Overview
Explore a comprehensive session that delves into Intercom's end-to-end journey of productionizing their Fin Chatbot, a breakthrough AI chatbot powered by large language models on Amazon Bedrock. Learn about critical aspects of successful generative AI deployments beyond proof of concept, including model selection and management, cost optimization, performance monitoring, and scalability in high-stakes production environments. Gain valuable insights into managing model access, balancing trade-offs, and future-proofing your AI strategy from experts Benoit de Patoul (AI/ML Specialist SA at AWS), Mario Kostelac (Staff Machine Learning Engineer at Intercom), and Damian Niezgoda (Senior Solutions Architect at AWS). This 37-minute talk provides practical knowledge for organizations looking to scale their generative AI implementations effectively using AWS services.
Syllabus
Intercom’s Best Practices for Scaling Generative AI on Amazon Bedrock | AWS Events
Taught by
AWS Events