Knowledge graph database startup Stardog Union Inc. is flexing its muscles in artificial intelligence with the launch of a new, “hallucination-free” version of its enterprise-grade chatbot Voicebox, aimed at high-stakes industries.
Voicebox can be thought of as an “enterprise answer engine” that’s linked to an organization’s internal data, allowing it to respond to knowledge worker’s questions with extreme accuracy in real time. Stardog said it’s targeted at organizations in the most heavily regulated industries, such as financial services, healthcare and defense, enabling them to ask complex questions and receive answers that are based on their own data and fully traceable.
The chatbot leverages Stardog’s pioneering knowledge graph platform, which is a flexible and reusable data layer that can access information from across various disparate systems, including siloed databases and applications. It unites data from across the entire organization to power data analytics and other big data initiatives.
The knowledge graph stands out due to its dynamic nature, which allows it to capture the constantly changing nature of the data it taps into, so it’s always up to date. Moreover, because it stores data in a graph format, this allows it to better highlight the relationships between different data points, which is essential for AI models that need to understand context.
Stardog says Voicebox is essentially an additional AI layer built atop of its knowledge graph, powered by multiple agents that collaborate behind the scenes on tasks such as data discovery, integration, modeling and mapping. The idea is to provide knowledge workers with a user-controlled, self-service analytics experience that’s completely accessible via natural language commands. It’s supposed to enable everyone within an organization to carry out their own analytics operations and dig up better business insights, the company said.
Its underlying knowledge graph is also the reason behind the company’s claim that Voicebox is free of hallucinations, which some studies claim cost businesses an estimated $67 billion per year. Hallucinations are often said to be one of the main reasons why AI’s adoption has stalled in regulated industries, because they create an unacceptable level of risk.
The company’s knowledge graph utilizes what Stardog says is a “Safety RAG architecture,” which it claims is safer than traditional retrieval-augmented generation because it’s designed to ensure no hallucinations can slip through the cracks. Stardog says Safety RAG is also more expressive, because its knowledge graph allows it to build a more complete data environment, expanding its reach from unstructured data only to include traditional databases and other structured data types.
According to Stardog, Voicebox will never generate false responses. Instead, it will simply admit when it doesn’t know how to answer a specific question. When this happens, it will ask users to provide examples of “competency questions” so it can direct its agents to perform the necessary integrations, modeling and mapping to try and answer the original question.
Stardog founder and Chief Executive Kendall Clark said this kind of trust is essential in regulated industries, and allows Voicebox to cater to customers including the U.S. Department of Defense and the National Aeronautics and Space Administration.
“Ontologies are a core part of our platform and by providing a traceable and automated ontology creation process, we’re giving users more control over what data they’re drawing from and getting them critical organizational insights they can trust much more quickly than ever before,” Clark said. “Ontologies are powerful but in most organizations they’re an obstacle to insight; we’ve automated the process of creating them to speed time to insight for users.”
