Run agents securely
Run an approved agent in an isolated microVM with governed authority.
Explore this feature →AIrspace / Images & workers
Trust the software and the machine that runs it
Registry and worker controls help establish what may run and where it is suitable to run.
What this means for your team
- Use artifact signatures, scan evidence, software inventories and provenance in release decisions.
- Keep publishing and independent approval separate where governance requires it; record authorized exceptions.
- Enroll supported hosts with their own identities and approved runtime posture.
- Manage placement, host state, upgrades and compatibility using supported fleet controls.
A practical example
An image approval does not automatically authorize every user or every host to launch it.
How it works
Select a step to read its explanation
- Prepare an agent image: the packaged operating system and software the agent will use. Record the available details about where it came from and what it contains so reviewers can make an informed decision.
- Review available evidence, such as signatures, security-scan results, the software inventory and where the image came from. These checks help the organization decide whether the image meets its release policy.
- When the organization requires it, another authorized person reviews the image before release. Any approved exception is recorded so a later reviewer can understand the decision.
- Choose an enrolled worker: a supported cloud VM, on-premises server or other host that will run the agent. Its security configuration and compatibility must satisfy the image’s requirements.
- At launch, AIrspace checks the relevant release and host authority again. This connects an approved image to a suitable host rather than assuming every image may run everywhere.
1 / 5
This example illustrates the journey. Select any step to explore it at your own pace.
Explore more AIrspace features
Model, tool & peer gateways
Control which models, tools and peer agents a run may reach.
Explore this feature →Live sessions & recordings
Follow a live run and review its recording with the right access.
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 →