Mo, an AI Chatbot Powered by Morningstar Intelligence Engine, Debuts in Morningstar Platforms

Morningstar, Inc., a leading provider of independent investment insights, launched a beta version of its generative artificial intelligence chatbot named “Mo” across Morningstar Investor, Research Portal, Direct, and Advisor Workstation platforms. Powered by the Morningstar Intelligence Engine, a platform that pairs Morningstar’s extensive investment research library with Microsoft’s Azure OpenAI Service, Mo is designed to surface and summarize Morningstar’s independent insights in a conversational format for investors and investment professionals.

Investors face an overwhelming amount of information amid a growing sea of more than 750,000 investment options. With the power of large language models and other AI tools, navigating large volumes of information can be made dramatically easier. Instead of working with keyword searches and pages of results, Morningstar customers can now ask questions directly to Mo and receive back a concise response within a matter of seconds. Mo does not provide investment advice.

AiThority: How AI Can Improve Public Safety

“AI has huge potential to support a better investor experience at scale, and this is just the beginning,” said James Rhodes, Morningstar’s chief technology officer and president of Data, Research, and Enterprise Solutions. “Mo is a digital research assistant that uses the power of the Morningstar Intelligence Engine to put Morningstar’s research just a question away. We look forward to learning how people interact with the beta so we can improve and expand its capabilities to make the day-to-day investing experience better.”

Mo is the first of several applications planned to be built on the Morningstar Intelligence Engine platform, which draws from Morningstar’s breadth of equity and managed investment research, editorial, and ratings. This extensive content library enables Mo to construct relevant responses by concisely summarizing information on a multitude of investment-related topics.

When a user types a question into Mo, it is routed to the Morningstar Intelligence Engine. The Engine is built on a Morningstar database that stores embeddings from Morningstar content. When Mo receives a user’s question, the Morningstar Intelligence Engine identifies the most responsive content to provide to OpenAI’s large language model to construct a response. The response is then tested for relevance and responsiveness, before being fed back to the user. Morningstar chose to work with Microsoft’s Azure OpenAI Service because of Microsoft’s commitment not to allow user data to train the OpenAI large language model. In keeping with Morningstar’s commitment to privacy, users are instructed not to input personal or confidential information into Mo.

Read More: The Practical Applications of AI in Workplace

This launch into Morningstar products follows a warm reception for the digital avatar and voice-recognizing representation of Mo that was first debuted at last month’s Morningstar Investment Conference. Morningstar CEO Kunal Kapoor conversed with Mo on the main stage, pointing to future potential for AI to synthesize investing insights, automate tasks, and provide in-software help. Conference-goers asked Mo more than 1,000 questions themselves, ranging from topics such as investing terms, saving for retirement, Morningstar ratings for specific securities, Morningstar’s take on emerging asset classes, and various market outlooks. While AI tools and large language models are still early in their development, broadening access to the beta version of Mo will allow the firm to further define and develop its usefulness.

Since its founding, Morningstar has been responsibly pairing the expertise and contrarian calls of humans with the speed and innovation of machines. Morningstar.com launched in 1997 to democratize access to investing insights previously only available to wealthy institutional investors. As recently as this month, the Morningstar Medalist Rating rolled out to combine forward-looking screening capabilities across what was previously known as the human-driven Morningstar Analyst Rating with the algorithmic and machine-learning-based Morningstar Quantitative Rating.

Latest Insights: What Techniques Will Deliver for Measuring Attention in 2023?

[To share your insights with us, please write to sghosh@martechseries.com]