Skip to main content

Overview

A Paladin agent can be assigned as a reviewer on any resource or group, just like a human reviewer or a service user automation. When a request is routed to the agent, Paladin investigates the request, gathers context from across your access graph and connected systems, and decides whether to approve, deny, or escalate. The agent’s reasoning, tool calls and actions are captured in the request, and every action is governed by the agent’s role and permissions.

What Paladin Evaluates

When a request is assigned to a Paladin agent, Paladin gathers organizational context from Opal and configured connectors:
  • Previous access requests and access history within Opal.
  • Tickets in your connected ticketing systems.
  • Discussions in your connected messaging systems, such as Slack.
  • Documents in your connected knowledgebases, such as Notion.
Paladin uses this context to evaluate against desired outcomes. By default, Paladin’s outcomes are:
  • Requester Understanding — understand who the requester is, their history, their work and their place in the organization.
  • Asset Understanding — understand what is being granted access to, the implications of granting access and any surrounding policy for this asset.
  • Temporal Understanding — does granting the requester access to this asset make sense right now given the gathered information on the requester and the asset?
  • Alternatives Analysis — if we do not grant this access, are there alternatives that the requester can use that are more appropriate?

Custom Outcomes

You can shape Paladin’s evaluation further by asking it to achieve additional outcomes when creating an agent. Each outcome has three fields:
FieldDescription
OutcomeWhat Paladin should achieve when it makes a decision.
EvaluationHow Paladin should check whether the outcome is met.
On FailureWhat Paladin should do if the outcome is not met.
For example, to enforce customer-specific data handling policies:
OutcomeEvaluationOn Failure
Customer data is highly sensitive and must follow customer-specific agreements.Search knowledge sources for customer-specific policies or agreements and apply them.Deny requests which do not follow customer policies.

Actions Paladin Can Take

Like any reviewer in Opal, a Paladin agent can:
  • Approve the request, advancing it to the next stage or granting access if it is the final stage.
  • Deny the request.
  • Escalate the request by taking no action, leaving the request open. Useful when more information is needed from the requester or a human reviewer.
Paladin’s reasoning for every action appears as part of the request, giving auditors and downstream reviewers a clear record of why the decision was made.

Configure Paladin as a Reviewer

  1. Create a Paladin agent using the Assigned to request trigger.
  2. Add the agent’s service user as an Automation reviewer in the resource or group’s approval flow.
  3. Decide how Paladin participates in the stage:
    • Sole reviewer: Paladin is the only reviewer on the stage and approves, denies, or escalates every request.
    • Advisory: Add Paladin alongside human reviewers using either:
      • A single stage, with a single human owner or reviewer, and Paladin, with ALL logic.
      • Multiple stages, with an initial Paladin-only stage followed by a human review stage.
  4. Submit a test request and review Paladin’s reasoning and decisioning.
Last modified on April 27, 2026