The shift from single-model AI features to multi-agent pipelines is no longer a future concern — it's running in production today. MCP has become the de facto protocol for tool-calling, agent-to-agent (A2A) communication patterns are proliferating, and enterprise teams are wiring together complex…
[](/blog/product-releases/kong-ai-gateway-3-14)
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,…
[](/blog/product-releases/kong-agent-gateway)
Every few weeks, the AI-adjacent internet crowns a new corpse. SaaS is dead. OpenAI is dead. The IDE is dead. Humans writing code is dead. The structure is always the same: take a real observation, strip it of all nuance, and toll the death knell to feed the hype train. Rinse and repeat. The…
[](/blog/enterprise/cli-vs-mcp-enterprise-ai-governance)
The microservices revolution promised agility and scalability. Teams could deploy faster, scale independently, and innovate without monolithic constraints. You gain speed and flexibility, but you also multiply trust boundaries, identities, network paths, and policy decisions. Then came AI, and…
[](/blog/engineering/5-best-practices-securing-microservices-scale)
Modern enterprise architecture faces a three-body problem. Three distinct traffic patterns pull your teams in different directions. External APIs serve mobile apps and partner integrations. Internal microservices communicate within Kubernetes clusters. AI and LLM calls flow to OpenAI, AWS Bedrock,…
[](/blog/enterprise/microservices-to-ai-traffic-kong-as-the-unified-control-plane)
AI APIs don't get enough credit for how much weight they're actually carrying. These AI APIs aren't merely technical connectors. They're, in fact, cost drivers and potential revenue engines. And when something goes sideways, they're ground zero. In production, they behave nothing like the…
[](/blog/engineering/monetize-ai-apis)
AI connectivity is enterprise infrastructure that governs, secures, routes, observes, and optimizes all AI interactions —providing the control layer organizations need to transform experimental AI into production-ready systems. Executive Summary AI adoption has moved past the "honeymoon phase" and…
[](/blog/enterprise/ai-gateways-for-scalable-ai-connectivity)
As enterprises race to deploy multicloud architectures and Agentic AI, they face a common bottleneck: "state." To govern AI token usage, manage agent-to-agent communication, or optimize performance via caching, API and AI gateways require a persistence layer to synchronize data. We’re excited to…
[](/blog/product-releases/multicloud-cloud-gateways-managed-redis-cache)
As enterprises start deploying AI agents into real systems, a new architectural challenge is emerging. Agents need a reliable way to discover tools, services, and capabilities dynamically, instead of relying on hardcoded integrations. This is where the Model Context Protocol (MCP) ecosystem is…
[](/blog/engineering/mcp-registry-dynamic-tool-discovery)
In the burgeoning intelligence economy, AI tokens are a metered utility, but enterprise profitability now hinges on a critical distinction: output tokens can cost up to 10x more than inputs, creating a new, invisible risk for cost overruns, particularly with Agentic AI. Learn how Kong AI Gateway…
[](/blog/enterprise/ai-input-vs-output-cost-management)
The AI coding and Agent Harness approach is no longer experimental. This is likely the most impactful agentic AI use case in production today, and Claude Code is one of the solutions really leading the charge. But as engineering teams race to adopt Claude Code across their organizations, a critical…
[](/blog/engineering/claude-code-governance-with-an-ai-gateway)
Gartner published a report last week (1) that I think marks a genuine inflection point for how enterprise technology leaders should think about AI strategy. The headline finding: we have crossed a threshold where competitive advantage in the AI era is no longer about access to data — it's about…
[](/blog/enterprise/the-context-economy)
Last week, Gartner published a report titled MCP Servers Will Fuel the Next AI Revenue Surge — Context as a Service (1) that should be required reading for every enterprise technology leader. Then, Kong CEO Augusto Marietti (Aghi for short) wrote out his thoughts on the subject and why context is…
[](/blog/enterprise/the-platform-enterprises-need-to-compete)
AI agents are spreading across organizations rapidly. Each agent needs secure access to different Model Context Protocol (MCP) servers. Authentication becomes complex. Scaling creates bottlenecks. The dreaded "too many endpoints" problem emerges. You face a classic AI infrastructure headache. The…
[](/blog/learning-center/what-is-a-mcp-gateway)
The promise of agentic AI is clear: autonomous systems that can reason, plan, and act on your behalf. But there's a fundamental problem standing between that vision and enterprise reality: agents need context to make decisions, and that context lives scattered across your organization. Context is…
[](/blog/product-releases/introducing-kong-context-mesh)
For too long, the Model Context Protocol (MCP) has operated on a principle of open access: connect an AI agent to an MCP server, and it gets access to every single tool that server offers. While this approach is simple for initial experimentation, it quickly becomes a liability in production.…
[](/blog/engineering/mcp-tool-governance-security-meets-context-efficiency)