Approach

How Gardener Works

01 / METHOD

Built for Real Biological Computing

Gardener is designed around the way modern biological analysis actually happens: data is large, compute is distributed, and decisions require expert judgment.

Instead of sending raw datasets into a cloud chatbot, Gardener separates reasoning, interaction, and computation into a privacy-preserving workflow.

02 / CORE PRINCIPLES

Our Approach

01
Reproducibility and Robustness
Compute where the data lives

Gardener treats HPC as the primary execution environment, not an afterthought. Datasets remain on the compute system where they belong, while the agent helps launch, monitor, and organize analysis jobs.

02
Accessibility
LLM, desktop GUI, and HPC each play a clear role

The workflow separates reasoning, interaction, and execution. The LLM assists with planning and coordination, the GUI keeps the user in control, and the HPC performs data-intensive computation without exposing raw data to the model.

03
Privacy
Built around rigorous dry-lab workflows

Gardener is built to work with established community pipelines such as nf-core. Instead of relying on ad hoc commands, analyses can be launched, recorded, and repeated through trusted workflow standards.

04
Scalability
Automation without replacing judgment

The agent helps with execution, record-keeping, and routine coordination, while biological interpretation and scientific decisions remain with the researcher.