Coveo (TSX:CVO), an AI platform that makes every digital experience relevant, 1:1 personalized and profitable, announced today Coveo Relevance Generative Answering. This new Generative AI question answering capability combines Large Language Models (LLMs) on top of the leading secure unified indexing capabilities of Coveo’s AI platform. This makes generative answering using LLMs applicable within enterprises, where security, privacy, real-time sources of truth, relevance and factuality are all key imperatives.
“Large Language Models (LLMs) such as ChatGPT and alternatives have taken the world by storm. Despite their current shortcomings for use in the enterprise (misinformation, hallucinations, no personalization, expensive training costs, lack of privacy and security, and questionable ethics, among others), we anticipate that demand for Generative AI question answering experiences will become ubiquitous in every digital experience, including in commerce and customer service. In the enterprise, we believe that search and generative question-answering need to be integrated, coherent, based on current sources of truth with compliance for security and privacy, providing relevant answers every time,” said Laurent Simoneau, President, CTO and Co-Founder of Coveo. “We are confident that Coveo’s very unique position to leverage our unmatched expertise in AI and ability to build on the power of our Coveo AI platform to make these LLM capabilities enterprise ready.”
Coveo has been developing with and deploying LLM capabilities with customers for a few years, delivering different capabilities such as case classification and question answering through smart snippets.
The Coveo Relevance Generative Answering, a new capability within the Coveo Relevance Cloud™ AI platform, will be available for customers with self-service use cases this summer, followed by other use cases in customer service, commerce, website and workplace search. This capability will leverage multiple LLMs, depending on the use case, to deliver the best answer. Coveo Relevance Generative Answering will combine these LLM technologies with its own powerful enterprise search and relevance technology using strategies like Retrieval Augmented Generation (RAG).
For example, in a self-service use case, Coveo already creates a unified index of all customer service and knowledge documents within an enterprise, wherever they live, and keeps them fresh, secure, and private. When a specific user searches for an answer, it will search this unified index, with the security that this user has access to, and return the most relevant content for the context of this user. Coveo Relevance Generative Answering will then use an LLM to summarize that relevant content corpus and create a personalized answer, respecting the company’s privacy and security, and provide citations to the original documents to provide the source of truth, both key imperatives for enterprise use.
“At Coveo, we understood a long time ago that there would be a shift from traditional search experiences to AI-powered digital experiences, and that’s why we have been investing in AI technology for more than a decade,” said Louis Têtu, Chairman and CEO. “We have built a market-leading AI platform, the Coveo Relevance Cloud™, working closely with more than 625 leading enterprises around the world, building AI models on massive and complex data sets to pioneer the paradigm shift between traditional search and AI experiences (answers, recommendations, 1:1 personalization, etc.). We believe innovations like Coveo Relevance Generative Answering once again lead the market by solving key challenges for enterprises and will help our customers improve their end customer and employee satisfaction, increase customer loyalty, reduce costs, and grow profits.”