External pipelines · RISE project catalogue
Claude Science
Anthropic's AI workbench for researchers ("Claude Code for science"), announced 2026-06-30: a desktop app (macOS/Linux) in which a generalist coordinating agent with 60+ curated skills and connectors spawns specialist agents to run literature analysis, database queries, multistep data analyses, figure iteration, and manuscript drafting, with compute spanning the local machine, HPC clusters via SSH, and Modal GPUs. Covers a broad slice of the RISE pipeline from literature work through manuscript refinement, in the same big-lab workbench layer as Prism and Google Co-Scientist.
Where it sits
left: what it builds on · right: what builds on it · pale: exampleContributed by Anthropic
How studies reach it
No published study reaches it yet.
Disciplines it reaches
No study reaches it yet.
Solid: published studies. Light: examples.
Computed from the records on this site: what each study, template and specialist names as used, which study extends which, and who contributed what. 0 studies in total.
What it does
Auditable-artifact design: every figure ships with a reproducibility package (exact code, computational environment, plain-language methodology, full message history), and a background reviewer agent flags incorrect citations, untraceable numbers, and figures that don't match their underlying code as work progresses. Deepest pre-configured life-science stack of any big-lab offering — 60+ databases (UniProt, PDB, Ensembl, ChEMBL), NVIDIA BioNeMo Agent Toolkit, Evo 2, Boltz-2, OpenFold3 — backed by a grants program of $30,000 in credits for up to 50 AI-for- science projects (applications closed 2026-07-15).
- Focus
- end-to-end
- Inputs
- research-task-prompt, user-datasets, custom-skills-connectors
- Outputs
- analysis-artifacts, reproducibility-packages, figures, manuscript-drafts
- Architecture
- multi-agent, tool-use, persistent-memory, iterative-loop, artifact-versioning
- Maintained by
- Anthropic
- Started
- 2026
Description
Data model- Discipline
- General
- Method family
- not specified
- Design
- not specified
- Research stage
- Literature discoveryLiterature synthesisResearch designData acquisitionData analysisCode generationDraftingRevision and editing
- Contributors
- Anthropic
- Usage
- not used in published research yet
- Source
- RISE project catalogue · projects/landscape · @4c17bae
- Record
- pipeline:claude-science · JSON
Solid tags are declared by the source or mapped from its terms; dashed tags are inferred by a published rule. Hover a tag for its provenance.
Bring it into the standard
A pipeline built outside E2ER can meet the standard by describing its steps as a template, attaching the floor of checks and publishing evaluation records. Its authors keep ownership and credit.