If AI is positioned to unlock self-serve analytics, it needs to evolve beyond simple text-to-SQL tools and learn from the real-world expertise of human data analysts.
This is a much more compelling vision for AI-augmented data analysis.
It's not just enabling "text-to-SQL" (which is a sort of anti-pattern) but integrating business context into the analysis. The AI asking follow-up questions for context is just the first step. Once that "loop" is in place, capturing that context is also invaluable. If it can then also compare questions / answers to broader context and internal docs to refine and suggest the most effective approach to actually expanding the company's knowledge & model of reality... possibility abounds.
Excited to see more builders in data space moving forward here.
This is a much more compelling vision for AI-augmented data analysis.
It's not just enabling "text-to-SQL" (which is a sort of anti-pattern) but integrating business context into the analysis. The AI asking follow-up questions for context is just the first step. Once that "loop" is in place, capturing that context is also invaluable. If it can then also compare questions / answers to broader context and internal docs to refine and suggest the most effective approach to actually expanding the company's knowledge & model of reality... possibility abounds.
Excited to see more builders in data space moving forward here.