Introducing SQL Data Insights Pro

2026-06-08 · Source: IBM Research · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics, Cybersecurity & Data Privacy · Depth: Advanced, short

Summary

IBM SQL Data Insights Pro (SQL DI Pro), generally available in March 2026, integrates advanced AI capabilities directly into Db2 for z/OS. This new offering introduces semantic search, similarity discovery, anomaly detection, and unified analysis across structured and unstructured data. Developed by IBM Research, SQL DI Pro extends traditional SQL to enable AI-driven pattern discovery, addressing challenges in data sovereignty and compliance by minimizing data movement to external analytical frameworks. It builds on SQL Data Insights by incorporating transformer-based encoders for unstructured text, aligning these with structured data embeddings in a shared latent space. The system also features incremental model training and leverages IBM Z Telum processors and the IBM Z Deep Learning Compiler for accelerated processing.

Key takeaway

For AI Architects and Data Scientists managing mission-critical Db2 for z/OS environments, SQL DI Pro offers a compelling solution to address data sovereignty and compliance. By embedding AI directly within Db2, you can perform advanced semantic analysis across diverse data types without moving sensitive information, significantly reducing operational complexity and risk. Consider evaluating SQL DI Pro upon its March 2026 general availability to streamline your data insight workflows.

Key insights

SQL DI Pro embeds AI directly into Db2 for z/OS, unifying structured and unstructured data analysis to enhance insight discovery.

Principles

• AI in-database reduces data movement risks.
• Unify structured and unstructured data.
• Embeddings enable approximate reasoning.

Method

SQL DI Pro processes unstructured text with transformer encoders and structured data with specialized models, aligning both into a shared latent vector space for unified semantic analysis within Db2.

In practice

• Perform similarity detection across entities.
• Identify anomalies in enterprise transactions.
• Generate data-driven decision recommendations.

Topics

• SQL Data Insights Pro
• Db2 for z/OS
• Semantic Search
• Unstructured Data Analysis
• AI Hardware Acceleration
• Data Sovereignty

Code references

• IBM/zDLC

Best for: CTO, VP of Engineering/Data, Director of AI/ML, AI Architect, Data Scientist, Research Scientist

Related on AIssential

• Conversational Data Analytics with SQL Embeddings — SQL embeddings transform historical queries into a semantic, queryable memory for enhanced analytics and pattern reuse.
• Bridging the Gap Between Business Intelligence and Data Access — NL2SQL systems can democratize data access by translating natural language into executable SQL queries, enhancing decision-making speed.
• To Describe or Not to Describe? Benchmarking Database Representations for Schema Linking in Text-to-SQL — LLM-generated natural language descriptions enhance Text-to-SQL schema linking more effectively than DDL/DML.
• Your Database Knows Everything. Too Bad It Only Speaks SQL. — An open-source Agentic AI module has been developed to enable users to query databases like Redshift and SQLite using plain English, eliminating the need for manual SQL writing for common tasks.
• Democratizing business intelligence: BGL’s journey with Claude Agent SDK and Amazon Bedrock AgentCore — A robust data foundation and modular AI agent design are crucial for secure, scalable, and accurate natural language data analysis.
• AI tips & tricks (Ep. 307) — RAG systems enable secure, cost-effective, and performant AI for institutional knowledge by localizing data and leveraging smaller models.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by IBM Research.