ReAct AI agents and gateway policy: what IAM teams need to know

TL;DR: Agent decision paths can outgrow the policy assumptions embedded in conventional IAM and API governance, according to Kong’s walkthrough of how ReAct agents route prompts, tools, and model calls through an AI gateway, with architecture spanning LangGraph, multi-model selection, and observability layers. The central issue is that agent decision paths can outgrow the policy assumptions embedded in conventional IAM and API governance.

NHIMG editorial — based on content published by Kong: How to Strengthen a ReAct AI Agent with Kong AI Gateway

Questions worth separating out

Q: How should security teams govern AI agents that can route to multiple models and tools?

A: Security teams should govern AI agents through a control plane that can enforce model access, tool access, logging, and policy decisions outside the prompt.

Q: Why do ReAct agents complicate traditional IAM and API security models?

A: ReAct agents complicate traditional IAM because they make decisions during execution, not only at provisioning time.

Q: What breaks when agent policy lives only in prompts or application code?

A: When policy lives only in prompts or application code, it becomes easy to bypass, hard to audit, and fragile across model changes.

Practitioner guidance

• Inventory every model and tool dependency Create a complete list of models, external functions, vector stores, and observability endpoints that the agent can reach.
• Enforce policy outside the agent prompt Move access rules, routing constraints, and logging requirements into the gateway or surrounding control plane.
• Trace every reasoning loop hop Record prompt input, model selection, tool invocation, response handling, and failure state for each agent run.

What's in the full article

Kong’s full blog post covers the implementation detail this post intentionally leaves for the source:

• Step-by-step ReAct agent code and prompt structure used in the example architecture
• Kubernetes and Konnect deployment commands for the data plane and control plane
• Minikube, Redis, Ollama, and observability setup details for the lab environment
• The blog series roadmap for extending the agent from a simple ReAct loop to LangGraph and multi-LLM patterns

👉 Read Kong’s walkthrough on strengthening a ReAct AI agent with Kong AI Gateway →

ReAct AI agents and gateway policy: what IAM teams need to know?

Explore further

View Full Forum →  |  NHI Foundation Course →