Scalability and reliability are 🔑 when you're processing millions of orders every day. Load testing helps ensure everything runs smoothly — even during peak times like holidays 🎄📈. But here's the catch: manually analysing those results is slow, tedious, and often misses critical issues like latency spikes, excessive resource usage, or sneaky memory leaks 🐛 in your Golang services.

This talk dives into how AI can transform load test analysis — cutting through the noise to spot what really matters, faster and smarter 🤖⚙️.

This talk bridges the gap between theoretical performance testing concepts and hard-earned lessons from real-world implementation. We dive into actionable techniques that will help you deploy and maintain a fruitful Continuous Performance Testing practice. We address a wide spectrum of common mistakes and misunderstandings: the crucial differences between Performance Testing and Load Testing, environment must-haves, pitfalls in metrics management, result analysis challenges, and much more.

By the end of this presentation, you'll be better equipped to implement a truly continuous approach, enabling your team to deliver faster, stronger, and better applications that meet modern performance expectations.

This talk covers Grammarly's approach to using a combination of third-party LLM APIs and in-house LLMs, the role of LLMs in Grammarly's product offerings, an overview of the tools and processes used in our ML infrastructure, and how we address challenges such as access, cost control, and load testing of LLMs, sharing our experience in optimizing and serving LLMs.