Join top executives in San Francisco July 11-12 to hear how leaders are integrating and optimizing AI investments for success. Learn more
Stravio, an enterprise analytics firm, is introducing proprietary generative AI capabilities to its platform to streamline enterprise knowledge management. The goal is to streamline the research experience by providing transparent answers, complemented by clickable links to source documents for fact checking.
While Dropbox and Box recently introduced similar offerings that let users conduct general keyword searches within documents and ask questions about the content, Stravito said it sets itself apart by providing information from more relevant sources.
Instead of offering a single response per document, Stravito’s response engine offers a comprehensive analysis. Additionally, the company says its response engine is adept at handling complex datasets, even when they present conflicting information. For example, the engine will identify and highlight discrepancies if different sources provide different numbers.
“Our solution is designed to help users avoid bias by providing context and will not just share yes/no binary answers, but will share more details, prompting more questions for follow-up research,” Thor Olof Philogène, CEO and Founder by Stravito, he told VentureBeat. “Answers are generated based on proprietary knowledge, not unverified internet data, and sensitive customer information remains within the trusted corporate cloud environment.”
Improving traditional search through generative AI
The company said its generative AI uses a client company’s internal knowledge base to generate responses. The tool will explicitly communicate if the platform lacks relevant knowledge to answer a question. However, the user can still receive related context and existing information from the knowledge base.
>>Follow VentureBeat’s continued coverage of generative AI<
According to Philogène, while generative AI is exciting and promising, human intervention remains crucial. He emphasized that AI-generated summary answers should serve as a starting point, allowing users to quickly grasp key points, rather than being treated as the definitive answer to a question.
“The direct links to the source documents make it easier to check facts as well as dig deeper and uncover important nuances in the data,” Philogène told VentureBeat. “That’s why Stravito’s AI capabilities not only provide links to sources, but also explicitly highlight the exact paragraphs that were used to generate the response.”
He said that in the realm of consumer insights and market research, the quality of answers depends heavily on the questions asked.
“While asking the right question is a valuable skill, not all business stakeholders possess it, despite researchers investing a lot of time in developing this skill,” explained Philogène. “The questions recommended by our AI aim to solve both of these challenges: to motivate users to continue exploring and learn more, but also to help them ask better questions to get more concrete and useful answers for further decisions.”
Philogène said his company has a strong focus on reliability, data privacy and security in line with stringent business requirements, as the platform runs on enterprise cloud solutions with a Type II SOC 2 ratio.
“The agreements we have in place cover confidentiality, data ownership and intellectual property (so that no service provider uses customer content to train their model). As an ISO 27001 certified organization, we ensure high data privacy and security for our new generative AI features, just like for the rest of our platform,” she said.
What is the future of Stravito?
The company said it will continue to build generative AI capabilities based on customer feedback and needs, and plans to introduce several enhancements to the platform, including source control that allows users to exclude unwanted documents from response generation. Additionally, Stravito aims to integrate Generative AI into existing workflows, such as Scrapbooks.
The company is exploring other areas to expand into. These include providing concise one-page summaries for loaded research, optimizing the desk research process through new production capabilities, and creating automatically generated summaries tailored to each user’s preferences.
“In the near future, AI-powered communication will enable us to have meaningful interviews and get personalized help from virtual assistants. At the same time, both new interfaces (from suppliers) and new skills (from users) will be needed to make this cooperation smooth and effective,” said Philogène. “At Stravito, we are very excited about the developments in generative AI and we look forward to the game-changing developments we believe will take place in the market over the coming months and years.”
>>Don’t miss our special issue: Building the Foundation for Customer Data Quality.<
VentureBeat’s mission it is to be a digital city square for technical decision makers to gain insights into transformative business technology and transactions. Discover our Briefings.