scores code variations based on your optimization metrics.

Literature Insights

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.

Comprehensive Literature Search

Perform high-signal filtering and search to find relevant papers for your research.

Automated Data Extraction

Extract data, such as complex metrics and variables, from your papers to compare side-by-side.

Traceable Research Reports

Extract comprehensive literature search with citations that can link claims back to the highlighted text in the source.

Custom Artifact Generation

Transform deep literature analysis into shareable team resources by using the studio panel to instantly produce slide decks, mind maps, audio overviews, infographics, and more.

Hypothesis Generation

Generate novel research ideas through a multi-agent system that simulates the scientific method to help identify knowledge gaps and propose testable research plans.

Collaborative Research Partner

Chat with a specialized agent to help expand and refine your research challenge, preferences, and focus areas before initiating a run.

Tournament-Style Evaluation

Employs a multi-step tournament process to generate a breadth of novel research directions while rigorously evaluating their potential.

Grounded Knowledge Base

Generated ideas are linked to a comprehensive knowledge base of verified scientific references used by the agent during the run.

Critical Flaw Detection

Surfaces insights that can distinguish high-potential directions from non-viable ones by helping to identify key limitations and critical flaws.

Computational Discovery

Discover models and algorithms with an agentic research engine that generates and scores code variations based on your optimization metrics.

Collaborative Task Definition

Work with the agent to help define your optimization task, evaluation requirements, and apply relevant scientific methods.

Deep Exploration

Generates and scores thousands of code variations in parallel to test modeling directions that would be extremely difficult to explore manually.

Insights and Inspection

Inspect the evolutionary lineage of your code and use the agent to help understand the specific "jumps" in performance scores.

Workflow-Ready Results

Delivers expert-level, vetted code that can be quickly integrated into your existing research workflow or used for further iteration.