Executives want both traditional dashboards and conversational experiences, but the sticking point isn't demand — it's quality control. When AI hallucinates a time series graph from data without dates, non-technical users treat it as truth. The challenge: data professionals expect 100% accuracy, but can't dictate what prompts users will enter.
Key takeaways:
Conversational analytics demand exists alongside traditional BI — different executives prefer different interfaces for consuming insights
The core challenge isn't building conversational experiences, it's ensuring high-quality outputs from unpredictable user prompts
Hallucinations remain a critical problem — AI confidently creates visualizations (like time series graphs) from incomplete or wrong context
Non-technical users don't understand when AI is guessing, treating hallucinated outputs as verified truth
Data teams need frameworks and measurements to validate conversational AI quality before users can trust it in production
