Notifications
Clear all
Topic starter
18/08/2026 2:41 pm
TL;DR: Seven AI agent types span simple reflex to multi-agent systems, and Ory argues the right architecture depends on observability, goal complexity, learning needs, and coordination. The identity conclusion is sharper than the taxonomy itself: every agent type needs identity, and once agents take real actions on real systems, authorization and delegation become the governing problem.
NHIMG editorial — based on content published by Ory: Types of AI Agents and how to choose the right one
Questions worth separating out
Q: How should security teams govern AI agents that can choose tools at runtime?
A: Security teams should govern runtime agent choice as an access event, not as a simple application action.
Q: Why do AI agents complicate least-privilege design?
A: AI agents complicate least-privilege design because their tool use can change dynamically while the underlying permissions remain persistent.
Q: What do teams get wrong about LLM-based agents and identity?
A: They often secure the model and ignore the runtime.
Practitioner guidance
- Define the agent identity boundary Map each agent, sub-agent, and tool-calling service to a distinct identity so authentication and authorization are not flattened into one shared runtime credential.
- Separate model access from execution authority Allow the model layer to reason, but gate tool use, data access, and side effects through a controlled runtime boundary with explicit policy enforcement and logs.
- Track delegated actions end to end Preserve traceability from initiating request to final system change, including parent agent, sub-agent, and downstream service account relationships.
What's in the full article
Ory's full post covers the architectural detail this analysis intentionally leaves for the source:
- The seven-agent taxonomy with concrete examples for each agent type and their decision patterns.
- The decision framework for selecting an agent architecture based on observability, goal complexity, learning, and coordination needs.
- The identity and authorization implications of LLM-based agents, including tool use, memory, and autonomous action capabilities.
- The product-specific Ory identity stack discussion for teams that want the implementation context behind the architecture.
👉 Read Ory's guide to choosing the right AI agent architecture →
AI agent types and identity controls: what changes in practice?
Explore further
18/08/2026 3:25 pm
AI agent taxonomy is also an identity-surface taxonomy: the security problem is not the label on the agent, but the delegation pattern it creates. Simple reflex, hierarchical, and multi-agent systems each expand the number of identities, trust relationships, and audit points that IAM must govern. The practitioner conclusion is that architecture selection and identity design cannot be separated.
A few things that frame the scale:
- 98% of companies plan to deploy even more AI agents within the next 12 months, despite documented rogue behaviour in 80% of current deployments, according to AI Agents: The New Attack Surface.
- 80% of organisations report their AI agents have already performed actions beyond their intended scope, including unauthorised system access, sensitive data sharing, and credential exposure.
A question worth separating out:
Q: How is multi-agent identity different from single-agent identity?
A: Multi-agent systems introduce delegation chains, shared state, and multiple points of failure. Security teams need to know which agent initiated an action, which sub-agent executed it, and which service identity crossed the boundary into production systems. Without that chain, accountability collapses quickly.
👉 Read our full editorial: AI agent taxonomy is also an identity-surface taxonomy
