Systems | Development | Analytics | API | Testing

Standing up a production agent means taking it through six stages: At API & AI Summit, we announced the evolution of Kong Konnect into the AI Connectivity Platform and announced a slate of launches built around that idea. Here's what we launched, where each piece fits, and what you can use today. An agent that only runs when a person prompts it isn't autonomous. Real autonomy starts when something happens in the world, like a payment failing or a ticket opening, and the agent responds.

Traditional observability was built around requests. A request comes in. A service processes it. A response goes out. You trace what happened in between. That model works well for APIs. It breaks down for AI. With agents, a single user request can trigger multiple model calls. An agent might invoke a tool, call another agent, query an MCP server, retry a model, hit a guardrail, and call another tool before finally producing a response. And all of this happens non-determinstically.

At SmartBear, we’re dedicated to empowering teams by delivering application integrity: continuous, measurable assurance that their software works as intended, even as AI accelerates the SDLC. The AI Test Innovators Award: QMetry + Reflect celebrates customers who are using AI to reimagine how they create, maintain, and manage tests – without sacrificing rigor or reliability.

Before you start, paste this into Claude Code, Cursor, Codex, Gemini CLI, Kiro, or any assistant that can read a URL and run commands: The install-speedscale skill installs proxymock for your operating system and walks you through proxymock init. It stops when you need to complete browser sign-in, keeps your recordings on your machine, and connects the proxymock MCP server so your assistant can run the prompts later in this article.

Today we're announcing Kong Operator 2.3. Building on 2.2's expansion into supporting Event Gateway and Dev Portal, this release significantly broadens our feature set. While 2.2 introduced foundational event-driven capabilities, 2.3 brings Kong **AI Gateway** fully into the Kubernetes-native fold, enabling teams to manage LLM routing and policies through familiar GitOps workflows. This update also rounds out Gateway API coverage with `TCPRoute`, `UDPRoute`, and `GRPCRoute`.

Service virtualization tools don’t all solve the same problem. One team needs to simulate a single flaky HTTP dependency in CI. Another is dealing with mainframe middleware and legacy messaging protocols that most tools don’t touch. A third is running microservices on Kubernetes and wants traffic captured automatically without writing a single stub file. The category has expanded fast.

API simulation replaces real dependencies with stand-ins that respond like the actual service, keeping tests deterministic and free from rate limits, per-call fees, or unfinished upstream APIs. Simulators are built from hand-written stubs, OpenAPI specs, or recorded traffic; Keploy follows the recorded-traffic approach, capturing real HTTP, gRPC, database, and queue calls and replaying them automatically.

The first number from my local PostgreSQL 16 test was roughly 1,600 statements per second. It looked impressive. It was also the least useful result in the run. The useful part was the workload. It came from queries the demo app had actually sent: the same prepared statements, parameters, reads and writes. A synthetic benchmark tells you how PostgreSQL handles a synthetic workload. It does not tell you whether your migration just broke the UPDATE your app depends on.