AI holds the potential to dramatically speed up scientific discovery and the development of healthcare interventions. Since launching life sciences efforts last fall, Anthropic has worked to improve model capabilities, build connections to the scientific ecosystem via MCPs and skills, and establish partnerships to realize this potential.
Anthropic has now introduced its most significant expansion of these efforts: Claude Science, an AI workbench designed for scientists. Claude Science is an application that integrates the tools and packages researchers most commonly use, produces auditable artifacts, and provides flexible access to computing resources.
What Is Claude Science
Scientific research is often tedious. Researchers must work across dozens of databases, each with its own schema, deal with file formats requiring bespoke data pipelines and viewers, and switch between a roster of tools: PubMed, Jupyter, R, a cluster terminal, and more.
Claude Science brings these fragmented tools into a single research environment where scientists can conduct all stages of their work. It helps analyze literature and execute multistep research, produces detailed artifacts, and lets users iteratively refine figures and manuscripts until they're ready for publication. Every output carries an auditable history of how it was made, enabling validation and reproduction of results. Like a Jupyter Notebook, Claude Science can be accessed wherever researchers already work-locally on macOS or Linux, or on a remote machine over SSH or with an HPC login node.
Users interact with a generalist coordinating agent that has access to over 60 curated skills and connectors pre-configured for genomics, single-cell analysis, proteomics, structural biology, cheminformatics, and more. These agents can spin up additional agents and engage with specialist agents created by users. A reviewer agent checks citations and calculations, flagging and correcting errors.
Claude Science is being released in beta for Claude Pro, Max, Team, and Enterprise users, with ongoing refinement planned as user feedback is collected.
How It Works
Rich scientific artifacts, fully reproducible. Scientific research is inherently visual, so Claude Science generates figures and manuscripts alongside the code that created them. It natively renders rich scientific artifacts, including 3D protein structures, genome browser tracks, chemical structures, and more. Users can chat with the agent about any detail, annotating figures and manuscripts in-line so the agent knows what to address to make them publication-ready.
When it generates a figure, Claude Science includes the exact code and environment that produced it, a plain-language description of how it was created, and the full message history. This allows users to understand the inputs, making the work easier to validate and reproduce even months later. Users can ask Claude Science to make edits to figures in plain language-removing gridlines, for example, or changing an axis to log scale-and the agent will edit its own code.
Manages compute and scales on demand. Large analyses-folding a protein, for example, or running a genomics pipeline over a massive dataset-often require researchers to shift focus to setting up a computing job, waiting while it's sent to a cluster, checking whether it succeeded or failed, and pulling results back. Claude Science handles this process automatically. It drafts a plan, asks before reaching new resources, and lets users review or revoke any decision before writing and submitting the job to existing computing resources (an HPC cluster over SSH, or a Modal account for compute on demand), scaling the analysis from a single GPU to hundreds as needed.
Because its agents work inside a running session that holds context in memory, even massive datasets only need to be loaded once. It runs on a lab's own infrastructure-a laptop, Linux box, or HPC login node-so large or sensitive datasets never have to leave the systems they're already on, and only the context needed for each step of the analysis is sent to Claude. As the pipeline runs, a reviewer agent inspects the outputs, flagging incorrect citations, untraceable numbers, and figures that don't match their underlying code, and self-correcting as it goes. Users can fork the session at any point to compare two approaches without losing the original thread.
Domain-ready on day one. Scientific knowledge is scattered across hundreds of specialized sources. In biology, for example, relevant data might sit across resources such as UniProt, PDB, Ensembl, Reactome, ClinVar, ChEMBL, GEO-each with its own schema and query language-as well as in journals and preprint servers, and domain-specific open models. When a user asks Claude Science a question in plain language, specialist agents query and synthesize across all of these sources so the user doesn't have to navigate them individually. Claude Science uses the skills in NVIDIA's BioNeMo Agent Toolkit to connect natively to the life sciences models and libraries in BioNeMo, including Evo 2, Boltz-2, and OpenFold3.
Scientists who already have models, datasets, and pipelines they trust can connect those to Claude Science as well, saving any pipeline as a reusable skill or accessing a lab's preferred tool using a connector, with future sessions inheriting them automatically. This customizability allows access to Claude, proprietary data, and validated tools all in one conversation. Claude Science benefits from Anthropic's partners' specialized expertise and platforms, while more scientists reach their tools through Claude.
What Scientists Are Doing with Claude Science
Over the past few months, researchers have worked with Claude Science in beta for tasks like single-cell RNA sequencing analysis, CRISPR screen design, protein structure prediction, cheminformatics, and more.
Manifold Bio, which designs tissue-targeting medicines that home to a specific organ or cell type, used Claude Science to nominate targets for its latest experiments. For each tissue and target, Claude Science assessed surface expression, trafficking, and safety, ranking candidates against criteria Manifold had learned from its own internal proprietary data. Manifold noted that what set Claude Science apart from a general coding assistant was its ability to do this end-to-end, gathering the right data and applying the right judgment with the context of past programs built in.
Jérôme Lecoq, a neuroscientist at the Allen Institute, used Claude Science to build a multi-agent "computational review template" comprising about 20 custom skills geared towards writing long-form reviews. The sub-agents read through thousands of papers, pulling the central claim and key quantitative findings and storing them in an evidence state database. Then the pipeline constructs a narrative arc, writing the review section by section and delegating each to its own specialized sub-agent. Within each section, dedicated agents generate quantitative cross-study figures directly from the evidence database. A key component of the workflow, enabled by Claude Science, is the use of actor-critic pairs: one agent creates content while a separate reviewer agent evaluates it for accuracy and citation fidelity. Before Claude Science, it could take Lecoq's team as many as two years to write such a review. He now has about 10 reviews, many exceeding 100 pages, with citations checked by reviewer agents.
Stephen Francis, an associate professor and epidemiologist at the UCSF Brain Tumor Center, has used Claude Science to support studies on the molecular epidemiology of glioma. His lab investigates the genetic basis for how thousands of small-effect germline variants combine to shape individual susceptibility. Francis said the app has dramatically accelerated the analysis, enabling comprehensive germline workups across multiple approaches in roughly one-tenth the time it previously took. His group independently validated Claude Science's results, confirming that it can produce both rapid and robust analyses.
Getting Started with Claude Science
The Claude Science app is available in beta on macOS and Linux for Pro, Max, Team, and Enterprise plans.
Team and Enterprise users will need their admin to enable Claude Science. A Team plan offering discounted seats is available for active scientific labs at academic institutions and nonprofit research organizations; learn more here.
Anthropic is also supporting up to 50 Claude Science AI for Science projects, providing up to $30,000 in credits. Modal will also provide up to $2,000 in compute for select projects. Anthropic is looking for projects that span domains and explore the boundaries of science, with an early focus on biology and biomedical research. Applications are open through July 15, 2026, with award notifications sent out by July 31. Projects will run from September 1 to December 1, 2026-apply here.
To stay up-to-date on product announcements, provide feedback, and learn from others in the Claude Science community, join the AI for Science Discourse community.
Get started with Claude Science at claude.com/science.