QueryStory: Making AI Data Analysis More Trustworthy
QueryStory uses AI to help businesses turn complex data into reliable stories, aiming for accuracy and transparency.
Key points
- QueryStory raised $6 million in 2025 from Brightmind Ventures and New York Life Ventures.
- Co-founded by Shapor Naghibzadeh, the startup aims to improve AI data analysis for big companies.
- The platform provides real-time data analysis and confidence indicators for decision-makers.
How can AI help businesses understand their data better? Shapor Naghibzadeh, a former Google engineer, thinks large language models, or LLMs, the technology behind chatbots like ChatGPT, can transform how companies work with their data. After co-founding Chronicle at Google's X Labs to tackle data and cybersecurity issues, Naghibzadeh noticed LLMs taking center stage in data analysis. So, he launched QueryStory with Stanley Yang and David Glusic to make AI-driven insights clearer and more reliable for businesses.
QueryStory, coming out of stealth with $6 million funding from Brightmind Ventures and New York Life Ventures, targets large enterprises with big databases. The platform helps users like sales teams and operations managers analyze and review data. It's designed to provide trustworthy answers and bridge the gap where AI usually falls short.
A practical example: Tim Del Bello from New York Life Ventures uses QueryStory to replace manual work in creating quarterly business reviews. What used to take multiple people now happens with a real-time dashboard, allowing decision-makers to access the ground truth without a data science team.
How does QueryStory work?
QueryStory uses AI to create a narrative from complex data, providing visualizations and dashboards. The platform also offers a confidence indicator, which explains why the AI believes its analysis is accurate. This is especially useful for people without a dedicated data science team, who need to work with diverse data sources.
In one test, QueryStory quickly turned a database about space activities into visual insights, something a developer took weeks to do manually. This efficiency and clarity could be game-changing for companies relying on data-driven decisions.
Should users be worried about AI reliability?
Shapor Naghibzadeh acknowledges that AI can be brittle, meaning it might struggle with tasks that need to be robust and reliable at a large scale. QueryStory aims to solve this by being model-agnostic and focusing on context preservation. This means the tool isn't tied to a specific AI model, allowing it to provide more accurate and consistent results. The goal is to sell trust in the answers it provides, adding value to businesses by making costs predictable.
Common questions
How does QueryStory ensure AI accuracy?
QueryStory includes a confidence indicator that explains why its AI analyses are considered accurate. It also allows users to review and flag data for human oversight.
Who benefits most from QueryStory?
Large enterprises with big databases and decision-makers who lack a dedicated data team benefit the most. The platform offers them tools to analyze complex data without needing specialized staff.
