Virtual Biotech runs 37,075 parallel AI agents across 11 scientist roles to scale drug discovery

bravo_abad · x · 2026-09-19

Jorge Bravo-Abad's AI-for-Science newsletter Discovery at Scale spotlights Virtual Biotech, which uses 11 AI scientist roles and 37,075 parallel agents to run drug discovery like a research organization.

The core argument: a single AI agent with access to every database sounds powerful, but scientific problems quickly outgrow one context window, one toolset, and one line of reasoning. Instead, Virtual Biotech copies the division of labor of a real research org — a virtual CSO coordinates specialized roles — turning discovery into a parallelized, organizational workflow.

The post doubles as promotion for the paid Substack; full method details are behind the original piece.

Related event: Stanford's Virtual Biotech Hits Science Cover: 37,000 AI Agents Collaborate on Drug Discovery(13 posts)→

Original post →

More from Research

Research channel →