Topic starter
24/06/2026 7:24 pm
TL;DR: The core issue is that agentic systems break the assumption that identity, context, and execution stay in a single, reviewable flow, and Agent Gateway extends AI governance from LLM and MCP traffic into agent-to-agent communication, giving enterprises policy enforcement, observability, and audit logging across the full AI data path, according to Kong.
Editorial analysis by NHI Mgmt Group, based on content published by Kong: “Kong Agent Gateway Is Here”.
Key questions
Q: How should security teams govern Agent2Agent communication in production?
A: Treat every agent as a governed non-human identity, not just a service integration.
Q: Why do agentic AI workloads increase governance risk compared with normal model calls?
A: Agentic workloads can chain decisions, retry automatically, and expand context across multiple calls.
Q: What are the signs that agentic AI governance is too focused on the agent and not the system?
A: Common signs include strong controls around individual identities but weak oversight of orchestration, action chaining, and inter-agent trust.
Practitioner guidance
- Define policy for agent-to-agent communication Document which agents may initiate, receive, or delegate tasks to other agents, and tie that policy to business workflow boundaries rather than just protocol endpoints.
- Require authenticated agent identity Bind every agent interaction to a verifiable identity so delegated tasks, tool calls, and downstream actions can be attributed to a specific machine actor.
- Correlate logs across the full AI data path Join API, event, MCP, LLM, and A2A records into one audit trail so investigators can reconstruct the sequence that led to a policy decision or data movement.
Bottom line: Agent-to-agent traffic expands the AI governance problem from single interactions to multi-step delegation chains across multiple systems.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
25/06/2026 4:41 am
Agent-to-agent governance is the missing control plane for multi-agent AI. The governance model that works for one LLM request and one response does not survive delegation chains, event-driven agents, and tool-calling loops. Once an agent can hand work to another agent, policy enforcement has to move from the edge of the model to the path between autonomous actors. Practitioners should read this as a governance shift, not a gateway feature.
A question worth separating out:
Q: What should teams do when agents can delegate work without human approval?
A: Teams should place controls at the delegation boundary and require explicit policy for which agents may call, hand off to, or consume output from other agents. Without that governance, approval-free delegation turns routine orchestration into uncontrolled downstream action.
👉 Read our full editorial: Kong Agent Gateway expands governance across agent-to-agent traffic