Microsoft Windows Feedback Hub is designed to receive customer feedback on a wide variety of subjects including critical topics such as power and battery. Feedback is one of the most effective ways to have a grasp of users' experience with Windows and its ecosystem. However, the sheer volume of feedback received by Feedback Hub makes it immensely challenging to diagnose the actual cause of reported issues. To better understand and triage issues, we leverage Double Machine Learning (DML) to associate users' feedback with telemetry signals. One of the main challenges we face in the DML pipeline is the necessity of domain knowledge for model design (e.g., causal graph), which sometimes is either not available or hard to obtain. In this work, we take advantage of reasoning capabilities in Large Language Models (LLMs) to generate a prior model that which to some extent compensates for the lack of domain knowledge and could be used as a heuristic for measuring feedback informativeness. Our LLM-based approach is able to extract previously known issues, uncover new bugs, and identify sequences of events that lead to a bug, while minimizing out-of-domain outputs.

While Microsoft is preparing for the release of Windows 10 IoT Core for a multitude of devices, the Redmond giant is also quietly pushing for the availability of Cortana in all the devices that the Windows 10 software variant will be supporting. This is based on the information Microsoft officials provided last week at WinHEC 2016 in Shenzhen that has come to light early this week. In a presentation, entitled "Cortana and the Speech Platform," Microsoft officials revealed to OEM partners what the company's big move for its advanced voice assistant is all about. ZDNet has learned that the tech giant is preparing for its PCs and device partners to utilize the "Wake on Voice from Modern Standby" and "Far-field Voice" functionality of Cortana through the Creators Update that is arriving in Spring 2017. The "Wake on Voice from Modern Standby" technology enables Cortana to control devices from their inactive state.