Graph Neural Networks are a tantalizing way of modeling data which doesn't have a fixed structure. However, getting them to work as expected has had some twists and turns over the years. In this talk, I'll describe the Graph Mining team's work at Google to make GNNs useful. I'll focus on challenges that we've identified and the solutions we've developed for them. Specifically, I'll highlight work that's led to more expressive graph convolutions, more robust models, and better graph structure.