Context, Not Models: What Actually Made AI BI Reliable

Description and use

<p>You're in a planning meeting and someone says, "Can't we just let the LLM write the SQL?" Everyone looks at the data team. The honest answer is "yes, if we build the right things around it." Here's what those things are.</p> <p>That answer has gotten more specific over the last couple of years. In 2024, Uber and LinkedIn published detailed write-ups of <strong>text-to-SQL</strong> systems running against warehouses with hundreds of thousands of datasets (Uber, in a limited release) and millions of tables (LinkedIn). Both teams said what worked and what didn't. Since then, newer models have

Problem

<p>You're in a planning meeting and someone says, "Can't we just let the LLM write the SQL?" Everyone looks at the data team. The honest answer is "yes, if we build the right things around it." Here's what those things are.</p> <p>That answer has gotten more specific over the last couple of years. In 2024, Uber and LinkedIn published detailed write-ups of <strong>text-to-SQL</strong> systems running against warehouses with hundreds of thousands of datasets (Uber, in a limited release) and millions of tables (LinkedIn). Both teams said what worked and what didn't. Since then, newer models have

Outcome

<p>You're in a planning meeting and someone says, "Can't we just let the LLM write the SQL?" Everyone looks at the data team. The honest answer is "yes, if we build the right things around it." Here's what those things are.</p> <p>That answer has gotten more specific over the last couple of years. In 2024, Uber and LinkedIn published detailed write-ups of <strong>text-to-SQL</strong> systems running against warehouses with hundreds of thousands of datasets (Uber, in a limited release) and millions of tables (LinkedIn). Both teams said what worked and what didn't. Since then, newer models have

Evidence

Context, Not Models: What Actually Made AI BI Reliable

Source