Block's GraphQL copilot: Easier schema discovery and query automation via LLMs & RAG

Curious to see how AI can ease and accelerate your developer experience? Join this talk to learn how you can use Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) to make schema discovery and query generation easier in federated GraphQL systems with massive schemas.

We explore how using vector embeddings and prompt engineering can help you quickly turn natural language queries into accurate GraphQL operations with a process that gets better over time.