Skip to main content
Admins set these controls once, and every agent inherits them. Each row names where the setting lives and the page that covers it. Screenshots show sample data.

The controls

Admins can ask Omni to change most of these settings, from the Omni sidekick or an MCP client. Omni stays within your role, shows each change before and after, applies it only after you confirm, and records it in Audit log under your name.

Details

Each person turns these on for themselves in Settings > Security. There is no organization switch.
  • Two-step sign-in: Set up authenticator app adds a code from an app such as Google Authenticator or 1Password on top of the usual sign-in. Recovery codes > Create codes gives one-time codes for a lost phone. Once a person has an authenticator app, every xpander service refuses their session until they enter a code.
  • Passkeys: Add a passkey signs the person in with a fingerprint, face or device PIN, with no password or email code. Offered on xpander cloud and Hybrid. Air-Gapped offers only two-step sign-in (Air-Gapped access).
  • Admin reset: in Platform > Organization > Members & groups, a member’s card shows Two-step sign-in On or Off. For a member who has it on, Reset two-step sign-in in the row’s menu removes their authenticator app and recovery codes and signs them out everywhere. Their passkeys stay. A session they already have can keep working until its access token expires. The reset is recorded in the Audit log.
Skills registry admin page with Connect clients, Agent-built skills and Add item, and items with their type, source and setting

Platform > Agents > Skills registry: what agents and clients can call, each item's type, source and setting. Shown with sample data.

Agents can build custom functions, Markdown skills and API skills as drafts, test them and publish them here.
With no decision within the hold window (four hours by default, configurable), the action does not run and the run continues. A later decision can still approve a pending gated command. Every decision is recorded with the approver’s name, including self-approvals allowed for unattended agents.
Approvals page with Waiting for you and Decided lists

Settings > Approvals: Waiting for you and Decided. Shown with sample data.

Platform > Agents > Secrets stores every credential encrypted. Agents reference a secret, and the value is injected at the moment of use. An external vault (Azure Key Vault today) can be the source. Model provider keys live under Platform > AI governance > Models and follow the same rule.
Secrets page with Storage locations, Bulk add and Add secret, Type and Owner filters, and the list of secrets with their type, owner, location, access and last use

Platform > Agents > Secrets: names, location and access; values are never shown. Shown with sample data.

Every model call goes through the AI Gateway. Agents reach only the providers and models you configure in Platform > AI governance > Models, which shows the gateway’s Base URL, each provider’s key status (Connected or Needs a key) and who may use each model. A call to a provider with no key is refused with a message naming it. Every call is logged in Platform > AI governance > Logs.
Models page with Base URL and a Providers table showing Connected and Needs a key

Platform > AI governance > Models: the Base URL and each provider's key status. Shown on an Air-Gapped install, where the Base URL is http://llm-gw:4000. On a Hybrid install with the release name xpander, it is http://xpander-llm-gw:4000. Shown with sample data.

Budgets page with an overview and tabs for Groups, Members, API keys, Agents and End users

Platform > AI governance > Budgets: overview and spending limits by scope. Shown with sample data.

Manage access drawer with visibility options Private, Group and Org-wide

Manage access on an agent: private, a group, or the whole organization. Shown with sample data.

Next steps

Set budgets and blocks

Spending limits.

Set up single sign-on

Connect your identity provider.