Skip to main content
This is in development. Details may change before it is available.
With the AI Gateway, your organization can send model traffic through Altrum before it registers any AI system: with an organization key, or with a person’s own key. Organization guardrails govern that traffic.

​
How they work

  • Open AI Gateway, then Guardrails. The page has the same eight guardrails as an AI system. See Guardrail types.
  • It works the way AI system guardrails do: a draft, Save draft, Apply as a numbered version, Test guardrails and Roll back under Versions. There is no Risks and controls tab, because the organization has no assessment.
  • Requests made with an organization key or a personal key are checked against the organization’s live version.
  • Requests made with an AI system’s key are checked against that AI system’s live version instead. If the AI system has none, its requests are not checked: the organization’s guardrails do not apply to it.
  • A key that nothing checks shows Unguarded next to Active in Virtual keys and on the AI system’s AI Gateway tab.
  • When an organization key is attached to an AI system, its next request uses the AI system’s guardrails.
  • Applying a version sends it to the AI Gateway. If the AI Gateway cannot be reached at that moment, the version is still live in Altrum, the screen says “Not yet sent to the AI Gateway. Altrum keeps trying.”, and Altrum keeps trying until it has.
Organization guardrails are configured by hand, and so have only versions set by hand. Suggestions from an assessment apply to AI systems only.

​
Who can change them

Owners and admins. Other members do not see the page.