Speakers

Phil Birch
SkySpark Team Lead, ENFRA
BIO: I started 10 years ago as an application engineer, working on Andover Continuum and Niagara Ax systems. Two years into my career, I moved into working on SkySpark, developing arcs, sparks, and KPIs. Since then, I have spent the past 8 years working within every aspect of SkySpark development. I am currently a Software Development Manager for ENFRA Solutions.
ABSTRACT: SkySpark at Scale: Best Practices for Fast, Reliable Delivery
Delivering your development team’s innovations to clients quickly and reliably is key to maximizing impact. In this session, we’ll explore proven strategies for managing large-scale SkySpark deployments—shortening release cycles, tightening feedback loops, and improving system resilience. Learn how to implement CICD pipelines, optimize server infrastructure, and adopt scalable practices that empower your team to move faster without sacrificing quality. Whether you’re expanding your portfolio or refining your delivery model, these insights will help you unlock the full potential of SkySpark at scale.

Jason Briggs
CEO, XetoBase
BIO: A key player in the founding of Project Haystack, Jason Briggs is a visionary entrepreneur and passionate innovator. At just 21 years old, Jason co-founded Controlworks, a systems integration company recognized for completing one of the largest building automation system (BAS) installations in Las Vegas at the time. He went on to found J2 Innovations in 2009. Under his leadership, the company developed the acclaimed product, Fin Stack, which has played a key role in the growth and success of the company.
Today, Jason continues his entrepreneurial journey as a proud founding member of Novo Studio, a venture studio that specializes in nurturing and supporting startups in the smart building space. He is excited to make a lasting impact in the industry and help other entrepreneurs achieve similar success.

Philip Buonomo
VP Product Development, Intellastar
BIO: Philip Buonomo is VP of Product Development at Intellastar. With over ten years of experience in the IoT space, Philp is responsible for delivering Intellastar’s best-in-class products, including Energy Analyst, Edgevisor, and T-Star hardware platform. Intellastar enables partners to reduce costs, boost resilience, and meet evolving regulatory and sustainability goals.
ABSTRACT: Analyzing Energy Costs and Responding Intelligently to Volatile Pricing and Economic Opportunity
Intellastar’s Energy Analyst is a solution designed to help organizations analyze energy costs and respond intelligently to volatile pricing and economic opportunity. Data is recorded by T-Stars from meters, Distributed Energy Resources, and facility systems, to deliver insights and responses that reduce peak demand charges and deliver Demand Response participation results in real time. Data is streamed to dashboards for KPI tracking, forecasting, and reporting that is tailored for decision-makers.
In this session, we’ll explore how Energy Analyst delivers measurable results in commercial and industrial facilities at the site and portfolio level through predictive models and automated responses. Included will be a showcase of NYISO ICAP and PJM’s PLC reduction by data analysis and automated responses for load reduction, BESS dispatch, and EVSE management. The session’s emphasis will be placed on the platform’s reports, predictive modeling, market data integrations, and alerting mechanisms during economic opportunities that drive savings and generate new income for facilities.
Attendees will learn how resilient and modular energy strategies that leverage edge computing and market integration can be used to reduce costs and generate new revenue from their managed assets.

Juan Colon
ENFRA
BIO: I have been nearly 3 years with Enfra. I have grown from a Support Specialist into a key member of the development team. My background in Computer Science provides the foundation for my current responsibilities, which include developing custom applications used by our engineers and working directly with clients to solve complex device integration challenges. I am passionate about creating tools that empower both our team and our customers.
ABSTRACT: SkySpark at Scale: Best Practices for Fast, Reliable Delivery
Delivering your development team’s innovations to clients quickly and reliably is key to maximizing impact. In this session, we’ll explore proven strategies for managing large-scale SkySpark deployments—shortening release cycles, tightening feedback loops, and improving system resilience. Learn how to implement CICD pipelines, optimize server infrastructure, and adopt scalable practices that empower your team to move faster without sacrificing quality. Whether you’re expanding your portfolio or refining your delivery model, these insights will help you unlock the full potential of SkySpark at scale.

