Beyond RBAC

Roles answer who. Agents need why.

Why AI agents need access control that evaluates purpose, context and behaviour.

Kevin Keller · kevinkeller.org

Why it matters

RBAC can't see what an agent is doing with its access

  • For a human, purpose can be inferred from job function.
  • At step 47 of an autonomous chain, that inference breaks.
  • The access system knows the role, not the purpose, chain depth or agent type.
Can this agent invoke this tool on this data for this purpose?

A concrete example

Every tool call passes RBAC while the data walks out

  1. A support agent is asked to summarise a customer's tickets.
  2. A prompt injection in one ticket triggers export_customer_data.
  3. Then call_external_api sends the data out.

Same role, same permissions. The purpose changed and nothing noticed.

The idea

Evaluate context, not just identity

Attribute-based access control asks what the agent is doing, why, with what, and whether that makes sense right now.

Four attribute dimensions

A policy needs far more than a role

  • Agent identity: human principal, agent type, version, current tool
  • Request context: purpose, data classification, chain depth, prompt lineage
  • Environment: time, region, network path, regulatory regime
  • Behaviour: access pattern, velocity, data volume, escalation

Three decisions

The policy engine decides more than allow or deny

DecisionQuestion
Tool authorisationCan this agent call this tool, on this data, for this purpose, at this depth?
Inference routingCan this data go to this model?
Response transformationShould the result be masked, redacted or sampled for this purpose?

State of the industry

The pieces are shipping, but in silos

LayerStatus (March 2026)
Agent identity and delegationProduction
Tool authorisationProduction
Data access with agents as identitiesProduction
Purpose and intent classificationEmerging
Behavioural baselinesEarly
Unified policy engineEmerging

What's missing

The connective tissue between layers

  • No unified evaluation: no single engine sees tool, data, inference and behaviour at once.
  • No shared attribute schema: agent_type, chain_depth and purpose mean different things per vendor.
  • Enterprises map between incompatible models at every integration point.

The enterprise pattern

Centralised policy, federated enforcement

LayerOwner
Global policies, non-overridableCentre of Excellence: compliance, legal, CISO
Domain policies, extend but never weakenDomain owners
Enforcement point configurationPlatform teams
Audit and response across all pointsSecurity operations

Why now

Regulators ask what the AI does with its access

  • EU AI Act Article 9 expects governance beyond RBAC for high-risk systems.
  • DORA requires automated systems to operate within defined bounds.
  • "The agent has a role that can access the table" satisfies neither.

The takeaway

Three attributes, one deny decision, zero data leaked.

Read the full article

Kevin Keller · kevinkeller.org