liveBook · Manning

Policy engine

As explained in AI Governance

A policy engine is a service or software component that evaluates requests against defined policies and returns decisions such as allow or deny.

An agent manipulated by prompt injection may attempt an unauthorized tool call. A policy engine places the authorization decision outside the agent’s reasoning: it checks the proposed action against written rules before execution and returns an allow or deny decision. section 3.8 section 4.8.8

The orchestration layer queries the engine before invoking a tool. Policies describe which roles may perform actions on resources, and the decision can account for the requester, tool and circumstances. A denied action is stopped before it reaches the network. section 4.8.5 section 3.8

External authorization avoids scattering checks through agent code. Embedded logic can suffice for simple scenarios but becomes harder to audit as rules grow. Platform-native controls centralize management, though multicloud deployments may require duplicate configuration. section 4.8.5

Claims tool authorization

A claims assistant uses Cerbos to govern tool access. Customers and adjusters can read claims they own; adjusters can update status on assigned claims below $10,000. Larger claims require a separate approval path. section 4.8.5

Listing 4.1 Cerbos policy for ClaimAssist tool access .
resourcePolicy:
resource: "claims_tool"
rules:
- actions: ["read_claim", "get_status"]
effect: EFFECT_ALLOW
roles: ["customer", "adjuster"]
condition:
match:
expr: request.resource.attr.claim_owner == request.principal.id
- actions: ["update_status", "flag_for_review"]
effect: EFFECT_ALLOW
roles: ["adjuster"]
condition:
match:
all:
Of:
- expr: request.resource.attr.assigned_adjuster == request.principal.id
- expr: request.resource.attr.claim_amount < 10000

The policy listing shows how roles, actions and claim attributes combine in authorization rules. section 4.8.5

An allow decision does not establish that the agent was not manipulated, that the tool is trustworthy or that the overall workflow is safe. Pair authorization with agent identity, short-lived credentials and records of actions and accountability. section 4.8.5 section 3.8 section 4.8.8

How AI Governance covers it

How deep it goes
Explains external authorization workflows and configuration trade-offs, with a policy listing and explicit limits on what authorization establishes.
Examples
Uses a claims assistant’s role- and attribute-based Cerbos policy to restrict reads and status updates.
What you can do after
Apply tool authorization with Cerbos by expressing role and resource conditions and querying the engine before invocation.
How it connects
Connects tool authorization to policy as code, agent identity, short-lived credentials and prompt injection.

Also explained in

Compare how 4 books explain policy engine →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of AI Governance. The section links point to the parts of the book it draws on.