Search results for Text to SQL
AI & Enterprise
Natural-language database queries too early to trust, experts warn non-specialists should use caution
Database and analytics companies are rolling out text-to-SQL tools that let users query databases in natural language, but experts warn non-specialists should be cautious. Toronto University computer science professor Nick Koudas said systems can generate queries that are grammatically correct but not what business users intended. He put current accuracy at about 80 percent, below human experts at around 93 percent, and said company-specific data and jargon are hard for LLMs without extra training.
AI & Enterprise
Why AI delivers no impact: Tech-first approach, ignoring data complexity and vendor-centric design
Han Sun-ho, chief AI officer at Bespin Global, said many companies fail to feel the impact of AI investment because they take a technology-first approach, overlook data complexity and build systems from a vendor perspective. He said AI is a management issue and requires internal capability-building alongside partners who understand the technology. Han cited text-to-SQL accuracy limits and vector database constraints, and urged firms to define problems first and start small based on business impact.
AI & Enterprise
Mcloudbridge targets AI and BI market with conversational data agent
Mcloudbridge, a company specialising in an AI-integrated work platform, said on March 10 it will strengthen its push into the next-generation AI and business intelligence market with its conversational analytics solution, Ai 365 Data Agent. The company said the platform connects data sources including Microsoft Fabric, Databricks, Snowflake and Azure and provides querying, analysis, visualisation and insights via natural-language questions. It also supports follow-on task automation through Power Automate integration.