Uri Craimer
Data Analyst, Dual Fuel
BIO: Uri Craimer is a 23-year-old software engineer at DualFuel, based in Israel. New to the energy technology industry, he works primarily with Python and SkySpark to develop data-driven tools for smarter, more efficient building and energy management.
ABSTRACT: Custom Alarms in the Real World
As the number of monitored buildings and systems continues to grow, maintaining reliable and centralized alarm management becomes increasingly critical. This presentation introduces Dual Fuel’s scalable Alarm Engine, designed and implemented within the SkySpark platform. Leveraging SkySpark’s existing data infrastructure and event framework, the Alarm Engine enables centralized control, seamless historization, and intelligent distribution of alarms across multiple buildings.
The system integrates native user management, allowing flexible subscription options based on site, system, or alarm type, and supports multi-channel notifications via text, email, or phone. Its fully customizable architecture, powered by Axon logic, provides adaptability for complex workflows and evolving operational needs.
By unifying alarm processing, event tracking, and user notification under one SkySpark-based solution, the Alarm Engine establishes a robust foundation for scalable, efficient, and transparent building monitoring.

Allison Fitzpatrick
CoFounder and CEO, Actuate
BIO: Allison Fitzpatrick is the co-founder and CEO of Actuate, a company bridging the gap in building automation for portfolios of small-to-midsize commercial facilities. Allison brings over 17 years of experience in energy efficiency, renewables, and data analytics within the built world, and has led Actuate from concept to commercialization. Her work centers on making smart building solutions accessible to the 80% of commercial facilities that operate without traditional BAS systems or on-site facilities managers.
ABSTRACT: Using SkySpark from Scratch—Solutions for the 80% of Buildings without a BAS or Building Engineer
Over 80% of commercial buildings in the U.S. lack a BAS and on-site building staff, leaving operators without visibility or control. This session explores how we used SkySpark to build a modern, full-featured building management system from scratch, purpose-built for portfolios of small-to-mid-sized buildings.
We’ll highlight the distributed architecture we deploy, plus how applying best practices such as structured tagging from the outset enables scalable analytics and portfolio-wide control logic.
The session will also explore the tools and analytics we’ve developed within SkySpark to help non-technical users shift from reactive operations to performance-driven operations. We’ll share real-world examples such as M&V at scale, thermostat setpoint optimization, refrigeration temperature prediction, custom visualizations, and other exception-based workflows that reduce manual oversight across large, decentralized portfolios. In each case, we’ll highlight where we’ve integrated tools from other SkyFoundry partners to extend functionality, enhance automation, and bring advanced capabilities—originally built for large buildings—into the hands of those managing the other 80%.

Brian Frank
CEO and Founder, SkyFoundry
BIO: Brian Frank is the President and a Co-Founder of SkyFoundry, a software company specializing in the storage, analysis, and visualization of data from the Internet of Things. SkyFoundry’s software is used across the world in thousands of sites to analyze and optimize IoT systems including energy, HVAC, and lighting. Previously, Brian was a founder of Tridium and architect of Tridium’s software framework products. He designed and implemented the core subsystems for two generations of the Niagara Framework, widely acclaimed as a leading technology in the IoT space. During his tenure at Tridium, he also led the design of the open source Sedona Framework—a programmable control engine for smart sensors and embedded controllers. Brian currently serves as the technical lead for Project Haystack. He works with the Project Haystack community to curate domain models and technical specifications.

