Systems | Development | Analytics | API | Testing

Why “standalone AI” falls short AI works best when embedded in a process Guardrails are not a limitation—they’re an enabler Process-driven AI in action How leaders should be thinking about AI now Artificial intelligence is no longer optional in state and local government—it’s essential for meeting public expectations amid staffing shortages and budget constraints. AI is showing up across agencies and programs.

Somehow, another year has passed and we’re back again to deliver our Trends Outlook for 2026. As Qlik’s first milestone of the year, it’s a busy but exciting time that hugely energizes me after the holiday break. We weren’t short of inspiration. The world has given us a far from a blank canvas on which to illustrate our Trends and in particular, conversations around AI have firmly evolved from future-gazing to wrestling with the formula for harnessing its power.

In one of our posts, Kong AI/MCP Gateway and Kong MCP Server technical breakdown, we described the new capabilities added to Kong AI Gateway to support MCP (Model Context Protocol). The post focused exclusively on consuming MCP server and MCP tools through Kong MCP Gateway. Now, it's time to check how an AI agent can leverage the AI and MCP infrastructure exposed and protected by Kong AI/MCP Gateway.

Agentic AI is now moving into quality assurance (QA), and its impact is undeniable. What used to be a human-only responsibility is now becoming a shared system of humans and intelligent agents that observe, reason, and act across the stack.

Modern LLM coding agents are great at reading code, but they still make assumptions. When something breaks in production, those assumptions can slow you down—especially when the real issue lives in live traffic, API responses, or database behavior. In this post, I’ll walk through how to connect an MCP server to your LLM coding assistant so it can pull real production data on demand, validate its assumptions, and help you debug faster.

‍ The healthcare industry stands at the precipice of a revolution, shifting away from reactive, hospital-centric care towards proactive, personalised, and remote management. At the heart of this transformation is Remote Patient Monitoring (RPM), a system that uses connected digital health technologies to gather and transmit patient physiological data outside of traditional clinical settings. While RPM offers tremendous value, it generates a massive, continuous stream of data.

When we launched Ably in 2016, we set out to solve a fundamental problem: delivering reliable, low-latency real-time experiences at scale. So we set out to build a globally distributed system that didn't force developers to choose between latency, integrity, and reliability – trade-offs that had defined the realtime infrastructure space for years.

How AI pair programming changes the way developers design, build, and ship data connectors.

I still remember when our CI/CD pipeline crashed at 3 AM because one tiny UI element moved two pixels and every automated test failed. That single night proved how fragile traditional testing and script-based automation really are. AI-powered testing tools changed everything for our team almost overnight. They brought AI test automation, self-healing tests, and intelligent test generation that actually adapted instead of breaking.

The new fully managed remote BigQuery MCP server makes it easier to build intelligent data AI agents.