NEWS · CODING · #949
Designing Fast, Delightful UX With LLMs for Mobile Frontends (QCon presentation)
At QCon San Francisco, Amazon senior engineer Balakrishnan Ramdoss presented techniques for architecting production-grade conversational mobile apps with LLMs, discussing model latency mitigation, server-driven UI and Backend-for-Frontend patterns, prompt optimization for UI selection, and options for low-latency, privacy-first on-device AI integration.
KEY POINTS
- At QCon San Francisco, Amazon senior engineer Balakrishnan Ramdoss presented techniques for architecting production-grade conversational mobile apps with LLMs, discussing model latency mitigation, server-driven UI and Backend-for-Frontend patterns, prompt optimization for UI selection, and options for low-latency, privacy-first on-device AI integration.
- The talk provides practical architecture and patterns for building production conversational mobile apps that balance latency, privacy, and deep app integration.
- Presentation: Designing Fast, Delightful UX With LLMs for Mobile Frontends
WHY IT MATTERS
The talk provides practical architecture and patterns for building production conversational mobile apps that balance latency, privacy, and deep app integration.