James Gessel
Founder, Ontologent
BIO: With a background in mechanical engineering and years of experience architecting advanced software for energy, automation, and analytics, James has helped transform how teams interact with complex building systems. He’s passionate about burying complexity beneath simple, elegant interfaces that make powerful tools accessible to all. Through his latest venture, James is building native AI solutions designed to bridge the gap between buildings, operators, engineers, developers, and decision-makers. His vision: a future where anyone—regardless of technical background—can engage with building intelligence through natural, intuitive, and transparent experiences.
ABSTRACT: Open Source AI Tool: SkySpark MCP Server
Want to experiment with AI with SkySpark? Come explore free, open-source tools that bring AI into your development workflow—from a Python-based MCP server to a git-like CLI for syncing SkySpark records to your machine, and beyond. These are community-driven side projects looking for curious minds to experiment, contribute, and push the boundaries of what’s possible.

Matthew Giannini
Senior Developer, SkyFoundry
BIO: Matthew Giannini is a software engineer with close to 18 years of experience writing software in the BAS industry. His current role is software engineer at SkyFoundry, where he works on the SkySpark analytics platform. In that role, Matthew had the opportunity to become more involved in the open-source community, where he is also a contributor to the Fantom programming language and an active member of the Project-Haystack community.

Grace Gillenwater
Sr. Energy Project Manager, Group 14
BIO: Grace Gillenwater, PE, CEM CMVP, SkySpark CP is a building performance specialist with over 13 years of experience dedicated to enhancing new construction and existing building operations. At Group14, she manages large-scale projects on complex campuses, leading existing building commissioning (EBCx), monitoring-based commissioning (MBCx), and energy audits, along with other energy consulting services.
She manages the development of SkySpark fault detection and diagnostics at Group14, leveraging the software to improve client workflows and analyze and optimize building performance, ensuring significant reductions in energy use.
ABSTRACT: Data-Driven Approach to Vivarium Air Valve Replacement
The presentation tells the story of a project where SkySpark was used to complete 100% remote commissioning testing. A Vivarium (animal lab) program could not relocate their entire program at one time to accommodate the construction process, so the project was executed in a phased approach, moving 3-5 spaces at a time. The presentation will review the benefits of implementing fully remote testing, as well as obstacles and how they were overcome for project execution.

Lincoln Harmer
VP - Smart Buildings, kW Engineering
BIO: Lincoln is a VP with kW Engineering and leads kW’s Smart Buildings Division. He has over a decade of commissioning and mechanical design assistance experience. He has managed hundreds of on-site facility assessments and recommissioning projects. He has also managed dozens of new construction commissioning projects. Lincoln is a registered Professional Engineer as well as an ASHRAE Certified Building Commissioning Professional.
ABSTRACT 1: Powering Fleet Success: Analytics-Driven EV Charging Station Management System for Fleet Applications
Tower Mobility operates highly utilized EV chargers that recharge fleet electric vehicles. They were looking for a Charging Station Management System (CSMS) to help them better understand how their Los Angeles EV charging operation, consisting of fourteen DC EVSE ports rated up to 150 kW, was performing from the electric utility interconnection to the charging plugs.
Tower Mobility partnered with kW Engineering, a trusted energy systems integrator, to implement a customized Charging Station Management System (CSMS) powered by SkySpark. The kW team tailored dashboards, KPIs, and real-time alerts to match Tower’s operational needs, ensuring full visibility without disrupting ongoing charge sessions.
Operating a successful EV charging business requires more than just hardware—it demands a robust software platform for system integration, KPI tracking, performance benchmarking, fault detection, work order management, and load control. These capabilities are essential to stay competitive in a rapidly evolving market.
ABSTRACT 2: Driving Business Value Through Integrated Utility Data and AI-Powered Insights
Reactive energy management falls short in today’s competitive environment—proactive approaches driven by comprehensive data and intelligent tools are essential for cost savings and sustainability. This session explores the strategic advantages
of coupling a global utility data connector with an AI-driven demand forecasting and anomaly detection tool within the SkySpark ecosystem.
Case studies from large-scale portfolios show how this approach streamlines data handling, anticipates problems, and delivers actionable intelligence.

