Like many other fields of programming languages research, the program synthesis problem is undecidable. In some narrower scopes things get better, and it’s just very hard. Algorithmic improvements also often require additional inputs, inputs that are at times weird or hard to generate. Put together, these traits are the furthest thing from what you could put in a user-facing tool: users expect tools to be reliable, quick, and easy to operate. But algorithms like program synthesis exist to take in user intent and return their output to users. How can we bridge this gap?