Razer has announced a new AI-powered game development tool called AI QA Copilot, which aims to help QA testers find and report bugs faster.
A faster QA cycle could help developers get games out of the door in less time too so if it works well, it would be good for everyone. Bugs appear everywhere in games during development — they’re impossible to avoid. QA (Quality Assurance) teams are dedicated to finding problems and creating detailed reports to help get things fixed faster.
Whenever a tester finds something in a game that’s clearly broken or doesn’t look quite right, they write up a bug report. This includes a summary of the problem, a detailed description, plenty of screenshots and recordings, log files, and a priority assessment.
One of the most annoying things about a bug is reproducing it — there are so many factors that could be affecting the game that it can be hard to make a bug you saw once appear again in the same way.
To help speed up the process, bug reports also contain a lot of information about the environment the bug occurred in and the potential causes. This includes the device type, operating system, configurations, and detailed descriptions of what the tester was doing when the bug happened.
It’s slow and careful work and the more detail you put in, the better. Razer’s AI QA Copilot, however, is designed to automate this whole process. While testers play through the game, it tracks bugs, crashes, and performance issues, generating detailed reports containing all the points described above, including recordings, screenshots, and even potential steps for reproduction. This gives testers the freedom to focus on finding more bugs, and by adding their own notes to the generated reports, they can increase the level of detail while reducing the time.
Like most AI tools, it’s designed to work in tandem with human testers and its work should always be reviewed. An AI can learn to predict and recognize patterns but it doesn’t understand the purpose of a game or what it’s trying to achieve — so it could definitely flag things inaccurately sometimes.
In the world of QA, however, a few mistakes from the AI tool wouldn’t be enough to diminish its value. Bug reports are truly time-consuming and if Razer’s QA assistant could save a bit of time on most reports, the results could be significant.