Your model will keep getting better at writing SQL. To make it trustworthy, nail down the access rules before tuning for ...

Data platforms make decisions all day. An SQL query keeps the rows over a threshold, matches a keyword, and joins two tables on a shared ID. A pipeline sends a failed job down a retry path. Rules like ...

AI agents can generate valid SQL and still deliver wrong answers. Discover how semantic layers help connect AI to approved ...

As enterprises race to connect AI agents to their most sensitive data, Oracle database tools specialist Jeff Smith is making a contrarian case: ...

NVIDIA has open-sourced Auto Ontology, a framework designed to make AI agents more reliable when querying enterprise databases using natural-language instructions. The system creates a semantic layer ...

The new capabilities aim to help developers simplify enterprise data retrieval, maintain agent context across sessions, and ...

AI agents need data products to reliably discover and use enterprise data.

The Streamhouse architecture aims to deliver up-to-date business data for enterprise AI, analytics, and decision-making.

Confluent, an IBM company, today announced new capabilities for building a Streamhouse, a new type of data architecture that keeps business context current ...

Oracle’s Deep Trust AI Architecture moves AI agent security into the database. This article looks at the announcement, how it ...

"I connected an AI agent to a database and asked it to 'get last month's net sales,' and it wrote and executed the SQL in ...