Systems | Development | Analytics | API | Testing

By Noam Harel, Co-founder and CMO, ClearML AI is certainly transforming industries, but delivering it at scale is a harder task The shift to enterprise-grade AI isn’t just about building better models. It’s about managing the growing sprawl of infrastructure, tools, and people involved in every phase of your AI production From building and training to production deployment, teams are bogged down by fragmented workflows, manual provisioning, inconsistent environments, and underutilized compute.

At Koyeb, we run a serverless platform for deploying production-grade applications on high-performance infrastructure—GPUs, CPUs, and accelerators. You push code or containers; we handle everything from build to global deployment, running workloads in secure, lightweight virtual machines on bare-metal servers around the world. One of the core metrics we track is time to HTTP 200: the time between a successful deployment (excluding build) and the moment the app is ready to accept traffic.

Today, we're announcing the Koyeb MCP Server in public beta to let you interact with your Koyeb resources in natural language. Using the Koyeb MCP Server, LLMs and agents can easily discover and leverage Koyeb primitives to: All of this using your favorite AI assistants like Claude, Cursor, Windsurf or any other applications that support the Model Context Protocol.

Exploratory Testing is one of the most valuable practices in software testing, especially when we want to discover issues that impact user experience. But at the same time, it is also one of the most demanding approaches in terms of time and focus. In a world where product development life cycles are becoming shorter and where QA teams need to ensure faster releases without compromising quality, a question arises: How can we gain time without sacrificing the depth of exploratory tests and their findings?

In my previous post, we discussed how we can implement a basic AI Agent with Kong AI Gateway. In part two of this series, we're going to review LangGraph fundamentals, rewrite the AI Agent and explore how Kong AI Gateway can be used to protect an LLM infrastructure as well as external functions.