Brandon Hicks
Lead IoT Developer, ENFRA
BIO: I got my start in IT working on help desk and networking, eventually moving into system administration and earning my Network+ certification. That early experience gave me a solid grounding in troubleshooting, infrastructure, and how all the moving parts of a system fit together.
From there, I joined First Solar as a Data Engineer, where I managed data acquisition and recovery for more than 150 sites using historian systems. I spent years digging into network, server, and calculation issues to keep data flowing smoothly, and later moved to the manufacturing side where I continued doing similar work at an even larger scale.
After that, I came to Bernhard (now Enfra), where I took on the role of lead IoT developer. I was responsible for building and maintaining a SCADA appliance designed to interface with BACnet devices, which gave me a lot of hands-on experience with HVAC communications and edge data collection.
Now, as Enfra transitions away from on-prem SCADA devices and deeper into SkySpark, I’m shifting my focus to SkySpark control sequences and helping refine how we monitor and interact with BAS systems.
Outside of work, I’m a big audiobook fan — I’ve listened to over 250 titles so far — and I love playing board games with my siblings and cousins. Most of all, I enjoy spending time with my wife and our four kids
ABSTRACT: Reset Logic Reinvented: Leveraging SkySpark to Tame Rogue VAVs
Rogue VAV boxes can wreak havoc on AHU reset strategies—forcing systems into inefficient operating states and undermining energy goals. This session explores how SkySpark’s powerful analytics can detect and isolate these outliers in real time, allowing for smarter, more resilient reset logic. By shifting reset control into SkySpark, teams gain a standardized, scalable approach that simplifies programming, improves maintainability, and enhances overall system performance. Co-presented with Lawrence Berkeley Lab highlights innovative ways to get more out of your analytics layer to unlock new efficiencies in HVAC control.

Rick Jennings
Data Analytics Application Engineer, SkyFoundry
BIO: Rick Jennings, PE, CEM, is an E-Mobility Product Manager and Data Analytics Application Engineer at SkyFoundry focused on applying the highly successful SkySpark platform as an analytics-driven energy management system for EV charging applications.
Rick has 12+ years of experience involving nuclear propulsion systems, railway electric traction systems, data centers, electric vehicle charging infrastructure, energy management, advanced data analytics, and IoT technologies.
In his previous role, he was ABB E-Mobility’s Product Marketing Manager and subject matter expert responsible for Terra 50 to 360 kW EV chargers in North America.
ABSTRACT: From Data to Decisions: SkySpark’s Advanced Analytics and Load Control for EV Charging
SkySpark is actively being applied at the edge to locally control and coordinate battery energy storage systems and EV chargers and in the cloud to manage EV charging operations. Campus facility energy management programs, involving HVAC and EV chargers, are using SkySpark. These project examples show the SkyFoundry community is creating solutions that directly address the intersection of EV charging and the built environment.
In this presentation, we will review sales and technical lessons learned by the SkyFoundry community in pursuing and winning on EV charging projects. We will highlight product features and sales tools by SkyFoundry for the community to use on EV charging projects.

Apoorv Khanuja
Data Analyst II, kW Engineering
BIO: Apoorv Khanuja is a Data Analyst II at kW Engineering, specializing in AI-driven solutions for building energy optimization. With a Ph.D. in Building Systems from the University of Cincinnati, he leverages large language models and time series forecasting to develop innovative tools that improve operational efficiency through load forecasting and anomaly detection across building portfolios.
ABSTRACT: AI-Driven Insights and Agentic LLMs: Transforming Energy Analytics in SkySpark
In building energy management, harnessing AI for precise predictions and LLM agents for intuitive querying unlocks new levels of operational insight. This technical session dives into the mechanics of EnergyAgent and SkyGraph, two cutting-edge
extensions for SkySpark that drive proactive decision-making through sophisticated data processing and interaction.
EnergyAgent employs an adaptive prediction engine that rapidly learns from time-series data, incorporating fine-tuned AI models for energy use forecasting, anomaly detection, and next-week load projections. SkyGraph builds on this by transforming SkySpark’s
relational data into a knowledge graph, accessible via an agentic LLM framework. The agent is equipped with specialized tools for querying sites, equipment, and rules in natural language.
This session equips developers and engineers with practical insights into implementing these technologies, fostering innovation in energy analytics while staying grounded in achievable outcomes.

