Kong reveals ‘agent-to-agent communication’ critical for Asian enterprises

Author: Ruiguo Lai, regional sales director Asia, Kong.

Agentic AI is experiencing rapid advancements in the APAC region. But with evolution also comes great risk. Without unified visibility and control of Agentic AI, security gaps emerge, costs spiral, and compliance becomes impossible to verify. According to



Kong Inc.



, a leading developer of API and AI connectivity technologies, as enterprises in APAC move AI from experimentation to production, they face a growing connectivity and governance challenge.

Organisations do not route prompts to a single LLM, but orchestrate complex systems where agents communicate with external tools via MCP and collaborate with other agents using emerging agent communication protocols, like Agent to Agent (A2A). Most solutions address only a fraction of this traffic, leaving enterprises to stitch together multiple point solutions or accept blind spots in their AI infrastructure.

Empowering safer and clearer pathways for LLM traffic

“When enterprises started experimenting with LLMs,



the governance challenge



, while still difficult, was relatively contained once you had an AI Gateway for LLM traffic. You had a request going to a model, a response coming back, and a gateway in between to enforce policy. With the right solutions, this becomes manageable pretty quickly,”



said



Alex Drag, head of product marketing at Kong.

“That world is now over. Today’s agentic architectures look nothing like that. Agents are calling tools via



MCP



. Agents are delegating tasks to other agents via A2A. These other agents are producing and consuming event streams. Data flows in every direction, often with little to no human in the loop, and often with no visibility into what’s actually happening.”

Kong



recently announced



a new solution,



Kong Agent Gateway



in the AI Gateway 3.14 release. According to Kong, this launch positions Kong AI Gateway as the only gateway solution on the market to support advanced LLM, MCP, and agent-to-agent (A2A) use cases.

“This is the problem we built Kong Agent Gateway to solve. And now Agent Gateway is GA and prod-ready as of AI Gateway 3.14,” Drag said.

Transition from experimental AI to commercial automation in Asian markets

According to Ruiguo Lai, regional sales director Asia, Kong, for APAC organisations, the transition from experimental AI to production-grade autonomy represents an important change in regional competitiveness.

“As enterprises in ASEAN, South Korea and Greater China Region scale multi-agent systems in regulated and multi-cloud environments, the primary challenge has moved beyond simple model access to the complex governance of “Agent Sprawl,” he said.

“This is a matter of managing operational risk and unpredictable token costs, to securing the “Agent Mesh” and ensuring that autonomous agent-to-agent (A2A) communications remain in the guardrails of regional data sovereignty laws and internal security protocols.”

According to Lai, the launch of Kong’s new Agent Gateway provides organisations in Asia with a definitive control point for the entire AI lifecycle. By centralising visibility and policy enforcement in the full AI data path – from APIs and LLMs through to MCP tools and agent-to-agent workflows.

“Kong lets a seamless flow of intelligence without sacrificing governance. This is particularly vital in the APAC region, where the need for rapid digital commerce innovation must coexist with stringent compliance requirements in financial services and government sectors. With the Agent Gateway, organisations can finally move from isolated AI pilots to a scalable, “agentic” infrastructure that is secure, cost-effective, and fully resilient,” he said.

With agent gateway, organisations can have:

• 
  
  Unified observability in all native AI traffic: Kong Konnect acts as a single observability dashboard for all native AI traffic.
  
  


• 
  
  Production-ready agentic AI: Security, access control, and audit abilities to confidently move agentic workloads out of pilot and into production.
  
  


• 
  
  Cost visibility and control: Granular tracking of token consumption and resource use in agent workflows, enabling accurate cost allocation and margin optimisation.
  
  


• 
  
  Reduced compliance risk: Full audit logging of A2A conversations for regulatory requirements and internal governance policies.
  
  


• 
  
  Faster time to see value: Teams can focus on building agent abilities not piecing together governance infrastructure and custom gateway policies.
  
  

“Every enterprise is wrestling with the same three challenges: not having full visibility into all AI traffic and resource consumption in an agentic workflow, struggling to adopt AI in a way that helps increase margins, and dealing with issues when moving AI and agentic workloads into production,” said Reza Shafii, SVP of Product at Kong.

“We built Agent Gateway to solve this directly. Engineering teams can now govern all of their multi-agent traffic in a single place. This is the kind of control and connectivity that makes agentic AI workable at enterprise scale.”

Agent Gateway is now available in Kong AI Gateway, part of the Kong Konnect platform. To learn more, visit


/products/kong-ai-gateway



.

Author: Ruiguo Lai, regional sales director Asia, Kong.