This is the second post in a series. For the first part, see Why We Need to Stop Prompt Hacking . Generative AI systems do not fail because models are weak. They fail because architectures are incomplete. Once organizations accept that prompts cannot guarantee reliability, a new challenge emerges:…
Generative AI has completely changed the landscape of enterprise automation, knowledge work and operational efficiency. In 2026, the question is no longer whether these models can perform complex tasks, but whether they can do so reliably enough for mission-critical systems. Despite the…
This is part of a three-part series. For the full story, see Your AI Agent Knows What, It Doesn't Know Why and The Case for Kafka as the Agent's Memory Layer . We made the case for why agentic AI systems need a durable commit log rather than static state snapshots. The argument is…
This is part of a three-part series. For the full story, see Your AI Agent Knows What, It Doesn't Know Why and Building the Agentic Commit Log . Once you accept that agentic AI systems need a durable commit log — an ordered, immutable record of every tool call, decision, and context shift —…
AI agents move fast. Securing them shouldn't slow you down. Kong and Noma are partnering to change that. Noma is the newest member of Kong's Technology Partner Program . This program delivers high-quality, reliable integrations providing real business value for customers. Together, Kong and Noma…
Today we're announcing kongctl 1.0, Kong's new command-line (CLI) tool for managing Kong Konnect programmatically. This release brings kongctl to the Generally Available (GA) level of support and capabilities, giving developers, platform engineers, and AI coding agents a streamlined tool for…
Each change to Kong Gateway's codebase triggers a comprehensive test suite that runs more than 17,000 * 2 = 34,000 test cases among the two primary architectures (x86 and ARM) we support. This process takes about 23.5 hours on a single machine. But we don't wait that long. A large fleet of machines…
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…
Every few months, a frontier AI lab makes a move that says the quiet part out loud: agents are only as useful as the systems they can reach. The latest example is Anthropic's acquisition of Stainless, the company behind the tooling that turns API specs into SDKs and MCP servers. Anthropic's own…
Customers today face significant challenges as their Kubernetes environments scale. The proliferation of microservices, external integrations, and new AI workloads increases traffic volume and connectivity complexity, creating material risks to performance and availability. The core issue is a lack…
This is part of a three-part series. For the full story, see Building the Agentic Commit Log and The Case for Kafka as the Agent's Memory Layer . There's a reason we don't find our keys by scanning every room like a security camera. We replay the tape. We remember the groceries, the front…
Your AI infrastructure is producing financial signals your CFO has never seen. Token consumption is a direct cost line item. Cache hit rate is a margin improvement. Model routing decisions are cost arbitrage events. These things are happening right now, in the gateway layer, with no route to the…
AI agents are only as capable as the tools they can reach. When an agent needs to query a database, file a support ticket, or pull data from a CRM, it has to find the right tool, authenticate, and invoke it — all at runtime. The Model Context Protocol (MCP) standardizes how agents communicate…
GitHub just sent waves of budget panic across its developer base. Seat-based Copilot pricing is out. Consumption-based credits are in. And if you're building an AI-driven product today on flat-rate pricing? You're building a problem into your roadmap. GitHub just announced Copilot plans will shift…
Key takeaways - An MCP server is a lightweight process that exposes tools, resources, and prompts to AI applications over a standardized protocol. - It acts as the bridge between an LLM-powered client and an external system — a database, API, file system, or SaaS product. - The protocol…
Three-quarters of enterprises are now piloting or deploying AI agents. But here’s the problem: actually integrating those agents with enterprise applications is proving to be one of the hardest parts of the whole endeavor. That’s the core finding of a recent Gartner research note, How to Integrate…