How We Built a Virtual Scheduling Assistant at Microsoft

With all the progress happening in AI, we wondered if we could create a virtual assistant that could handle the conversational back-and-forth required for scheduling meetings, much the same way that executive admins schedule meetings for CEOs. There is a long history of AI research around building digital personal assistants, but for a number of reasons, none of the early scheduling AI work has taken off. We took a step back and considered long-standing rapid-prototyping approaches in design. These involve building and testing lo-fi prototypes before gradually iterating on higher-fidelity—and more expensive—designs. We also followed a humans-in-the-loop approach, creating a prototype that looks and feels real for users, but behind the curtain, there are human researchers pulling the strings and controlling the interface. Although this was a lot of work, with nearly two years of iterations, it allowed us to get a product into people’s hands early so we could observe their behavior and iterate quickly. It also gave us a deeper understanding of the problem we were trying to solve—and let us start evaluating which portions of the work could eventually be performed through AI. Overall, we believe creating and using systems like Calendar.help to manage routine tasks are an easy way for companies to leverage AI in their daily business practice. The AI tools are already out there—you just have to figure out the process that best takes advantage of them.