Lab Agent Works.

How it works

Local computation. Connected scientific guidance.

Lab Agent Works separates the scientific workspace from the guidance that supports it. You work with your data locally, while specialized knowledge and workflows are maintained through the protected Core.

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.

Three parts, clear roles

Built around your working environment.

01

Your local workspace

Your data, R/Python environments, analysis artifacts, figures, and reports live on your computer.

02

Your model access

Use your own model authentication for reasoning and execution. Review the context sent to your provider and its data policies.

03

The protected Core

Connect to versioned workflows, scientific skills, reusable experience, account services, entitlement, and updates.

In practice / scRNA-agent

A guided process, with you in the loop.

Start with a biological question, review the analysis choices, run local tools, and inspect the outputs. Revisit earlier steps as your understanding develops.

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.

Scientific judgment remains essential.

Guidance helps you navigate methods; it does not validate every assumption or guarantee a result. Study design, quality assessment, and biological interpretation remain researcher responsibilities.

Explore scRNA-agent

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