TestMu AI, the Full Stack Agentic AI Quality Engineering platform, has announced Kane CLI Exploration. This autonomous agent learns a web application before anyone writes a test. Given a single URL, it walks the entire app on its own. Along the way, it flags problems. It also gives Kane CLI the context needed to generate and run tests. Notably, it works even when no requirements, user stories, or acceptance criteria exist.
Why Test Plans Fall Short Without Documentation
Every test plan starts from something written down. However, many apps never had that record. Legacy products lose their specs when the people who wrote them move on. Similarly, apps built by a coding agent in a week often carry no record of intended behavior beyond the prompt history. As a result, a testing agent ends up grading the app against itself.
“Teams now write careful instruction files for the agent that writes their code, while the agent testing that code gets a URL and nothing else, and in a lot of apps there is no spec left to hand it,” said Mudit Singh, Co-Founder and Head of Growth, TestMu AI. “Kane CLI Exploration builds that context from the app itself. For a team inheriting a legacy product, or shipping AI-written code faster than anyone can document it, that is the difference between a blank test file and a real starting point.”
How Kane CLI Exploration Maps the App
Starting from the developer’s URL, the exploration agent moves through every page, junction, and flow it can reach. It works the way a new QA engineer clicks through a product in the first week. For each page, it records the controls, the flows in and out, and the possible screen states. A form before and after a validation error is one example.
Each exploration runs across dozens of parallel browsers in the TestMu AI cloud. Therefore, a large app can be mapped in hours. Anyone on the team can also open a live browser session to watch the agent work. Without being told what to look for, the agent flags UX bugs, security issues, and accessibility concerns. These appear on pages that existing Playwright, Selenium, or Cypress suites never reached.
The map then becomes the testing context. Kane CLI reads it the way it would read a requirements document. It writes use cases and acceptance criteria from it. Next, it runs the resulting tests in real browsers and saves an Evidence Pack for every run. A person who knows the product reviews the generated tests. Finally, the approved tests run in CI on every future pull request.
Kane CLI Exploration is available today for web applications as part of the KaneAI Max plan. The plan includes three exploration sessions per license. Kane CLI launched in April 2026 and tests both web and mobile applications. Readers can learn more on the Kane CLI page.
Explore IT Tech News for the latest advancements in Information Technology & insightful updates from industry experts!
News Source: Businesswire.com
