Feature

Automated tasks, safely executed.

Agents run automated tasks in a secure, isolated environment with no access to your live systems. Analyse data, generate reports, and transform files — all inside a controlled workspace.

What you get

Automated task execution

Agents can run automated tasks as part of their work. Data analysis, file processing, report generation — if you can describe it, an agent can do it.

Safe and isolated

Every task runs in a secure, isolated environment with no access to your live systems. The workspace is set up for each run and cleaned up when it finishes.

Smart task handling

Agents pick the right approach for the job and execute tasks in a controlled environment. You describe the goal — the agent figures out the rest.

Captured results

Everything an agent produces — outputs, generated files, and status updates — is captured and stored as part of the run log for you to review.

Persistent file access

Agents can read from and write to your project files. They can process files from previous runs or save results for future ones.

Agent-driven

The agent decides when to run a task, what to do, and how to interpret the results. Task execution is part of the agent's toolkit, not a separate workflow.

How it works

Enable the task execution permission on an agent so it can run automated tasks during its work.

During a run, the agent determines what tasks to perform and executes them in a secure, isolated environment.

Tasks run with access to project files but no access to your live systems or external services you haven't authorised.

Results are captured automatically and the agent uses them to continue its work or produce reports and artifacts.

Ready to get started?

Set up your first AI agent in minutes. Connect your tools, tell it what to do, and let it run.