Anthropic Launches Claude Science Beta: A Multi-Agent AI Workbench for Reproducible Genomics, Proteomics, and Cheminformatics Pipelines
Not a chatbot. Anthropic just shipped Claude Science — a multi-agent workbench that handles reproducible genomics pipelines end-to-end, with full code lineage and fact-checking built in.
Why it matters
Anthropic is moving Claude from conversation layer into specialized scientific workflows. This signals a shift toward agentic products that integrate compute infrastructure, domain databases, and reproducibility as core features — a play for enterprise science teams where accuracy and auditability are non-negotiable.
The key facts
6 to knowClaude Science beta launched June 30, 2026
Multi-agent architecture: coordinating agent + domain specialists + reviewer agent
Every figure ships with exact code, environment, and full message history
Manages compute across local machines, HPC over SSH, and Modal
Integrates with 60+ databases + NVIDIA BioNeMo skills
Targets genomics, proteomics, and cheminformatics use cases
Go to the source
MarkTechPostmarktechpost.com
Publisher excerpt: Anthropic released Claude Science in beta on June 30, 2026. The app runs on existing Claude models. A coordinating agent delegates to domain specialists, a reviewer agent flags and corrects citations and numbers, and every figure ships with its exact code, environment, and full message history. It…