Fast-track GenAI success: Coveo launches Passage Retrieval API for secure, more relevant AI experiences

- Passage Retrieval API enhances accuracy, relevance, and security, reducing hallucinations and protecting sensitive data for smarter, more reliable GenAI applications

- Proven with global enterprises, new Passage Retrieval API accelerates time-to-value with industry-leading retrieval

MONTREAL and SAN FRANCISCO, Feb. 6, 2025 /PRNewswire/ - Coveo (TSX: CVO), the market leader in AI-Relevance — delivering AI-search, generative, and business-aware relevance at every point-of-experience, today announced that the Coveo Passage Retrieval API, a headless retrieval method for generative AI applications that leverages the Coveo's best-of-breed AI-Relevance Platform^TM, is now generally available.

Coveo's Passage Retrieval API: Strategic and critical for enterprises' GenAI success

"Enterprises today are challenged with turning vast amounts of fragmented data into accessible and relevant knowledge for generative and conversational AI," said Laurent Simoneau, Co-Founder, President and CTO at Coveo. "While large language models (LLMs) hold immense potential, their success hinges entirely on the quality of the data they access—a growing concern as many enterprises develop their own GenAI applications. Many organizations are adopting Retrieval-Augmented Generation (RAG) and quickly realizing that the hardest part—the 'R'—lies in retrieving precise and relevant information from scattered enterprise systems. This critical step ensures secure, accurate, and relevant AI responses, yet its complexity often hinders progress."

Coveo's Passage Retrieval API directly addresses this challenge by delivering precise, trustworthy text to LLMs and AI applications, including Salesforce Agentforce, Microsoft Copilot, Amazon Bedrock Agents, and SAP Joule. The API boosts accuracy, minimizes hallucinations, and meets enterprise security requirements, all while improving deployment speed and reducing costs. Organizations can, therefore, consistently scale multiple generative AI applications using a single, reliable retrieval method.

A Unified Index for All Your GenAI Needs

With Coveo's proven information retrieval method and advanced relevancy and ranking techniques now available to power generative AI applications, organizations can ground results in enterprise knowledge with greater efficiency and significantly accelerate time-to-value. Coveo's platform centers on an industry-leading unified index that combines advanced ranking techniques—lexical, vector-based, and behavioral—to securely connect data from systems like CRMs, ERPs, ITSMs, and CMSs using prebuilt connectors. This eliminates redundant indexing and integration work, cutting maintenance costs while supporting a wide range of AI applications such as search, recommendations, generative AI and content discovery.

Designed to scale seamlessly, the platform handles large data sets, high user volumes, and multiple applications. With hybrid semantic and lexical indexing, machine learning models like Automatic Relevance Tuning (ART), and personalized ranking, as well as control over weighting factors and business rules in the query pipeline, Coveo continuously improves retrieval results, ensuring enterprise-wide AI performance that evolves with each user interaction.

Early Access Program Sees Impressive Results

Early Access Program customers saw impressive results. One Fortune 500 software organization that implemented Coveo's Passage Retrieval API reported that in only 2 weeks they were able to improve article and passage retrieval accuracy by 22% over their in-house retrieval tool which led to a 73% improvement in generated answer accuracy of their internal GenAI chatbot.

"Integrating Coveo's Passage Retrieval API has improved our ability to deliver highly customized AI solutions," said Eric Immermann, Search and Content Practice Director at Perficient, a close System Integration partner of Coveo who tested the Passage Retrieval API during our Early Access Program. "From automating sales queries and enhancing global search experiences for our clients, to powering our own internal RFI generation tool, we've seen how better relevance in generative answering drives efficiency and business value. With Coveo's unified hybrid index, we can improve answer relevance across various GenAI applications — making AI adoption faster, easier, and more cost-effective for us and our clients."

Unlocking Possibilities: Top Use Cases for Coveo's Passage Retrieval API

• Custom GenAI Experiences: Improve the reliability and security of any generative AI application by providing your LLM with the most relevant passages from unified enterprise content sources.
• Chatbots and Virtual Agents: Improve the relevance of the answers from your chatbots, co-pilots, and agentic AI applications so your users experience personalized and context-rich conversations.
• Internal Knowledge Management: Empower employees with personalized, accurate answers grounded in enterprise knowledge, reducing search time and boosting productivity.
• Customer-Facing Support & Case Deflection: Provide precise self-service answers cited from support knowledge that minimize escalations, lower support costs, and boost customer satisfaction.

