The New Jersey Devils have launched “Bott Stevens,” a customized AI chatbot designed to reinforce digital fan engagement.
Named after Devils legend Scott Stevens, the chatbot is powered by Theta EdgeCloud’s (THETA) decentralized AI infrastructure and can be out there on the workforce’s official web site throughout the 2024-25 NHL season.
The AI agent will present followers with real-time info on sport schedules, tickets, stats, and merchandise. Using Theta’s Retrieval Augmented Era know-how, Bott Stevens will pull information from official NHL sources, making certain accuracy whereas avoiding misinformation from unverified sources.
Followers can ask the chatbot a variety of questions, corresponding to upcoming match particulars or season statistics, and obtain on the spot responses.
Bott Stevens can be powered by Theta EdgeCloud’s community of over 30,000 edge nodes and distributed GPUs, providing greater than 80 PetaFLOPS of computation energy.
This ensures scalability, even throughout peak demand, corresponding to playoffs or main workforce bulletins.
Past answering questions, the AI chatbot will provide historic highlights, sport recaps, venue info, and updates on workforce occasions. Over time, it might develop to incorporate predictive analytics for fantasy sports activities and interactive fan engagement instruments.
Q&A with Mitch Liu, CEO of Theta Labs
Q: How will Theta EdgeCloud’s decentralized design be certain that the chatbot can deal with peak demand throughout main occasions?
A: EdgeCloud’s decentralized design gives over 80 PetaFLOPS of on-demand distributed GPU compute energy, combining each cloud and edge computing units. Over 30,000 international edge units allow us to deal with peak utilization over the baseline capability supplied by cloud-based servers, and demanding in skilled and esports industries the place main occasions corresponding to playoffs and finals draw probably the most fan curiosity.
Q: How will “Bott Stevens” pull correct, real-time information from sources just like the NHL API? What safeguards forestall outdated or incorrect info? How will you retain RAG from being pulled from crowd-sourced and probably inaccurate sources?
A: The EdgeCloud back-end platform defines which information sources to drag information from, and this feeds into the real-time RAG database, so crowd-sourced or inaccurate sources might be prevented. As in most generative AI LLM fashions, the largest problem isn’t just getting correct real-time information from trusted sources however how that information is cleaned, ready and normalized so it may be effectively and precisely integrated into the mannequin.
Q: How will you guarantee information privateness and safety for customers interacting with the chatbot? Are you storing person information?
The chatbot doesn’t retailer or keep any person information past the person’s session, and in contrast to conventional chatbots like DeepSeek or ChatGPT, Theta chatbots are targeted on trade particular content material, for instance solely hockey associated info for the NJ Devils.
Q: Are there plans to develop “Bott Stevens” with options like predictive analytics? Do you need to take the tech any additional?
A: A giant space of improvement for us now’s extending the interactive RAG chatbot to develop into proactive agentic AI with numerous extendable actions, that’s unbiased and autonomous. For instance, with the ability to interface with customer support and CRM methods to mechanically create help tickets to enhance person satisfaction, and AI brokers that create “fantasy sports activities/esports groups” that may play towards customers to extend fan engagement and a step in the direction of predictive analytics for expertise identification, participant valuation, and opponent evaluation.
Q: What attracted Theta Labs to companion with the New Jersey Devils? What customization choices can be found for different groups or manufacturers?
A: Theta EdgeCloud has gotten good traction with skilled sports activities groups beginning with the Las Vegas Knights and esports groups together with FlyQuest and Evil Geniuses. The person interface is absolutely customizable and branded to be built-in into every workforce’s web site, cellular apps, Discord and different social channels. Extra importantly, the real-time information supply and APIs that feed into EdgeCloud’s RAG database is personalized to domain-specific info, corresponding to NHL hockey, esports video games like Valorant, League of Legends, workforce/league particular info, and extra.
Q&A with Marc Ciampa, Vice President of Content material of the NJ Devils
Q: How will the workforce promote “Bott Stevens” to drive fan engagement and adoption?
A: To advertise “Bott Stevens,” the Devils will combine promotion throughout a number of platforms to encourage fan interplay, “Bott Stevens” capabilities, and lift common consciousness.
Q: What varieties of curated content material will the chatbot provide past stats and schedules?
A: Past offering statistics and schedules, “Bott Stevens” will provide curated content material to counterpoint the fan expertise, together with historic highlights and occasion and venue info. “Bott Stevens” will reply questions on memorable moments from the workforce’s historical past, present particulars on upcoming occasions, theme nights, and so forth. within the Devils and live performance area, and provide complete particulars about Prudential Middle facilities. These facilities embrace accessibility companies, bag insurance policies, concession areas and ATM areas all through the venue.
Q: How will you measure the chatbot’s success in enhancing fan engagement or sharing related and correct stats/information?
A: We’ll measure success by way of person engagement metrics, accuracy charges, fan suggestions and help load discount. We plan to watch the variety of interactions, session durations, and repeat utilization, in addition to observe the precision of knowledge supplied, making certain that stats and information shared are right and up-to-date. We may also gather person suggestions by way of surveys to grasp satisfaction ranges and areas for enchancment and discover methods to measure the lower in inquiries dealt with by human help, indicating the chatbot’s effectivity in addressing frequent questions.
Q: As AI fatigue is rising amongst clients, how will you make “Bott Stevens” totally different from different AI brokers that your shoppers already ‘digitally’ meet each day?
A: By way of steady studying, human-like conversational tone, customized interactions, and making a chatbot ecosystem. We’ll implement machine studying algorithms that adapt to fan suggestions and evolving pursuits, making certain the chatbot stays related and interesting, in addition to design the chatbot’s communication type to be pleasant and relatable, enhancing the general person expertise. We glance to leverage AI to tailor responses primarily based on particular person fan preferences and behaviors, making every interplay distinctive. Finally, “Bott Stevens” can be out there in our app and tied to different key facets corresponding to our concession information, wayfinding and different issues we would consider down the road.
