“Empower Your Business with Data Conversations on Numbers Station”

Numbers Station, a startup that is using large language models (LLMs) to power its data analytics platform, is launching its first cloud-based product today: the aptly named Numbers Station Cloud, which is now in early access. With this service, virtually any user in an enterprise can analyze their internal data using Numbers Station’s chat interface. As Numbers Station co-founder and CEO Chris Aberger told me, he’s somewhat tired of talking about how the service allows users to “chat with their data,” because there is so much noise around that. Numbers Stations’ research shows that its approach results in significantly improved precision compared to more traditional text-to-SQL pipelines. “Numbers Station is at the cutting edge of enterprise AI for structured data,” said Sharad Rastogi, the CEO of Work Dynamics Technology from Jones Lang LaSalle.

Introducing Numbers Station Cloud: Revolutionizing Data Analytics With Large Language Models

The world of data analytics is about to experience a game-changing innovation with the launch of Numbers Station Cloud, the first cloud-based product from startup Numbers Station. Currently in early access, Numbers Station Cloud harnesses the power of large language models (LLMs) to offer an integrated, intuitive way to process and analyze internal data for businesses. Users can now effortlessly navigate vast amounts of data using Numbers Station’s chat interface, regardless of their technical knowledge.

While several similar tools translate natural language queries into database languages such as SQL, Numbers Station takes a different approach. As CEO and co-founder Chris Aberger explains, the generic LLM lacks an understanding of a company’s operations, data structures, and unique terminology. This limitation is what led to the development of Numbers Station’s chat-based interface, allowing business executives and non-technical users to easily ask questions and receive answers from classic structured data sources.

But creating this seamless user experience required a significant amount of engineering resources. The cornerstone of Numbers Station’s platform is its semantic catalog, which is automatically curated for each individual company. This means that each company’s definitions and metrics are specific to their own data and not shared with others. Ines Chami, co-founder and chief scientist at Numbers Station, explains that the challenge of building this catalog was initially underestimated.

“It goes back to classical [machine learning] and classical data engineering: how do I create a representation of knowledge that the model can actually use to answer those questions?”

The team had to find a way to transform vague queries into concrete questions that the model could understand and answer accurately. While this may seem like an impossible task, Numbers Station’s research shows that this approach results in significantly improved precision compared to traditional text-to-SQL pipelines.

The launch of the chat service is just the beginning for Numbers Station. Aberger sees it as just one application of the company’s larger vision: building an AI platform for analytics. This includes a variety of data problems that can be addressed within this platform, such as enriching data with third-party sources and algorithms like fuzzy matching. The possibilities are endless, and the company is already making an impact with Fortune 500 customers such as global real estate services firm Jones Lang LaSalle.

Sharad Rastogi, CEO of Work Dynamics Technology at Jones Lang LaSalle, expresses their enthusiasm for Numbers Station’s cutting-edge approach to enterprise AI for structured data.

“Numbers Station’s trusted and engaging platform continuously learns as we use it, enabling our data teams discover and verify hypotheses for driving impactful business outcomes.”

The future is bright for Numbers Station, and their innovative use of large language models is revolutionizing the world of data analytics.