Francis Mahony
Executive Director of Building Analytics, NV5
BIO: Francis Mahony is the Executive Director of Building Analytics at NV5, where he leads the development of analytics and technology services, including MBCx, Automated Functional Testing, and Digital Twins. These offerings are delivered through SkySpark and NV5’s custom web platform, NVision. In addition to his analytics leadership, Francis brings expertise in networking and security, ensuring these solutions are dependable, scalable, and well-integrated into client environments.
With 15 years of experience in the buildings industry, Francis began his career as an energy engineer delivering turnkey retrocommissioning projects before transitioning into a hybrid role as Project/Construction Manager and Controls Engineer. In that capacity, he managed HVAC, lighting, and controls projects while contributing to controls design, programming, and Niagara system integration. His broad expertise in the buildings industry gives him the real-world experience to develop practical tools that help technicians, engineers, and owners manage and operate their facilities.
ABSTRACT: Mapping Faults to Solutions: Practical Applications of Graph Analytics, AI, and User-Centered Workflows in Building Operations
Building operations generate large volumes of fault and sensor data, often revealing complex interdependencies between issues. Leveraging graph analytics enables clearer mapping of fault relationships, supporting more effective root cause analysis. Artificial intelligence can assist with work order assignment and provide context-aware recommendations for remediation, supporting faster and more consistent decision-making. Advances in user interface and user experience design further streamline the management and prioritization of work orders, improving workflow transparency and accessibility for facility teams. This session explores practical approaches for integrating graph-based analysis, AI-driven insights, and user-centered digital tools to address challenges in modern building operations.

Mike Melillo
Software Engineer, Albireo Energy
BIO: Over 13 years in the controls industry, focusing on control systems development and integration, ranging from FDD, custom monitoring solutions, and advanced supervisory control. Focused on guiding clients to understand and deploy emerging technologies in different built environments.
ABSTRACT: Maintaining Reliable Systems
We want to spend our energy focusing on the exciting things: fixing problems, saving energy, improving systems. But we can’t do that unless SkySpark and the systems we connect to run reliably.
This presentation focuses on monitoring the foundations we build analytics on top of, both SkySpark and connected BAS & EPMS that in many cases we have deployed ourselves. It also features a deep dive on utilizing the event framework to snapshot different kinds of system diagnostics — CPU Usage Spikes, Rules breaking, Views not populating data correctly, Connector failure loss, and problems with remote systems like JACE hang-ups. Done well, this process keeps SkySpark and the BAS running well. Not done at all, and everything is stuck chasing communication & sensor failure noise instead of what matters.

Viren Nathoo
Software Engineer, Albireo Energy
BIO: With over 15 years in the energy and sustainability industry, driving strategic initiatives in energy management, systems integration, and advanced monitoring solutions such as FDD. Viren is passionate about helping clients make data-driven decisions to optimize performance and drive sustainable outcomes.
ABSTRACT: Charging at the Workplace: Turning EVSE Data into Actionable Insights with SkySpark
As electric vehicle (EV) adoption accelerates, the integration of EV charger data into building analytics platforms like SkySpark offers a significant opportunity to enhance energy management and customer value. This presentation will use an example from a real-world workplace EV charging application to showcase how SkySpark may integrate with Charging Station Management Systems (CSMS) to monitor charger usage patterns, detect anomalies, optimize load management, and support sustainability goals within a broader energy management context. Real-time and historical data analysis provides clarity on energy consumption trends, peak demand contributions, and potential cost-saving opportunities. These insights not only improve operational efficiency but also help customers to make informed decisions about energy use impact and infrastructure planning.

