The emergence of artificial intelligence has raised expectations for enterprise search, but the results do not always inspire confidence.

Users may encounter fragmented or irrelevant search results or receive answers that lack the context or security controls needed to determine whether the information is accurate.

Coveo Solutions Inc. is addressing these challenges through its AI-Relevance Platform, which combines search, recommendations and generative AI across commerce, customer service, websites and digital workplaces. The platform is available through AWS Marketplace.

“We help people find things that they’re looking for,” said Peter Curran (pictured), chief product officer of Coveo. “People don’t want to issue a query and see a bunch of documents or results that they have to interrogate. They want to ask a question, and they want to get an answer. We bring all of that context and security and accuracy to bear, ground the answer in truth and give them an answer they can rely on.”

Curran spoke with theCUBE Research’s John Furrier during an interview for the AWS Marketplace Series on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed the role of relevance, context and security in helping enterprises retrieve information from large and often disconnected content repositories. (* Disclosure below.)

Bringing context to enterprise search

Grounding search results in authoritative enterprise information is a central part of Coveo’s approach. The company’s AI-Relevance Platform uses real-time intent signals, dynamic reranking and continuous learning from user behavior to tailor results across different enterprise use cases.

“In general, we’re not talking about which cocktail dress I should wear to this party or what’s the best color to paint my bedroom,” Curran said. “We’re helping doctors find the right stent for an operation. We’re helping companies put a hydraulic pump into a bulldozer that allows road construction to continue. It’s not just about giving an answer. It’s about giving the right answer that allows somebody to move on with their work.”

Coveo is also extending its retrieval technology to agentic AI systems. Its Relevant Retrieval offering is designed to give AI agents access to information distributed across enterprise systems while applying the context and permissions associated with that content.

“We were very quick to integrate Model Context Protocol as a standard in Coveo,” Curran explained. “We think about how an autonomous non-human agent would interact with the content repository that we’re indexing. We’ve thought hard about how we give an agent the confidence that we’re answering its question accurately the same way we think about how we do that for humans.”

At the center of the platform is the Coveo Unified Index, a cloud-based repository that ingests and normalizes structured and unstructured information from disparate enterprise systems. This creates a common framework through which users and AI applications can retrieve relevant content.

“We think that this is an environment that needs to be unified,” Curran told theCUBE. “People don’t want to go to an e-commerce portal separate from a service portal. They want to go to one place because most questions touch both. They want to ask a question, have it find the right product and then get on with their production operation. That’s where we’re focused.”

Here’s the complete video interview, part of SiliconANGLE’s and theCUBE’s coverage of the AWS Marketplace Series:

(* Disclosure: TheCUBE is a paid media partner for the AWS Marketplace Series. Neither AWS, the sponsor of theCUBE’s event coverage, nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE