Lakera Guard
for LuumenAI
Screen AI traffic against Lakera Guard policies, and change those policies with approval
Connect Lakera Guard and your agent can screen a prompt or response against the policy that actually applies, read a project's detector configuration, and see per-detector confidence scores without an aggregate verdict. Policy and project changes are previewed first and sent for approval before anything is written. Luumen authenticates with an API key.
The Lakera Guard toolbox
10 tools: 4 read, 6 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadEvaluate DetectorsEvaluate content and return one confidence result per configured detector without producing an aggregate flagging decision or Guard screening log.
- ReadGet PolicyRetrieve an Enterprise Lakera policy by ID, including its detector configuration, custom guardrails, version, and assigned projects.
- ReadGet ProjectRetrieve an Enterprise Lakera project by ID, including its assigned policy, metadata, and detect-or-flag action.
- ReadScreen ContentScreen the latest LLM or agent interaction with Lakera Guard and return the policy decision.
- WriteCreate PolicyCreate an Enterprise Lakera policy with built-in detectors and/or custom guardrails. Approval by default
- WriteCreate ProjectCreate an Enterprise Lakera project, optionally assigning a policy, metadata, and detect-or-flag action. Approval by default
- WriteDelete PolicyPermanently delete an Enterprise Lakera policy by ID. Approval by default
- WriteDelete ProjectPermanently and irreversibly delete an Enterprise Lakera project by ID. Approval by default
- WriteUpdate PolicyReplace an Enterprise Lakera policy's complete configuration and create a new policy version. Approval by default
- WriteUpdate ProjectUpdate an Enterprise Lakera project by ID. Approval by default
One prompt, start to finish
What a governed Lakera Guard run looks like inside Luumen.
Questions
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — create policy, create project, delete policy, delete project, and more — is shown as a plan and requires approval by default, including the 2 actions classified as destructive. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to Lakera Guard — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Often connected alongside
All integrations
OktaAccess and posture from Okta, with approval on every change.
Microsoft Entra IDAccess and posture from Microsoft Entra ID, with approval on every change.
Auth0Access and posture from Auth0, with approval on every change.Ping IdentityAccess and posture from Ping Identity, with approval on every change.Put Lakera Guard to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.