Roger Quesnel
Chief Operating Officer, SkyFoundry
BIO: Roger Quesnel is the Chief Operating Officer at SkyFoundry, the developers of SkySpark™, a comprehensive software platform for connecting, storing, and processing analytic rules and algorithms from automation systems, metering systems, sensors, and equipment systems, to identify issues, patterns, deviations, and faults. He has over 30 years of experience in a variety of industries, having served in senior-level positions for manufacturers of engineered products and software. In his role at SkyFoundry, he focuses on operations and business development.
Roger is also a Board of Director for Project Haystack, which is an open-source initiative that seeks to standardize the way semantic tagging and data-modelling are used in smart buildings

Sherri Simms
Founder, ABI Advantage, LLC
BIO: Sherri Simms is the Founder and President of ABI Advantage LLC, a Certified Woman-Owned Small business that has provided effective solutions for reducing energy and water consumption since 2014. Sherri leads a team of experts, leveraging her strong foundation in Mathematics to guide the strategic analysis of complex building operational data. This leadership is key to empowering engineering firms and contractors by enhancing their offerings, helping clients achieve substantial savings, and significantly reduce consumption.
ABSTRACT: Beyond the Meter: Scaling Distributed Energy Monitoring with LoRaWAN
Advances in LoRaWAN wireless technologies are making distributed energy monitoring more flexible and cost-effective than ever. However, leveraging these innovations can present some unique challenges. We will share some of the lessons learned in a range of deployments from small churches to a 1.5 million square foot convention center, including monitoring of select 115V circuits all the way up to 13,200V substations.
With low-power, long-range capabilities, LoRaWAN wireless protocol makes it possible for some sensors to be self-powered and communicate hundreds of feet, even from inside a metal electrical cabinet. This opens up new opportunities in applications such as:
- Tenant Billing
- ESG Reporting
- Measurement and Verification
- Equipment Fault Detection

Sean Stackhouse
Solutions Architect, Actuate Facility Technologies
BIO: Sean is the solutions architect at Actuate, bringing almost a decade of experience around SkySpark and IoT HVAC platforms. His focus is on how best to model new systems, and to create processes and workflows standardizing and analyzing equipment data. At Actuate, the focus is on small commercial buildings, breaking away from the BAS world and into places that have never had access to the type of data and control SkySpark can offer.
ABSTRACT: How Xeto Enables Commissioning of RTUs and Refrigeration in Small Commercial Spaces
How do you manage buildings without a building automation system? Getting controllers into those spaces, while critical, is only part of the problem. We will discuss the tools surrounding commissioning controls for users without a controls background.
Utilizing xeto specs, we are able to install controllers on controllerless buildings, run commissioning reports, and continue to monitor equipment without the need for a controls expert. With helper functions and a user-friendly interface, even non-technical users can diagnose and resolve issues quickly. We’ll also show how built-in feedback and reporting tools not only empower users to improve their buildings, but also generate high-quality labeled data. This data feeds machine learning models that power generative AI tools—essentially giving users the support of a virtual building engineer in their pocket.
This session will focus on the specifics of how we use xeto, functions, and views, to accomplish the task of speeding up installs, and expediting maintenance.

