Notifications
Clear all
Topic starter
10/06/2026 12:16 am
TL;DR: Autonomous AI agents make sequential tool calls, preserve session context, and delegate work in ways traditional API gateways were never designed to govern, according to Pomerium. That shift means tool-level authorization, delegation tracking, and auditability become core identity controls, while assumptions built for static request flows break down.
NHIMG editorial — based on content published by Pomerium: What Is an Agentic Gateway? Definition, Architecture, and Why It's Different from an API Gateway
Questions worth separating out
Q: How should security teams govern AI agents that call multiple tools in one workflow?
A: Security teams should govern multi-tool agent workflows with tool-level authorisation, session context, and a complete audit trail.
Q: Why do API gateways fall short for autonomous agent governance?
A: API gateways fall short because they treat each request as independent and do not model conversation flow, delegation, or the business meaning of a tool call.
Q: What breaks when an agent can delegate work to another agent?
A: When one agent delegates to another, the accountability chain becomes part of the security problem.
Practitioner guidance
- Map tool semantics before building policy Inventory agent-exposed tools, classify each by business effect, and write authorisation rules against the tool name and parameters rather than the HTTP route.
- Carry session context through delegation chains Require the control plane to preserve who initiated the task, which steps have already run, and what authority was transferred to downstream agents or services.
- Treat agentic gateways as part of the identity stack Place policy evaluation, short-lived assertions, and audit logging in the path between agents and tools so every invocation is attributable.
What's in the full article
Pomerium's full blog covers the operational detail this post intentionally leaves for the source:
- Code-level request flow examples showing how an agentic gateway mints and forwards short-lived identity assertions.
- A side-by-side comparison table of API gateways, AI gateways, and agentic gateways for implementation teams.
- Step-by-step session context handling for multi-step agent workflows, including delegation and audit logging.
- Deployment examples showing how the gateway fits between agents, tools, and downstream services.
👉 Read Pomerium's analysis of agentic gateways, tool-level authorization, and AI agent governance →
Agentic gateways for AI agents: what IAM teams need to know?
Explore further
11/06/2026 1:59 am
Agent governance fails when identity control stops at the API boundary. Agentic systems do not just call endpoints, they sequence actions, retain state, and decide what to do next based on prior outcomes. That means the control point must move from request acceptance to tool-level authorisation and session-aware enforcement. Practitioners should treat the gateway as part of the identity plane, not only the network plane.
A few things that frame the scale:
- 91.6% of secrets remain valid five days after the targeted organisation is notified, showing a critical gap in remediation procedures, according to the Ultimate Guide to NHIs.
- Only 5.7% of organisations have full visibility into their service accounts, which means many identity programmes still cannot see the full non-human estate, according to the Ultimate Guide to NHIs.
A question worth separating out:
Q: What is the difference between an AI gateway and an agentic gateway?
A: An AI gateway manages model interactions such as token use, routing, and observability. An agentic gateway controls what the agent can do with the model’s output by enforcing tool-level authorisation, session context, and delegation rules. The two are complementary, but they solve different governance problems.
👉 Read our full editorial: Agentic gateways and why API gateways fall short for AI agents
12/06/2026 3:34 am
Agent governance fails when identity control stops at the API boundary. Agentic systems do not just call endpoints, they sequence actions, retain state, and decide what to do next based on prior outcomes. That means the control point must move from request acceptance to tool-level authorisation and session-aware enforcement. Practitioners should treat the gateway as part of the identity plane, not only the network plane.
A few things that frame the scale:
- 91.6% of secrets remain valid five days after the targeted organisation is notified, showing a critical gap in remediation procedures, according to the Ultimate Guide to NHIs.
- Only 5.7% of organisations have full visibility into their service accounts, which means many identity programmes still cannot see the full non-human estate, according to the Ultimate Guide to NHIs.
A question worth separating out:
Q: What is the difference between an AI gateway and an agentic gateway?
A: An AI gateway manages model interactions such as token use, routing, and observability. An agentic gateway controls what the agent can do with the model’s output by enforcing tool-level authorisation, session context, and delegation rules. The two are complementary, but they solve different governance problems.
👉 Read our full editorial: Agentic gateways and why API gateways fall short for AI agents
