We are developing a software which provides a quick and reliable way to detect and predict machinery failure through AI. The growth of sensing tech and IoT is causing an explosion in data generated by energy storage and conversion devices. This data can can detect the onset and type of failure, but there is currently no tool that can interpret this data. Failure prediction is key in reducing warranty costs, increasing operating efficiency, and getting to market fast. Organizations are forced to spend hundreds of thousands of dollars on ineffective in-house solutions or teams of engineers. For example, BC Hydro, Teck, and Lucid Motors (EV company) have all recently built data science teams to assist with asset management or R&D. Each of these companies has committed to spending near $1M per year to develop the capabilities that Machinery Analytics plans to offer via its SaaS platform. These are all significant market opportunities, EV being valued at over $62B in North America. Another example is our lead client. They design high capacity Li-ion batteries and have spent $200K+ on trying to develop an in-house data analysis solution before hiring us. Our software finally allows the client to understand how different manufacturing methods affect the micro-structure of a battery, and from there, its performance. We are building a SaaS product to better understand material microstructure and machine telemetry data from complex hardware systems. The objective is to automatically distinguish changes in performance from changes in load, configuration and the environment. The ability to predict failure and changes leads to reduced cost and increased efficiency. We already have a beta product we are charging clients for. We have recently signed a contract with one of our clients for $40K USD. For a full functioning version of the software, we are planning to launch it in October, 2021.