The New Jersey Devils have launched ‘Bott Stevens’, an adapted AI chatbot that is designed to improve the involvement of digital fans.
Named after Devils legend Scott Stevens, the chatbot is powered by the decentralized AI infrastructure of Theta Edgecloud (Theta) and will be available on the team’s official website during the NHL season 2024-25.
The AI ​​agent offers fans real-time information about game schedules, tickets, statistics and merchandise. Bottels use use of Theta’s Retrieval Augmented Generation Technology and will extract data from official NHL sources, which guarantees accuracy and avoiding wrong information from non -rewarded sources.
Maybe you also like it: Crypto exchange Deribit warns against job coctors with fake recruiter profiles
Fans can ask the chatbot a number of questions, such as upcoming competition details or seasonal statistics, and receive immediate answers.
Bott Stevens is driven by the network of Theta Edgecloud of more than 30,000 peripheral nodes and distributed GPUs, which offers more than 80 petaflops of calculation capacity.
This ensures scalability, even during peak demand, such as play -offs or important team announcements.
In addition to answering questions, the AI ​​-Chatbot offers historical highlights, game recaps, location information and updates on team events. In the course of time it can expand to predictive analyzes for fantasy sports and interactive tools for fan engagement.
Maybe you also like it: Privy protects more than $ 40 million in financing to expand the crypto infrastructure
Q&A with Mitch Liu, CEO of Theta Labs
Question: How will the decentralized design of Theta Edgecloud ensure that the chatbot can handle the peak demand during major events?
A: The decentralized design of Edgecloud offers more than 80 petaflops from on-demand distributed GPU calculation, where both cloud and edge computer devices are combined. More than 30,000 Global Edge devices enable us to process peak use about the basic capacity provided by cloud-based servers, and critically in professional and eSports industry where large events such as play-offs and finals attract the most fan interest.
Question: How will “Bott Stevens” accurate, real -time data from sources such as the NHL API draw? What guarantees occur outdated or incorrect information? How do you prevent RAG from being drawn from crowd-sourced and possibly inaccurate sources?
A: The back-end platform of Edgecloud determines which data sources must get data, and this feeds on the real-time rag database, so that crowd-sourced or inaccurate sources can be avoided. As in most generative AI LLM models, the biggest challenge is not only accurate real-time data from trusted sources, but how that data is cleaned, prepared and normalized, so that it can be included efficiently and accurately in the model.
Question: How do you ensure data privacy and security for users who communicate with the chatbot? Do you store user data?
The chatbot does not store or does not store user data outside the user’s session, and unlike traditional chatbots such as deep chat or chatgpt, theta chatbots are aimed at industrial specific content, for example only hockey -related information for the NJ Devils.
Q: Are there plans to expand “Bott Stevens” with functions such as predictive analyzes? Do you want to continue the technology?
A: A large development area for us now is expanding the interactive rag chatbot to become proactive agent AI with various expandable actions, which is independent and autonomous. For example, if you can communicate with customer service and CRM systems to automatically create support sticks to improve user satisfaction, and AI agents who make “Fantasy Sports/Esports teams” who can play against users to create the involvement of fans and a step towards predicting analyzes for talent identification, player evaluation and opponents evaluation and player evaluation and player evaluation and opponents valuation, and play -on evaluation and opponentysises.
Question: What did Theta Labs attract to collaborate with the New Jersey Devils? Which adjustment options are available for other teams or brands?
A: Theta Edgecloud has received a good traction with professional sports teams, starting with the Las Vegas Knights and Esports teams, including Flyquest and Evil Geniuses. The user interface is fully adaptable and branded to be integrated into the website of each team, mobile apps, disagreement and other social channels. What is even more important is that the real-time data source and APIs feeding in the RAG database of Edgecloud is adapted to domain-specific information, such as NHL hockey, eSports games such as Valorant, Legends, Team/League-specific information and more.
Maybe you also like it: Multibank Group who reportedly launches the launch of MBG -Token plans
Q&A with Marc Ciampa, vice -president of the content of the NJ Devils
Question: How does the “Bott Stevens” team promote to stimulate fans’ involvement and adoption?
A: To promote ‘Bott Stevens’, the Devil’s promotion will integrate on multiple platforms to encourage fan interaction, ‘Bott Stevens’ possibilities and to increase general consciousness.
Q: What types of composite content does the chatbot offer out of statistics and schedules?
A: In addition to providing statistics and schedules, “Bott Stevens” offers compound content to enrich the fan experience, including historical highlights and event and location data. “Bott Stevens” answers questions about memorable moments in the history of the team, gives details about upcoming events, theme -evenings, etc. In The Devils and Concert Space, and offers extensive details about Prudential Center facilities. These facilities include accessibility services, pocket policy, concession locations and ATM locations in the entire location.
Question: How are you going to measure the success of the chatbot in improving fan engagement or sharing relevant and accurate statistics/data?
A: We will measure success through user involvement statistics, accuracy percentages, feedback from fans and support support support. We are planning to check the number of interactions, session duration and repeat use, and to follow the precision of the information provided, to ensure that statistics and shared data are correct and up -to -date. We will also collect user feedback via surveys to understand satisfaction and areas for improvement and find ways to measure the decrease in investigations that are treated by human support, indicating the efficiency of the chatbot when answering common questions.
Question: As AI fatigue grows among customers, how will you make “Bott Stevens” different from other AI agents who already meet your customers ‘digitally’ daily?
A: Through continuous learning, human-like conversation tone, personalized interactions and creating a chatbot ecosystem. We will implement machine learning -algorithms that adapt to feedback from fans and evolving interests, ensure that the chatbot remains relevant and fascinating, and designing the chatbot communication style to be friendly and recognizable, which improves the overall user experience. We look at the use of AI to fit reactions based on individual fan preferences and behavior, making every interaction unique. Ultimately, “Bott Stevens” will be available in our app and be connected to other important aspects such as our concession guide, wayfinding and other things that we might think of.
