Science, with you at the center

Scientific analysis
agents built for
researchers.

Work directly with your data. Keep scientific computation under your control.

Lab Agent Works develops specialized AI-assisted tools that bring biological questions and computational analysis closer together. Our first product is scRNA-agent, for single-cell RNA-seq analysis.

A CLOSER LOOK. A CLEARER QUESTION.
Biological complexity. Human direction.Illustrative atlas · Not research data
Local scientific computation Your data, under your control Guided by science. Directed by you.

01 / Meet the first agent

From Lab Agent Works · Coming soon

scRNA-agent

Single-cell RNA-seq
analysis for biologists.

Your biological questions shouldn’t have to wait at the command line.

scRNA-agent helps you work from raw or processed single-cell data through quality control, annotation, downstream analysis, figures, and reports.

A local scientific workspace. Specialized protected guidance. You stay involved in the decisions that matter.

Get to know scRNA-agent
01

Ask biological questions

Explore your data with project-aware AI assistance and structured scientific guidance.

02

Run the analysis locally

Use local R and Python environments while raw scientific data stay on your computer.

03

Keep a traceable record

Review figures, reports, and analysis artifacts in a project you control.

02 / Local by design

Your data stay close. Your analysis moves forward.

Raw matrices stay on your computer, where R and Python run the analysis. The protected Core provides maintained workflows and scientific guidance without needing your raw dataset.

On your computerLOCAL WORKSPACE
01

Your scientific data

Raw matrices & processed inputs

02

scRNA-agent workspace

Your question, context & decisions

03

R / Python analysis

Local scientific computation

04

Project outputs

Figures, tables, reports & provenance

Raw matrices stay on your computer. Scientific computation runs locally.

YOUR MODEL ACCESS

Your own AI provider supports reasoning and execution. Prompts and shared project context may leave your computer and are subject to that provider’s policies.

Explore the architecture

03 / From question to insight

A framework for the way you explore.

Move through single-cell analysis with guidance at each stage, and room to revisit decisions as the biology becomes clearer.

01

Start with the data

  1. Data intake
  2. Quality control
  3. Filtering
02

Assess & prepare

  1. Doublet detection
  2. Ambient RNA handling
  3. Dimensionality reduction
03

Resolve the biology

  1. Batch / integration assessment
  2. Clustering
  3. Annotation
04

Explore & communicate

  1. Differential analysis
  2. Pathway analysis
  3. Figures and reports

An adaptable framework, not a fixed pipeline. The steps and methods depend on the dataset and biological question.

04 / Work you can build on

More than an answer. A scientific record.

Keep useful outputs connected to the work behind them.

Figures & tables

Visual summaries and tabular results for review and further exploration.

figures/ · tables/

Analysis & provenance

Analysis artifacts, parameters, and records that keep the work traceable.

artifacts/ · provenance/

Summaries & reports

Scientist-facing summaries alongside technical reports for deeper inspection.

summaries/ · reports/

Illustrative output categories. Contents depend on the analysis performed.

05 / Purpose-built assistance

Scientific tools. Thoughtfully connected.

01

Guided analysis workflow

Move from a biological question to a structured analysis, with decisions you can review.

02

Local R / Python execution

Run scientific tools in local environments, close to your data.

03

Project-aware AI assistance

Work with an agent that uses your project context to support the next step.

04

Reference-resource handling

Acquire supported reference resources automatically when an analysis needs them.

05

Reproducible figures and reports

Keep generated figures and reports connected to the analysis that produced them.

06

Versioned analysis guidance

Use maintained guidance with versions that can be traced across your work.

Local-first data handling

Your scientific data stay on your computer.

Raw matrices stay local. Project files remain under your control. The protected Core provides guidance without needing your raw dataset.

Our privacy model

Your next biological question

Closer to your data.
Further in your research.

Meet scRNA-agent, the first tool from Lab Agent Works.

View scRNA-agent availability