Run agents securely
Run an approved agent in an isolated microVM with governed authority.
Explore this feature →AIrspace / Live sessions & recordings
Watch, intervene and review under authority
Live access and recordings make an Agent run observable to authorized people.
What this means for your team
- Open an authorized desktop session and use supported intervention controls.
- End a run through the control plane and retain lifecycle evidence.
- Record supported sessions with evidence integrity controls and governed viewing.
- Limit recording access because a recording may contain sensitive customer content.
A practical example
An approved recording viewer can inspect evidence; an unrelated operator does not gain standing recording access.
How it works
Select a step to read its explanation
- Establish the governed Agent run and the session context that an operator wants to inspect.
- Check that the viewer has authority for the requested run and viewing operation.
- Provide the supported live view or intervention controls without turning viewing access into unrestricted Agent authority.
- End the run or session through the control plane and retain its lifecycle evidence.
- Authorize recording access separately, since recordings may contain sensitive information.
1 / 5
This example illustrates the journey. Select any step to explore it at your own pace.
Explore more AIrspace features
Images & workers
Prepare approved agent images and connect the hosts that run them.
Explore this feature →Model, tool & peer gateways
Control which models, tools and peer agents a run may reach.
Explore this feature →AI Agent Session Recording Analyzer
Under Development
Investigate recorded agent sessions through evidence-linked findings, timelines and clips.
Explore this feature →Agent threat intelligence
Under Development
Correlate evidence from independent observers to investigate agent behavior.
Explore this feature →