When you think about building a vision-enabled product, you probably think about things like: Which processor am I going to use? What neural network will it run? Where will I get the training data? These are important questions that need answers! But there are other, less obvious things that also require careful, early consideration in order to lay the groundwork for a successful product development. In this talk we’ll draw on BDTI’s experiences building vision-enabled products for consumer and industrial applications to explore five critical areas that often get overlooked. These include engineering management topics, such as how to plan and manage ML model experiments; avoiding not-invented-here syndrome (e.g., leveraging existing frameworks vs. creating your own); and being realistic about what your vendors can and can’t deliver (e.g., tools, drivers). They also include system architecture considerations, such as lighting, camera placement and dealing with memory constraints in cost-sensitive applications.