Google unveils ERA AI to accelerate expert-level scientific research

2026-05-26 · Source: Dataconomy · Field: Science & Research — Mathematics & Computational Sciences, Health & Medical Research, Research Methodology & Innovation · Depth: Fundamental Awareness, quick

Summary

Google has launched its Empirical Research Assistance (ERA) AI tool, detailed in a Nature journal article, to enhance scientific coding and accelerate computational discovery. Available through a trusted tester program in Google Labs as part of the Computational Discovery prototype, ERA utilizes Gemini technology to improve the efficiency of testing and refining computational experiments. It enables users to search scientific literature, write code, explore solutions, and combine techniques, employing a tree search method to optimize generated code towards specified goals. Extensive testing demonstrated ERA's expert-level performance across benchmarks in genomics, public health, and neuroscience. As of late April 2026, Google has produced eight manuscripts highlighting ERA's applications, with five newly released, and announced gradual access to the Computational Discovery tool, which also uses AlphaEvolve. New experimental capabilities like Hypothesis Generation and Literature Insights further support the scientific method.

Key takeaway

For research scientists and computational biologists seeking to accelerate experimental workflows, ERA AI offers a powerful new approach. You should consider registering for the Google Labs trusted tester program to explore its capabilities. This tool can significantly reduce the time spent on coding and refining computational experiments, allowing you to focus on hypothesis generation and deeper insights across fields like genomics and neuroscience.

Key insights

Google's ERA AI, powered by Gemini, accelerates scientific discovery through automated code generation and experimental refinement.

Principles

• AI can achieve expert-level scientific coding.
• Tree search optimizes generated code for goals.
• Combine literature search with code generation.

Method

ERA employs a tree search method to optimize generated code, allowing users to search literature, write code, explore solutions, and combine techniques for computational experiments.

In practice

• Apply ERA to genomics research.
• Use ERA for public health modeling.
• Explore neuroscience computational problems.

Topics

• ERA AI
• Scientific Research Automation
• Computational Discovery
• Gemini Technology
• AI for Genomics
• Google Labs

Best for: Research Scientist, AI Scientist, Tech Journalist

Related on AIssential

• Empirical Research Assistance (ERA): From Nature publication to catalyzing Computational Discovery — AI tools like ERA can achieve expert-level scientific coding, accelerating computational discovery across diverse domains.
• Google launches Gemini for Science at I/O 2026 — Google's Gemini for Science suite uses AI to accelerate scientific discovery from hypothesis generation to literature review.
• Fast-tracking genetic leads to reverse cellular aging — AI tool Co-Scientist accelerates genetic aging research by generating hypotheses and streamlining data analysis.
• Four ways Google Research scientists have been using Empirical Research Assistance — ERA accelerates scientific discovery by generating expert-level empirical software for diverse, complex real-world problems.
• Quoting Karel D'Oosterlinck — AI can automate research due diligence and experiment setup, saving significant manual effort.
• Google’s new Deep Research and Deep Research Max agents can search the web and your private data — Google's new Deep Research agents fuse web and private data, generating visual reports for enterprise workflows.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Dataconomy.