The Findings Workflow: An agentic, collaborative, provenance-tracked framework for scientific data analysis with Claude Code
- 1University of Washington
Abstract
Scientists presented with quantitative data often face two related problems: confidence that an analysis is statistically and computationally correct, and provenance sufficient to reproduce the resulting figures and conclusions. Large language models (LLMs) can make sophisticated analyses accessible through a collaborative, conversational interface, but unstructured use can worsen both problems by producing plausible but incorrect results and obscuring the steps that produced them. Here we present the Findings Workflow, a free, open-source Claude Code plugin designed to retain the flexibility of conversational LLM-assisted analysis while placing it within a structured, verifiable, and reproducible environment. The workflow uses staged, gated progression to ensure the science, metadata, and data are understood and tested data loaders are built before downstream analysis begins. Specialized subagents perform statistical analysis, programming, visualization, research, reporting, and validation, with independent review incorporated throughout. The plugin also provides vetted analysis templates, conventions, and methodological guidance that serve as trusted sources of opinion when deciding how analyses should be performed. Scientists remain actively involved throughout, exploring their data and directing the analysis through natural-language conversation, while the workflow supplies structure, verification, and persistent state around that collaboration. Findings are recorded automatically together with the data, code, methods, figures, and provenance needed to reproduce them. We demonstrate the workflow with a worked example that reproduces central findings from a published plasma extracellular vesicle proteomics dataset examining Alzheimer's disease (Mag-Net). Together, these features are designed to make LLM-assisted scientific analysis easier to trust, inspect, and reproduce without sacrificing its conversational and exploratory nature.
Related
- From Tool State to Scientific Action: Auditing Decision Provenance in Biomedical Research Agents
- A Scientific Claim Stability Framework for Evaluating MRI Morphometry Pipelines
- Clinical trial data transparency should match data access to scientific purpose: a tiered framework for reproducibility and reuse
- An end-to-end in silico framework for truth-based validation and regression testing of clinical genome sequencing pipelines, from simulated reads to reportable findings
- Macrophages in non-infectious uveitis: cell origin, disease stage, evidence provenance, and therapeutic maturity
BibTeX
@misc{riffle2026findings,
title = {{The Findings Workflow: An agentic, collaborative, provenance-tracked framework for scientific data analysis with Claude Code}},
author = {M. Riffle and A. Zelter and M. J. MacCoss},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.28.762630},
url = {https://www.biorxiv.org/content/10.64898/2026.10.28.762630v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - The Findings Workflow: An agentic, collaborative, provenance-tracked framework for scientific data analysis with Claude Code
AU - M. Riffle
AU - A. Zelter
AU - M. J. MacCoss
PY - 2026
DA - 2026/10/28
PB - bioRxiv
DO - 10.64898/2026.10.28.762630
UR - https://www.biorxiv.org/content/10.64898/2026.10.28.762630v1
AB - Scientists presented with quantitative data often face two related problems: confidence that an analysis is statistically and computationally correct, and provenance sufficient to reproduce the resulting figures and conclusions. Large language models (LLMs) can make sophisticated analyses accessible through a collaborative, conversational interface, but unstructured use can worsen both problems by producing plausible but incorrect results and obscuring the steps that produced them. Here we present the Findings Workflow, a free, open-source Claude Code plugin designed to retain the flexibility of conversational LLM-assisted analysis while placing it within a structured, verifiable, and reproducible environment. The workflow uses staged, gated progression to ensure the science, metadata, and data are understood and tested data loaders are built before downstream analysis begins. Specialized subagents perform statistical analysis, programming, visualization, research, reporting, and validation, with independent review incorporated throughout. The plugin also provides vetted analysis templates, conventions, and methodological guidance that serve as trusted sources of opinion when deciding how analyses should be performed. Scientists remain actively involved throughout, exploring their data and directing the analysis through natural-language conversation, while the workflow supplies structure, verification, and persistent state around that collaboration. Findings are recorded automatically together with the data, code, methods, figures, and provenance needed to reproduce them. We demonstrate the workflow with a worked example that reproduces central findings from a published plasma extracellular vesicle proteomics dataset examining Alzheimer's disease (Mag-Net). Together, these features are designed to make LLM-assisted scientific analysis easier to trust, inspect, and reproduce without sacrificing its conversational and exploratory nature.
ER -