From Physics to AI: Building a 200ms Coding Assistant | ft. Guy Gur-Ari, co-founder of Augment Code

Why watch

An interview with Augment Code co-founder Guy Gur-Ari exploring the technical architecture behind achieving 200ms response times in AI coding assistants while maintaining full codebase context awareness. The conversation covers how retrieval-augmented generation works for codebases, the engineering decisions around latency optimization, and Guy's career path from theoretical physics at the Institute for Advanced Study to Google AI research. Targeted at engineering leaders evaluating coding assistants and developers curious about AI code tool internals.