Technical agents
Agents that diagnose infrastructure — Linux, Windows, Kubernetes, storage and the network — with evidence from the machine itself.
Why has this service been failing since the last change?
The commands that ran on each host, their exit codes and output, and then the finding.
Government
Education
What a technical agent does
Infrastructure questions are answered by looking, not by reasoning from documentation. Was the service restarted, is the disk full, did the certificate expire, what changed in last night’s rollout. The work is collecting that evidence across many machines quickly, and being able to show it afterwards.
- Run the diagnostic on the machine rather than guessing from a description of it.
- Ask the same question of two hundred machines and get two hundred answers.
- Keep the raw evidence, so the finding can be checked and re-checked.
Those three run through the host workers themselves:
Every answer shows the exact commands that ran, their exit codes and output, per host.
Read-only execution policy is the default on every enrolled host; the full policy is an explicit, per-host choice.
The primitives it composes
An agent is a model, a set of approved skills, tools and a policy, applied to a scope.
A skill declares what it can and cannot do, the tools it needs, the paths it may read, and how it is evaluated.
Agents reach your systems through approved connectors — APIs, databases, applications — each with its own permissions.
Changes wait for human approval before they run.
The hosts and skills behind it
Every agent in this pack works through the same host execution: the agent object carries a name, a scope and a policy, and the execution and the evidence sit underneath it.
A host joins the fleet with one install command and an enrollment token; revoking the host unpairs it.
Skills come from a signed vendor catalogue or your own uploads, and can be enabled or disabled per workspace.
Bring one question of your own.
Request a demo