ThoughtSpot Integrates with GPT-3 to Launch Sage, a New AI-powered Search Experience for Analytics
MOUNTAIN VIEW, Calif., March 9, 2023 — ThoughtSpot today announced a new integration with GPT-3, the popular large language model (LLM) from OpenAI, to make analytics accessible, trusted, and scalable through artificial intelligence. This includes the launch of ThoughtSpot Sage, a new search experience that combines LLMs like GPT-3 with ThoughtSpot’s patented search technology.
With this combination, every employee, regardless of their skill level, can confidently use AI-Powered Analytics on even the largest, most complex data to ask and answer business questions, find accurate insights, and take action. ThoughtSpot Sage, currently in preview, currently supports GPT-3 with support planned for additional LLMs.
With ThoughtSpot Sage, ThoughtSpot is taking analytics to the next level through advanced natural language processing (NLP) and generative AI. In doing so, data teams are able to exponentially increase their impact across an organization by freeing themselves from tediously managing report requests as business users self-serve insights.
Specifically, customers can use ThoughtSpot Sage for:
- Natural language search: Customers can use LLMs to enhance the search-driven analytics capabilities in ThoughtSpot with true natural language. This means increased ease of use while preserving the accurate data discovery of the ThoughtSpot platform, along with improved search suggestions based on the search data model.
- AI-generated answers: With ThoughtSpot Sage, users can search existing analytical content, or automatically create new insights, charts, and visualizations based on natural language search. ThoughtSpot Sage then takes this further, using AI to create narratives explaining what insight is being surfaced, so users can quickly and easily understand a data visualization and act upon it.
- Data modeling: With AI-assisted data modeling that incorporates natural language, data professionals can create search data models that allow AI to answer questions faster than ever, while preserving the reliability and guardrails of the data model. Synonyms can be generated quickly using LLMs, shortening the time to value for these search models by making them immediately usable to business users quickly. Furthermore, with ThoughtSpot Sage, analysts can also automatically generate descriptions, helping business users understand what data they are utilizing and improving data literacy in the process.
Fueling a New Era of Information Creation
Large language models like GPT-3 have created new opportunity when it comes to how companies turn data into insights that drive action. Organizations in every industry know the value of building their business on data if they want to beat the competition, delight customers, and create sustainable, lasting companies. Historically, this has required teams of data experts with complex skills spoon feeding predefined, curated insights to decision makers.
ThoughtSpot pioneered natural language search powered by AI as the interface to solve this challenge. Over the last decade since inception, the company has continued innovating to enable anyone to use keywords to find and create accurate, meaningful data-driven insights that improve decision-making. The platform was built and continues to incorporate new capabilities to translate natural language queries into SQL, on the fly and at scale, making it possible to explore data through search in ways never before possible without increasing data sprawl.
GPT-3 has ushered in a new era for search, redefining the relationship between humans and machines in the process. Search is no longer simply the means to retrieve information. With a few simple natural language inputs, users can use LLMs to actually create new content and information that never previously existed.
When it comes to creating new data insights and analytical content, however, this technology breaks down. LLMs like GPT-3 can’t handle complex data or data in multiple fact-tables, lack business logic, and have issues working directly with data in a cloud data platform. This leads to inaccurate insights that can drive the wrong decisions, introduce risk, and erode trust from end users.
With ThoughtSpot Sage, however, customers can take advantage of the natural language of LLMs paired with the under the hood capabilities that have made ThoughtSpot the leader in search-driven analytics for even the largest, most data complex organizations in the world. Analysts and other data professionals can quickly build reusable search data models that provide guardrails for end users, so they can safely explore with natural language. This makes it possible to leverage the power of LLMs for analytics in an actual business environment, with real business data. Business users can then use natural language to explore all their organization’s existing analytical content to find answers that have already been created or create new insights. ThoughtSpot Sage also ensures they and their colleagues understand these insights with machine-generated narratives explaining the insight. In doing so, companies can deliver trustworthy AI-Powered Analytics to every kind of user that is incredibly intuitive, without sacrificing accuracy, reliability, governance, or security in the process.
“As a company, we made three strategic bets about what would define the next leader in analytics. First, that business users would demand personalized, useful insights from their data. Second, that when data moves to the cloud, customers want flexibility and freedom to choose the best tool for their specific use case. Last, we bet that user experience would crown the next leader in analytics,” said Sumeet Arora, Chief Development Officer, ThoughtSpot. “While our customers have already shown us these were the right bets to make to deliver a differentiated product, LLMs like GPT-3 have made each of these even more important. They’ve supercharged the value of each of the areas we focused on, showcasing just how incongruent the previous decade’s data visualization tools are with paradigm-shifting technology. Large language models promise to make interacting and conversing with data easier than it has ever been before, but doing so in a way that’s trustworthy and actionable will require the kind of analytics platform we’ve spent a decade building. We promise to make those conversations meaningful, accurate, and actionable when it comes to analytics for our customers, partners, and the cloud ecosystem at large.”
“We’re seeing a flood of lightweight ChatGPT integrations in the market right now. What stands out about ThoughtSpot’s work is that it is more than just a cool demo,” said Donald Farmer, Principal at TreeHive Strategy. “They have carefully thought through the implications of LLMs for their architecture and user experience – and they have even taken consideration of what IT needs to know in order to provision, secure and govern these features. So yes, it’s a cool demo and a feature many will enjoy using. But it’s also the first serious enterprise implementation I have seen of these LLM features in a mainstream analytics platform.”
ThoughtSpot is the AI-Powered Analytics company. The ThoughtSpot mission is to create a more fact-driven world with the easiest to use analytics platform. With ThoughtSpot, anyone can leverage natural language search powered by large language models to ask and answer data questions with confidence. ThoughtSpot enables everyone within an organization to limitlessly engage with live data in any popular cloud data platform, making it easy to create and interact with granular, hyper-personalized, and actionable insights. Customers can take advantage of both ThoughtSpot’s web and mobile applications to improve decision-making for every employee, wherever and whenever decisions are made.