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.

Software deployment looks simple on paper, but in real projects, it’s where most failures show up. Even stable code can break when deployment isn’t planned well. In 2026, software deployment is no longer just about pushing code – it’s about reliability, speed, and control. Let’s explore how modern teams can deploy smarter, faster, and safer in 2026.

When you look at the pace of change in industrial AI, one truth stands out: no single company can do it alone. The complexity of power grids, transportation networks, and manufacturing systems demands collaboration — and that’s exactly what analysts are watching closely.

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.

Developing Remote Patient Monitoring Software is a strategic investment that acts as a bridge between home care and clinical settings. Here are the essential highlights that will help you navigate through the blog. ‍ Driven by the need for continuous care and better patient engagement, healthcare delivery is rapidly shifting beyond hospital walls.

‍ 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.

API mocking plays a crucial role in modern software development allowing developers to simulate external API endpoints. It’s an effective way to isolate your application for testing and ensure that code changes don’t inadvertently break critical dependencies. Essentially, API mocking helps you create robust, reliable software by allowing you to test how your application interacts with external services.