QueryStory wants you to believe what AI is telling you

The challenge of verifying AI-generated insights is a hurdle that many enterprises are currently struggling to clear. For Shapor Naghibzadeh, this problem isn't new; it’s a familiar echo of his early career. Back in 2009, while working as a systems operations engineer at Google, Naghibzadeh was thrust into the high-stakes environment of "Operation Aurora," a sophisticated cyberattack campaign orchestrated by state-backed actors. Tasked with explaining the chaos unfolding within the company’s servers, he learned firsthand that in the world of cybersecurity, verified knowledge is the only currency that matters.

Today, Naghibzadeh is applying those hard-won lessons to the era of Large Language Models (LLMs). As the CEO and co-founder of QueryStory, he is leading a mission to bring that same level of rigorous, evidence-based analysis to corporate data, ensuring that when AI speaks, businesses can actually trust the narrative.

From Google X to the Enterprise Frontier

Naghibzadeh’s career has been defined by the intersection of complex data and security. Following his tenure at Google, he spent six years refining tools for security analysts before co-founding Chronicle within Google’s X Labs in 2016. When the generative AI boom began, he recognized that the techniques used to trace cyberattacks—querying disparate, messy datasets to build a coherent story—were the perfect antidote to the "black box" nature of modern AI.

He launched QueryStory alongside co-founders Stanley Yang (CTO), a former Google colleague and lead engineer at EvolutionIQ, and David Glusic (CPO), an Accenture veteran. The startup officially emerged from stealth today, backed by $6 million in seed funding raised in late 2025 from Brightmind Ventures and New York Life Ventures, at a valuation of $60 million.

“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. It’s about telling stories with data, right? Putting a narrative together that’s grounded in truth.”

Bridging the Trust Gap

QueryStory is designed for large enterprises that grapple with massive, proprietary databases. Rather than simply acting as a chatbot, the platform serves as an analytical layer that unites data review and business intelligence. It is intended to replace the need for "armies of forward-deployed engineers" by productizing the human judgment typically required to validate AI outputs.

Tim Del Bello, a partner at New York Life Ventures, has already integrated the platform into his own workflow. He notes that the tool effectively replaces the manual labor of several staff members, transforming static quarterly business reviews into dynamic, real-time dashboards.

Key Features of the QueryStory Platform:

• Transparency by Design: Unlike general-purpose AI agents, QueryStory automatically surfaces the underlying SQL queries, allowing users to verify the logic behind every insight.
• Confidence Indicators: The platform provides a clear breakdown of why the AI agent reached a specific conclusion, helping users assess the reliability of the data.
• Collaborative Review: Users can flag specific analyses for human colleagues to review, with all feedback and validation steps recorded directly within the platform.
• Model-Agnostic Architecture: While currently leveraging top-tier frontier models, the system is built to remain flexible, avoiding vendor lock-in.

Solving the Problem of Brittle AI

The primary critique of current AI tools is their fragility. When companies connect their internal data to a standard LLM chat interface, they often end up with a "sprawl of content"—thousands of employees generating conflicting versions of the truth, none of which are anchored to a verifiable source.

"AI is more brittle than people realize when it comes to building things that have to be durable and have large-scale businesses relying upon them," says Tayler Sipperly, a partner at Brightmind Partners.

QueryStory aims to solve this by acting as a "truth layer." In a demonstration, the platform successfully visualized complex space activity data—tracking satellites and orbital maneuvers—in just a few hours. A task that previously required weeks of developer time was completed with sophisticated dashboards and, crucially, a confidence score that explained the AI’s reasoning.

A Different Business Model

In a market dominated by companies incentivized to maximize token consumption and compute usage, QueryStory is positioning itself differently. Naghibzadeh argues that because his company is not built on a consumption-based model, they are better aligned with the customer’s ultimate goal: accuracy and cost-efficiency.

"The thing that we are selling is the trust in the answers," Naghibzadeh explains. "Our whole goal is giving the CFO the ability to understand exactly what a project is going to cost and why the data supports that conclusion."

By focusing on the "ground truth" rather than just the speed of generation, QueryStory is betting that large enterprises will prioritize control and reliability as they move past the experimental phase of AI adoption and into the era of durable, business-critical infrastructure. As organizations continue to integrate AI into their core operations, the ability to audit, verify, and trust the machine's narrative will likely become the most valuable feature of all.