
Building LLM apps is a cycle. To make a robust app, you need to build with continuous feedback in mind—testing, measuring, and iterating at every stage. In this hands-on workshop, we’ll walk through how to create and improve a chatbot from scratch using the principles of evaluation-driven development. You’ll learn how to:
- Use datasets and experiments to validate your chatbot during development
- Implement tracing and evaluation techniques to monitor performance in production
- Incorporate real-world production insights to drive continuous improvement
Whether you’re new to LLM development or looking to enhance your existing workflows, this workshop will provide practical tools and strategies to help you build more reliable, effective AI applications.