To avoid AI hallucinations, Square's AI tools translate merchant queries into deterministic actions. For example, a query about sales on rainy days prompts the AI to write and execute real SQL code against a data warehouse, ensuring grounded, accurate results.

Data is only truly "AI-ready" when it is not just technically accurate but also compliant with business context hidden in unstructured documents like policies. This involves vectorizing business logic and verifying it against facts in data warehouses.

A fundamental divide exists between consumer and enterprise AI. While consumer products often reward novelty and creativity, enterprise applications are worthless without correctness. This requires building systems grounded in truth that can extract what is verifiably correct from complex organizations.

Before implementing AI, organizations must first build a unified data platform. Many companies have multiple, inconsistent "data lakes" and lack basic definitions for concepts like "customer" or "transaction." Without this foundational data consolidation, any attempt to derive insights with AI is doomed to fail due to semantic mismatches.

The primary barrier for enterprise AI is the 'context gap.' Models trained on public data have no understanding of your specific business—its metrics, language, or history. The key is building infrastructure to feed this proprietary context to the AI, not waiting for smarter models.

AI models fail in business applications because they lack the specific context of an organization's operations. Siloed data from sales, marketing, and service leads to disconnected and irrelevant AI-driven actions, making agents seem ineffective despite their power. Unified data provides the necessary 'corporate intelligence'.

To enable AI tools like Cursor to write accurate SQL queries with minimal prompting, data teams must build a "semantic layer." This file, often a structured JSON, acts as a translation layer defining business logic, tables, and metrics, dramatically improving the AI's zero-shot query generation ability.

Before deploying AI across a business, companies must first harmonize data definitions, especially after mergers. When different units call a "raw lead" something different, AI models cannot function reliably. This foundational data work is a critical prerequisite for moving beyond proofs-of-concept to scalable AI solutions.

Text-to-SQL has historically been unreliable. However, recent advancements in reasoning models, combined with AI-assisted semantic layer creation, have boosted quality enough for broad deployment to non-technical business users, democratizing data access.