Imagine asking your database a question in plain English - and getting the right answer back, instantly. Thanks to advances in large language models (LLMs), this is now a practical reality. Natural Language to SQL (NL2SQL) systems are making data more accessible than ever, helping teams move faster without writing a single query by hand. In this talk, we’ll walk through the key building blocks that make it possible for LLMs to "talk" to databases.
We’ll start with natural language: how NL2SQL systems understand what the user is asking, map questions to the right parts of a database, and generate executable SQL. Of course, this is easier said than done. Natural language is full of ambiguity, and many databases have complex schemas, tricky joins, and domain-specific terms. But despite these challenges, benchmarks like Spider and BIRD show just how far we've come in the past decade.
Next, we’ll introduce the Model Context Protocol (MCP) - a way to give LLMs access to metadata, table relationships, and tools for query execution. Instead of guessing, the model can reason step-by-step using chain-of-thought, consult the schema, and run sub-queries to reach the right result.
Whether you're an engineer building LLM-powered interfaces or a data leader exploring self-serve analytics, this session will give you a clear view of how natural language is reshaping the way we interact with data and how to start using it in your stack today.
