Systems | Development | Analytics | API | Testing

Katalon's library of testing skills for AI agents holds 13 skills. Building it produces 124 files. The 13 skills are the actual work: how to plan a test cycle, how to design cases from a requirement, how to read a failing run and decide whether a release is safe. The other 111 files are packaging. Four of them arrived this month and they are the subject of this post.

Most test automation tools are sized for one kind of team. The ones a lean QA group can adopt inside a quarter tend to buckle when a compliance officer asks who approved a change and when. The ones large enterprises standardize on often need a dedicated platform team before anyone writes a single test. Anyone who has evaluated tooling knows the feeling of reading a glowing review and realizing it was written by someone at a company nothing like theirs.

July was an enterprise month. Most of what shipped answers the questions that come up once a test team grows past a handful of people: how do we hand documentation to an auditor, where is the evidence for this step, who changed this result and when, and how do we run the same suite against a feature branch without rebuilding the integration every time.

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.

At some point a product manager or a designer is going to turn to the most user-focused person on the team and say: can you run a usability test on this? That person is usually a manual tester, because manual testers already spend their days thinking about how real people use software.

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.

June's releases share one thread: less setup between what you already know and a working test. Production Insights can turn a single real user session into a test case without a full Journey Map first. Katalon AI Assistant now reads the docs and boards your team already works in, shows its reasoning as it goes, and reaches apps your CI never could. Test management got safer to run at scale, with version history, ALM sync, and encrypted secrets. Here's everything that shipped.

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.

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.

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.