ARIA is the World's First Generative AI-Powered Virtual Building Assistant Designed to Enhance Building Efficiency and Reduce Greenhouse Gas Emissions
Amazon Bedrock AgentCore now gives teams a native way to generate, validate, and test changes to agent behavior using traces, evaluations, configuration versions, and gateway-based A/B experiments. Caylent evaluated the feature through private-beta access. This article presents the results of those evaluations and what they mean for teams building on Bedrock.
Caylent’s Anthropic Consulting & Engineering (ACE) practice delivers the expertise, governance, and operating models enterprises need to move Claude into production at scale.
Explore Claude Opus 4.7, Anthropic’s most capable generally available model, with stronger agentic coding, high-resolution vision, 1M context, and a migration story that matters almost as much as the benchmark scores.
Irvine, Calif. [July 10, 2024] Caylent, an Amazon Web Services (AWS) Premier Tier Services Partner that enables companies to evolve their business through artificial intelligence (AI), cloud modernization, and data-backed solutions, today announced its contribution to the world’s first generative AI-powered solution that supports the reduction of energy consumption and greenhouse gas emissions in commercial buildings.
BrainBox AI, a pioneer in building technology, works with commercial real-estate owners and managers to improve the efficiency and sustainability of heating, ventilation and air conditioning (HVAC) systems using advanced AI. The company supports real-estate clients in various sectors, including office buildings, hotels, commercial retail, grocery stores, airports, and more. With the support of Caylent and AWS, BrainBox AI developed ARIA (Artificial Responsive Intelligent Assistant), an AI-powered assistant for intuitive HVAC and building data analytics and operations management. In building this solution, Caylent utilized Amazon Bedrock, a fully managed service that offers a choice of high-performing foundation models (FMs) from leading AI companies via a single API, along with a broad set of capabilities organizations need to build generative AI applications with security, privacy, and responsible AI. Caylent also leveraged Anthropic’s state-of-the-art model Claude for a conversational interface and generative AI capabilities, and deployed ARIA on AWS for seamless data ingestion, analysis, and reporting. ARIA, together with BrainBox AI’s core technology, can reduce HVAC energy costs by up to 25% and greenhouse gas emissions by up to 40%.
“The pathway to our generative AI innovation was made possible by working with Caylent and using Amazon Bedrock,” said Jean-Simon Venne, Chief Technology Officer & Cofounder, BrainBox AI. “Caylent has deep experience in Amazon Bedrock, industry-leading large language models (LLMs) including Anthropic’s Claude, and production-grade generative AI deployments. As a result, ARIA is an industry-defining technology, and together with our AI for HVAC solution, will have a momentous impact on furthering our mission to decarbonize and optimize the built environment with autonomous AI.”
“It’s exciting to see innovators like BrainBox AI and Caylent leverage the full breadth of AWS services in the development of a first-of-its-kind generative AI-powered virtual building assistant,” added Vasi Philomin, Vice President of Generative AI at AWS. “Built using Amazon Bedrock, BrainBox AI’s ARIA shows tremendous promise towards accelerating and improving the way building management understands and makes decisions around their HVAC and energy management systems.”
ARIA enables facilities managers and building operators to query and command their building's equipment, from rooftop units (RTUs) to chillers, boilers, and more through voice or text, transforming building data into precise insights and strategic actions in real-time.
In building ARIA, Caylent’s data and AI experts worked collaboratively with BrainBox AI’s CTO, data scientists, engineers, and DevOps specialists to understand BrainBox AI’s goals and plan out the deployment of AWS tooling for data ingestion, report generation, conversational interfacing, and autonomous action with HVAC systems. The solution uses multiple LLMs, including Anthropic’s Claude for the majority of workloads, which was chosen for its accuracy in generating SQL Queries from natural language. These are combined with BrainBox AI’s advanced algorithms and building data to provide complex data analytics and visualizations as well as generate performance and efficiency reports.
“One of the distinct benefits of Amazon Bedrock is the ability to efficiently switch between various LLMs,” said Randall Hunt, VP, Cloud Strategy and Innovation, Caylent. “By leveraging multiple types of compute across AWS Lambda and AWS Fargate, we’re able to fulfill user requests with the most efficient tool for various intents. ARIA is able to query thousands of data points and produce actionable results that enable building and facilities managers to responsibly drive energy usage towards a more sustainable future.”
“We’re proud to be collaborating with BrainBox AI and AWS in putting generative AI to work in the pursuit of reducing greenhouse gas emissions,” said Lori Williams, CEO, Caylent. “Our goal at Caylent is to continually help clients evolve their business, and in this case, evolve industry benchmarks and standards for sustainability.”
For more information, read our case study.
About Caylent
Caylent is a cloud native services company that helps organizations bring the best out of their people and technology. We are living in a software-defined world where technology is at the core of every business. To thrive in this paradigm, organizations need to empower their people and processes through technology. Caylent is uniquely positioned to fuel that engine of innovation by bringing ambitious ideas to life for our customers. We work with customers to build, scale and optimize sophisticated cloud solutions using deep subject matter expertise to deliver world-class outcomes through an agile co-delivery model.
Caylent achieved the AWS Generative AI Competency in 2024 and was named Application Modernization Partner of the year in 2023, Innovation Partner of the Year in 2022 and Rising Star Partner of the Year in 2021 by AWS. Caylent’s core practice areas include Migration, Application Modernization, Data and Analytics, Machine Learning, Artificial Intelligence, Cloud Native Application Development, and DevOps. Learn more at https://caylent.com/.
Caylent Team