Systems | Development | Analytics | API | Testing

Claude Code shipped workflows: reusable, versioned instructions an agent can follow instead of improvising a process from scratch each time. We used that feature to hand Claude Code our entire QA job. Not "write a test case." The whole loop: read the requirement, design the coverage, run it on the platform, file the defect, report back with evidence. The kind of work a QE does in a day, compressed into one skill triggered with a sentence.

May 2026 marks a turning point for how QA teams think about automation. This month's releases push Katalon True Platform closer to a world where you describe what you want to test, and the platform handles the rest: from generating test cases to running them, then handing you a ready-to-use script. Here is everything that shipped in May.

You opened the AI assistant for the first time with a fair amount of hope. You typed "write test cases for the login page." You got eight test cases back in about three seconds. Valid login. Invalid password. Empty username. Empty password. The kind of list you could have written in your sleep, missing every scenario that actually matters for your product. So you closed the tool and thought: this is fine for the basics, but it does not really get testing. AI is overhated.

If you only follow the loudest headlines, it is easy to believe AI is about to wipe out manual testing. Katalon's State of Software Quality Report 2025 tells a more useful story, and it comes from inside the industry: over 1,500 QA professionals, from individual contributors to senior executives, across North America, Europe, and Asia-Pacific.

You have tested hundreds of features. You know the drill. Open the test case, write the preconditions, list the steps, fill in the expected result, run it, compare. Pass or fail. Move on. Then someone hands you an AI feature. A chatbot. A "summarize this ticket" button. A search box that answers in full sentences instead of returning a list of links. You open your test case template, you get to the "expected result" field, and you stop.

A conversation with Gastón Marichal, QA Manager at QAlified, on why the hardest part of agentic QA has nothing to do with the technology. In the first installment of this series, we heard from Huy Tieu, a Katalon product manager building an AI quality companion from the inside. This time we wanted the other side of the table: someone who has to make agentic QA work for real client teams, on real delivery timelines, with real consequences if it goes wrong.

Enterprise software today isn't just complex, it's mission-critical. A single production issue can disrupt operations, impact revenue, and erode customer trust overnight. Yet despite years of investment in enterprise test automation and growing QA headcount, many organizations still ship broken software and miss release windows. The uncomfortable truth? Enterprise software doesn't fail because teams aren't testing enough.

"Agentic" is the word of the year in software marketing. Every product that sends an automated email is agentic now. Every tool with a chatbot interface is powered by AI agents. The term has been stretched to the point where it tells you almost nothing about what a product actually does.

If you have ever been asked "how do we know we tested everything?" and did not have a clean answer, a requirements traceability matrix is what you were missing. It is one of those deliverables that sounds bureaucratic until the moment you actually need it: an audit, a release sign-off, a requirement that slipped through without a single test covering it. Then it becomes the most useful document you own.

AI can write a test case in seconds. It looks clean. It is structured correctly. It has a name, preconditions, steps, and expected results - everything a good test case should have. And that is exactly the problem. A polished test case is not the same as a correct one.