In recent years, AI developer tools have progressed from research projects to critical parts of the developer toolset. Today, there are over 1.8 million paid subscribers to GitHub Copilot, Google reports that 50% of their code is written with AI assistance, and TabNine estimates that 5% of all code is written by AI. These numbers will only increase as these tools continue to improve and gain further traction among developers.

Researchers in the machine learning, programming languages, and software engineering communities continue to push the boundaries of what is possible, but turning promising research results into tools that are useful at scale is hard. It involves determining the right use cases, designing the right UX, evaluating and improving quality, and many other factors.

In this talk, Eddie Aftandilian will discuss how to bridge the demo-to-real-world gap via lessons learned from building several AI developer tools at GitHub, including the original GitHub Copilot, Copilot for Docs, and Copilot Workspace.

Eddie Aftandilian is a Principal Researcher in GitHub Next, where he works on AI-powered developer tools. Through these tools, he aims to help developers become happier and more productive.

While in GitHub Next, he helped create the original GitHub Copilot, led development of Copilot for Docs, and currently leads development of Copilot Workspace.

Previously, Eddie led the Java Tools and JVM teams at Google. While at Google, he worked on:

• Error Prone, Google’s static analysis tool for Java
• Fixbot/Graph2Diff, an ML-powered build repair tool integrated into Google’s code review system
• Tricorder, Google’s static analysis platform
• Bazel, Google’s build system