The latest news and announcements about Kong, our products, and our ecosystem, as well as voices from across our community.
Agents are moving from demos into production, and the platform teams running them keep hitting the same four problems: spend nobody can attribute, credentials that security cannot manage, enterprise APIs rewrapped as agent tools team by team, and no single view of what an agent actually did. Today…
Every request returned 200 OK, the task still failed. This is the problem in one sentence. A single user intent now fans out into multiple model calls, tool invocations, MCP (Model Context Protocol) interactions, policy executions, retries, and agent handoffs. Each call can look healthy on its own…
A healthy API and a successful model call do not prove that an AI application produced a useful result. AI observability connects logs, metrics, and traces with evidence about behavior, retrieval, tool use, quality, safety, and token consumption. That combined view helps AI engineers explain what…
Trace complete AI sessions across models, tools, agents, and infrastructure — and understand where performance, cost, and failures accumulate. Traditional observability was built around requests. A request comes in. A service processes it. A response goes out. You trace what happened in between.…
Most teams building multi-agent systems hit the same wall at roughly the same point. The prototype works. Agents chain together, tasks complete, the demo impresses the room. Then someone asks: "What happens when this runs a thousand times a day? What happens when an agent calls an external API…
Kong Mesh 2.14 delivers important improvements for multi-zone customers, with expanded policy support for zone proxies, new SNI-based matching for cross-zone and external-service traffic, stronger default security settings, and better observability through OpenTelemetry and Grafana dashboards. What…
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…
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…
Scaling LLM and agentic AI adoption from pilot programs to enterprise-wide deployments is a massive logistical rollout. As AI and agentic usage grow, so does a nagging question for leadership: Are agents using the right tools to get the job done? While raw infrastructure metrics might tell you if a…
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…
Kong is excited to announce Solace as the newest member of our Premium Technology Partner Program, a program designed to deliver high-quality, reliable integrations that provide real business value for customers. Together, Kong and Solace unify API-driven and real-time data movement into a single,…
Discover expanded OpenTelemetry support, full cloud-native authentication, powerful Datakit orchestrations, and PCI DSS 4.0 attestation for Kong Konnect and Cloud Gateways. As API ecosystems grow more complex, maintaining visibility and security shouldn't be a hurdle. Kong Gateway 3.13 simplifies…
The integration of next-generation AI workloads — from large language models (LLMs) to speech-to-text and text-to-speech — demands a powerful, secure, and scalable infrastructure. This is especially true for building advanced AI voice agents, which rely on seamless, natural, and highly efficient…
In this post, Kong Champion Sachin Ghumbre shares his journey of transforming a complex GenAI application from a state of operational challenges to streamlined control. Discover how Kong AI Gateway provided the enterprise-grade governance needed to secure, optimize, and scale his GenAI solution,…
Disruptive businesses are understandably rushing to deploy AI-native applications alongside traditional API infrastructure. However, managing observability across both domains (API and AI) while keeping a tab on performance visibility and operational control remains a pressing challenge. AI…
We're very excited to announce Kong Mesh 2.12 to the world! Kong Mesh 2.12 delivers two very important features: SPIFFE / SPIRE support, which provides enterprise-class workload identity and trust models for your mesh, as well as a consistent Kuma Resource Identifier (KRI) naming convention for…