The environment also decides which capabilities an Agent node can use. See What a node can do.
Browser
The Browser environment runs the workflow in a headless Chromium sandbox. Choose it when the work happens on the web:- filling forms and moving through web apps
- pulling structured content out of pages
- running deterministic browser automation
- mixing scripted steps with model-driven interaction
- Page structure — click, type and select by reading the DOM. This is the default.
- Scripts — deterministic JavaScript for precise, repeatable steps.
- Computer use — screenshot and coordinate actions, for pages the DOM cannot handle.
downloads/. See Workflow filesystem.
Linux
The Linux environment gives the workflow a full Linux desktop session in an isolated sandbox. Choose it when the work goes past the browser:- driving native desktop applications
- running terminal-driven work
- handling local files through desktop tools
- mixing browser and desktop steps in one execution
Windows
The Windows environment gives the workflow a Windows desktop session in an isolated sandbox. Choose it when the work depends on Windows-only software:- enterprise desktop tools
- vendor clients that ship for Windows only
- internal apps that need a Windows runtime
Windows workflows start after a demo with our team. Ask us at [email protected].
What every environment shares
The sandbox layout is identical in all three. Each execution mounts/home/agent with the same four directories — shared/, workspace/, downloads/ and uploads/. File handling and tool behaviour do not change with the environment. See Workflow filesystem.
Credentials, cookies and proxy settings come from the attached agent profile, whatever the environment.
What a node can do
Capabilities and the tools they unlock
Workflow settings
Where you choose the environment

