Inject NOVA AI into your everyday test strategy and find >30x improvements in speed, detect and resolve more bugs, and ultimately deliver better software, faster.
It's true: almost everybody claims AI. However, it's false that everybody actually has one. Much of what is marketed as AI is really nothing more than a few "if-then" statements underneath your tooling's feature/function.
However, NOVA is different. Built from the ground-up with big data, ML models, and neural network technology, mobile quality just met real AI for the first time. Keep reading to learn more!
Our AI can convert and execute one exploratory test across your library of real Android and iOS devices for you.
Each scriptless test captures functional crashes and visual bugs/discrepancies across your real devices, all with one test.
Every time that NOVA finds a functional crash or visual discrepancy or imperfection, you are brought to that exact moment to best remediate.
Easily add parameters and datasets to your scriptless test that our AI will execute for you, eliminating complex scripting and manual re-testing.
Compare the design and UX of your application to the best and most beautiful apps in the world for auto-recommendations around optimization.
Your scriptless test will also capture Performance discrepancies across different devices and chip speeds.
Check out what our AI Engineers and Data Scientists have been cooking up and how they've done it.
Writing the algorithms takes time, but it's the data that allows the algorithms to provide business value. AI has to learn intelligent behavior “from the ground up,” and this takes information fed into the “mind” over and over and over again. And it takes a lot of information to create something that can work, "see," “think,” and “adapt” on its own.
NOVA has been exploring in the background, gathering data from over 80,000,000 (and counting) test executions, test failures, quality metrics, device specifications, element locations, NoSuchElement exceptions, etc.
Our AI Engineers have combined complex ML algorithms with a neural net approach so that NOVA could actually learn from and make actionable all of the data that it's gathered over the years.
This is where your Kobiton AI has learned to succeed, while so many others have failed.
NOVA was designed around the understanding that AI is imperfect and meant to learn. Too many solutions in the market expect AI to perform the magic from launch. NOVA expects there will be situations when it cannot figure out the solution with confidence and will need user assistance. If NOVA hits an area of low confidence, it alerts the user to be the “human in the loop,” instead of just breaking your test.
From the outset of collecting its first test results (think baby AI), we’ve seen maturity and accuracy improve, going from 75% to 85%, to 90%, and now close-to-perfect (Think grown-up AI in its prime). However, at those moments of 75% accuracy, that meant that 25% of the time something failed or went wrong. In most cases, this would be a bad thing.
But not for NOVA. Every time that there was a failure of some sort, that failure, as well as the expected result, was data that ended up being fed into the AI mind. As the amount of data grew, so did the accuracy rate.
NOVA learned a lot to get here, but it's not done. Now that its out in the wild, the NOVA AI Egnine is still continuously learning from every test execution, test result, visual output, and perfect design that it sees.
Every time you execute your scriptless test with Kobiton, NOVA learns in the background. If it hits an area of low confidence, it will point it out to you as a "blocked" test so you can show it what was missed. Point out the element, tell NOVA where to scroll, etc. With NOVA, you are the human in the loop that will make the AI smarter, and, going forward, it will remember that instruction and adapt.
The NOVA AI Engine doesn't just learn from blocked executions. The same is true when your AI finds certain visual discrepancies (our scriptless automation acts as both a Functional and Visual Test).
NOVA will automatically point these areas out for you for quick remediation. Here, you can easily give guidelines in the Kobiton UI (without writing a single line of code) around whether to accept the issue as a bug and/or increase/relax the strictness of comparison going forward for certain devices, screen sizes, etc.
Companies like Office Depot and River Island are using the Kobiton testing platform to create perfect user experiences. Let us show you what Kobiton can do for you.