Performant Architecture for a Fast Gen AI User Experience

More and more developers are being asked to build Generative AI experiences into their web applications everywhere. However, the user's experience with Generative AI can sometimes be slow and frustrating. It’s been years since we would gladly wait over 10 seconds for a response to anything online. As AI processing gets faster, there are new limiting factors that could be negatively affecting your AI user experience.

In this talk, we will cover different ways to minimise laggy experiences in web applications when interacting with third-party Generative AI tools. We’ll be using a practical demonstration to show how you can reduce latency as we build one of my favourite sci fi gadgets, the babel fish.

Recently, Superhuman (formerly Grammarly) launched Superhuman Go, an AI assistant that works alongside you on every platform. To build it, we needed a scalable solution that supports an unlimited number of agents that dynamically shapes the user interface and looks similar across all supported desktop and mobile platforms. Join me to find out how we discovered solutions for this innovative new product.

Organizations face a significant challenge in balancing the rapid pace of AI innovation with the critical need for risk management and trust. While projections for AI investment are high, with some estimates suggesting it could account for 10-12% of technology budgets, a more cautious and critical approach is necessary.

Andy's talk will explore why firms should resist the pressure to blindly adopt AI and instead treat it like any other new technology investment. We'll discuss the importance of being agile while also maintaining a strong focus on managing risk, building trust, and critically evaluating the real-world implications of AI implementation before committing significant resources and how to differentiate ourselves, beyond the GenAI hype.

In this session, I’ll explore how AI-powered tooling is transforming large-scale refactoring and codebase migrations, making these complex tasks faster and more efficient. By leveraging tools like Large Language Models (LLMs), static analysis, and refactoring frameworks, we can automate repetitive code transformations, accelerate migration paths, and reduce human error. I’ll share practical examples of how we can migrate legacy systems to modern frameworks, break monolithic architectures into service-based structures, and automate large-scale code changes across thousands of files.

I’ll demonstrate how tools like OpenAI Codex, GitHub Copilot, and fine-tuned models for domain-specific transformations can assist in these processes, while still integrating with traditional migration tools and CI/CD systems. I’ll also cover the importance of developer oversight, highlighting lessons learned from real-world production rollouts and how to balance automation with manual reviews.

By the end of the talk, I want attendees to walk away with a clear understanding of how to use AI to enhance their refactoring and migration workflows, ensuring they can handle large-scale transformations while maintaining code quality, consistency, and governance.