Shapor Naghibzadeh first grasped the power of a well-crafted narrative back in 2009, while working as a sysops engineer at Google. When Chinese-backed hackers targeted the search giant in what became known as Operation Aurora, he was pulled into an emergency war room to clarify what was unfolding across the company's servers. Piecing together cyberattacks across scattered networks taught him the importance of verified information—but the process was slow and expensive. He now believes large language models can deliver that same capability to any database, and do it far more quickly.

Over the following six years, Naghibzadeh focused on the intersection of data and cybersecurity, leveraging Google's resources to build tools that let security analysts interrogate complex datasets. In 2016, he co-founded Chronicle within Google's X Labs, a startup designed to bring those capabilities to outside companies. Then, last year, as LLMs began playing a bigger role in data analysis, he spotted a fresh opportunity: applying the techniques he'd honed for cybersecurity to analytics across industries. That led him to co-found QueryStory, where he serves as CEO, alongside CTO Stanley Yang—a former Google colleague and lead engineer at EvolutionIQ—and CPO David Glusic, who came from Accenture. The company officially came out of stealth today.

“You get this pattern of an investigation—you ask a bunch of questions of the data, and after you have been able to ask a number of questions, you assemble that together into a narrative,” Naghibzadeh said. “That became the genesis for the name QueryStory. It’s about telling stories with data, right. Putting a narrative together that’s grounded in truth.”

QueryStory secured a $6 million seed round in late 2025, backed by Brightmind Ventures and New York Life Ventures at a $60 million valuation. Since then, the team has been developing and testing the product with early customers. The platform targets large enterprises managing big, proprietary databases, offering a unified space for data analysis and review—whether for sales teams or operations managers. “What we’re doing is bridging that trust gap for AI to give enterprises answers that they can act on,” Naghibzadeh said. “Instead of, you know, like renting human judgment and armies of forward deployed engineers, we productized that.”

Tim Del Bello, a partner at New York Life Ventures, invested in the company and is also using the platform himself. He's replaced the work of several employees with it, producing a quarterly business review that he hopes will eventually become a real-time dashboard.

I tested QueryStory with a database of space activity, useful for tracking what companies like SpaceX are doing in orbit. The tool generated a visualization of that data in just a few hours—a project I once tackled with a developer over several weeks. It produced sophisticated dashboards and analysis, and perhaps most notably, included a confidence indicator that explained why the AI agents believed the analyses were accurate.

This type of work can also be done with collaborative tools from frontier labs, but those tools are deliberately limited in their user experience. QueryStory is betting that users—especially at large organizations—want more transparency, reliability, and control when weaving AI into their workflows. In QueryStory, SQL queries surface automatically, and users can flag analyses for human coworkers to review, with those reviews logged in the platform. Naghibzadeh points out that when companies connect their data to an LLM’s chat interface, “you get hundreds or thousands of people within an organization all asking their questions and getting their version of the truth and putting that in a slide deck and sharing it—you just end up with this huge sprawl of content, and there’s no real place to hang that content that ties back to the data.”

Economics also play a role. QueryStory is built to be model-agnostic, though for now it mostly relies on the latest models from frontier labs. While the company competes with those labs on a product level, Naghibzadeh believes customers will prefer working with a provider that isn't incentivized to push as much intelligence as possible. “We have a lot of things going for us here in not being one of those companies that built their business around this consumption model of compute or storage or tokens,” he said. He argues that a purpose-built tool like QueryStory can be more efficient and accurate than a general-purpose agent by understanding and preserving context. “The thing that we are selling is the trust in the answers, right,” he said. “The thing that we’re selling them is the value that we’re adding to the business, and our whole goal is giving the CFO the ability to understand ‘what is this thing going to cost.’”