Leland Stenquist
Software Developer, ENFRA
BIO: I graduated from the University of Utah with a degree in Computer Science. I’ve been working with SkySpark since 2014, and my experience includes:
- Building hundreds of SkySpark sites
- Engineering and developing rules and KPIs
- Deploying and maintaining SkySpark instances on the AWS infrastructure
- Deploying on-premises SkySpark sites and implementing VPN solutions to support thousands of unique SkySpark connectors
- Creating and maintaining a wide range of SkySpark views and applications to improve site build productivity and enable deeper data analysis
In 2022, I took a break from SkySpark to help develop an IoT device. The device was designed for rapid deployment in on-premises networks to extract and trend BACnet points. This project gave me hands-on experience with:
- The BACnet protocol, including direct training from Optigo
- Microsoft Azure infrastructure and the .NET framework
- JavaScript UI development using React and Angular
I’m now back working with SkySpark, focusing on AHU Resets and supporting our Data Delivery team by quickly analyzing client networks and identifying optimal strategies to bring data into our SkySpark cloud environment.
Outside of work, I enjoy spending as much time as possible with my wife and our 2.5 kids. I also volunteer with the local Search and Rescue team, where I primarily train for rope rescue operations in the Utah Rocky Mountains and uphill hiking. When time allows, I enjoy gaming with friends.
ABSTRACT: Reset Logic Reinvented: Leveraging SkySpark to Tame Rogue VAVs
Rogue VAV boxes can wreak havoc on AHU reset strategies—forcing systems into inefficient operating states and undermining energy goals. This session explores how SkySpark’s powerful analytics can detect and isolate these outliers in real time, allowing for smarter, more resilient reset logic. By shifting reset control into SkySpark, teams gain a standardized, scalable approach that simplifies programming, improves maintainability, and enhances overall system performance. Co-presented with Lawrence Berkeley Lab highlights innovative ways to get more out of your analytics layer to unlock new efficiencies in HVAC control.

Jinzhao Tian
Ph.D. Candidate, Carnegie Mellon University
BIO: Jinzhao Tian is a Ph.D. candidate at the Center for Building Performance & Diagnostics, School of Architecture, Carnegie Mellon University. His research lies at the intersection of buildings and artificial intelligence, with a focus on building data analysis, fault detection and diagnostics, and intelligent control systems. By integrating advanced machine learning methods with architectural engineering, Jinzhao’s work aims to improve building sustainability and efficiency—reducing energy use and carbon emissions while promoting healthier indoor environments for occupants.
ABSTRACT: A Scalable Data-Driven Framework for Fault (Spark) Impact Analysis in Buildings
Understanding the impact of faults in buildings is essential for optimizing operations, improving energy efficiency, and maintaining healthy indoor air quality (IAQ). However, traditional fault analysis methods often rely on simulations that require detailed models for each building, limiting scalability. Additionally, these models may not fully capture real-world complexities, such as interactions between building systems, occupant behavior, and environmental factors.
This study presents a scalable, data-driven framework for fault impact analysis, leveraging the SkySpark platform to integrate energy meter data, IAQ sensor data, fault (Spark) and building automation system (BAS) records, and weather information. By applying machine learning techniques, the approach generates actionable insights that help facility managers prioritize fault resolution to improve both energy performance and IAQ. The framework has been validated using two years of data from 47 buildings for energy analysis and 25 buildings for IAQ assessment across the U.S. The findings highlight the potential of data-driven methods to enhance decision-making, reduce carbon emissions, and support more sustainable and healthier building environments.

Raphael Vitti
Senior Energy and Data Engineer, Lawrence Berkeley National Laboratory
BIO: Raphael Vitti, PE, is a Senior Energy and Data Engineer at Berkeley Lab. He manages the Lab’s SkySpark infrastructure and develops applications to support the ongoing commissioning program, as well as energy and water management activities. He also plays an active role in identifying energy and water savings opportunities, investigating issues in building operations, supporting the implementation of improvements, and verifying savings.
Previously, Raphael was an energy efficiency engineer at kW Engineering. He is a licensed Professional Mechanical Engineer in California and earned his M.S. in Electronics and Communications Engineering from École nationale supérieure d’électronique, informatique et radiocommunications de Bordeaux (France).
ABSTRACT: Making Sense of Work Orders with AI: Leveraging SkySpark’s Python Library and LLM APIs to Generate Valuable Summaries
Summarizing the work history of a piece of equipment can provide Facilities staff with helpful context before beginning work. It can also yield valuable insights about recurring issues, and surface important information that is occasionally buried in field notes.
