AWS Fargate
3 use cases using this technology
Ferrari Advances Generative AI for Customer Personalization and Production Efficiency
Ferrari S.p.A.
Ferrari built a car configurator on AWS using LLMs in Amazon Bedrock and Amazon Personalize, letting customers personalize their vehicle across millions of possible configurations with 3D visualization, which increased sales leads and cut configuration times by 20%. Ferrari also fine-tuned Amazon Titan, Claude 3 and Llama models in Bedrock (combined with Amazon SageMaker JumpStart) on its own documentation to power an after-sales generative AI chatbot that classifies and summarizes customer care tickets, and uses Amazon Lookout for Vision to automate quality inspection and defect detection on the assembly line. Generative AI is also used to run vehicle design simulations and text-to-image prototyping to reduce reliance on physical prototypes.
CarbonTrail cuts generative AI costs by 88% for sustainable emissions intelligence using Amazon Bedrock
CarbonTrail
New Zealand-based CarbonTrail built an AI-powered emissions measurement platform and CarbonAPI on AWS, running a document-analysis pipeline on Amazon Bedrock and workloads on AWS Inferentia to process bank-scale invoice and transactional data. The platform achieves an 87% reduction in processing time and 88% lower cost than a comparable GPT-4-with-embeddings approach, and reduces low-confidence classifications by up to 40%. The Bank of New Zealand (BNZ) uses CarbonTrail's CarbonAPI to progress toward measuring emissions across its SME customers.
NewDay lifts generative AI agent-assist accuracy from 60% to over 90%
NewDay
NewDay, whose contact centre handles 2.5 million calls a year, built NewAssist, a generative AI assistant on Amazon Bedrock using Retrieval Augmented Generation, out of an internal hackathon. Through iterative experiments — including a custom parser for its knowledge base and injecting internal acronyms into prompts — NewDay raised NewAssist's accuracy from below 60% to over 90%, cut the average time to retrieve an answer from 90 seconds to 4 seconds, and rolled it out to over 150 agents, running on serverless AWS infrastructure for under $400 a month.