Discover the power and versatility of the Coveo Passage Retrieval API. Whether you're working with AI platforms like Salesforce Einstein, Microsoft Azure AI, AWS Bedrock, or IBM Watson; LLM models such as Google Gemini, Anthropic Claude, and OpenAI GPT-4o; or AI agents like Salesforce Agentforce, Microsoft Copilot, Amazon Q Business, and SAP Joule, our API ensures more relevant answers and enhanced user experiences. Explore our blog to learn more.

Just getting started with RAG? Learn how Coveo's advanced search and retrieval solutions can elevate your RAG strategy for precision and speed. Watch the webinar on-demand or join us at our next Relevance 360 virtual event, register here.

About Coveo

Coveo brings superior AI-Relevance to every point-of-experience, transforming how enterprises connect with their customers and employees to maximize business outcomes.

Relevance is about moving from persona to person, the degree to which the enterprise-wide content, products, recommendations, and advice presented to a person online aligns easily with their context, needs, preferences, behavior and intent, setting the competitive experience gold standard. Every person's journey is unique, and only AI can solve the complexity of tailoring experiences across massive, diverse audiences and large volumes and variety of content and products.

Our Coveo AI-Relevance Platform™ ️enables enterprises to deliver hyper-personalization at every point-of-experience, unifying all their data securely, with the highest level of contextual and prescriptive accuracy while simultaneously optimizing business outcomes.

Coveo brings AI-Relevance to the digital experiences of many of the world's premier and most innovative brands, serving millions of people across billions of interactions.

What we believe is bold: Digital is table stakes, Relevance is not. It's the only way to win in the digital age.

The Coveo AI-Relevance Platform™ is ISO 27001 and ISO 27018 certified, SOC2 compliant, HIPAA compatible, with a 99.999% SLA available. We are a Salesforce ISV Partner, an SAP Endorsed^Ⓡ App, an Adobe Gold Partner, MACH Alliance member, Optimizely Partner, Shopify Partner, and a Genesys AppFoundry^Ⓡ ISV Partner.

Coveo is a trademark of Coveo Solutions Inc.

Stay up to date on the latest Coveo news and content by subscribing to the Coveo blog, and following Coveo on LinkedIn and YouTube.

Forward-Looking Information

This press release contains "forward-looking information" and "forward-looking statements" within the meaning of applicable securities laws (collectively, "forward-looking information"). This forward-looking information is identified by the use of terms and phrases such as "may", "would", "should", "could", "might", "will", "achieve", "occur", "expect", "intend", "estimate", "anticipate", "plan", "foresee", "believe", "continue", "target", "opportunity", "strategy", "scheduled", "outlook", "forecast", "projection", or "prospect", the negative of these terms and similar terminology, including references to assumptions, although not all forward-looking information contains these terms and phrases. In addition, any statements that refer to expectations, intentions, projections, or other characterizations of future events or circumstances contain forward-looking information. Statements containing forward-looking information are not historical facts but instead represent management's expectations, estimates, and projections regarding future events or circumstances.

Forward-looking information is necessarily based on a number of opinions, estimates, and assumptions that we considered appropriate and reasonable as of the date such statements are made. Although the forward-looking information contained herein is based upon what we believe are reasonable assumptions, actual results may vary from the forward-looking information contained herein. Moreover, forward-looking information is subject to known and unknown risks, uncertainties, and other factors, many of which are beyond our control, that may cause the actual results, level of activity, performance, or achievements to be materially different from those expressed or implied by such forward-looking information, including but not limited to macro-economic uncertainties and the risk factors described under "Risk Factors" in the Company's most recently filed Annual Information Form available under our profile on SEDAR+ at www.sedarplus.ca. There can be no assurance that such forward-looking information will prove to be accurate, as actual results and future events could differ materially from those anticipated in such information. Accordingly, prospective investors should not place undue reliance on forward-looking information, which speaks only as of the date made.

Moreover, we operate in a very competitive and rapidly changing environment. Although we have attempted to identify important risk factors that could cause actual results to differ materially from those contained in forward-looking information, there may be other risk factors not presently known to us or that we presently believe are not material that could also cause actual results or future events to differ materially from those expressed in such forward-looking information.

Except as required by law, we do not assume any obligation to update or revise any forward-looking information, whether as a result of new information, future events, or otherwise, after the date on which the statements are made or to reflect the occurrence of unanticipated events.

SOURCE Coveo Solutions Inc.