1. OpenBlue
  2. Insights
  3. AI 101: Building a Foundation for Smarter Buildings

Video: AI 101 Webinar Series

Part 1 On-Demand

AI 101: Building a Foundation for Smarter Buildings

In Part 1 of our AI 101 Webinar Series, OpenBlue experts broke down key AI concepts in plain language and connected them to real-world building operations use cases. Watch on demand now to learn how AI can support predictive maintenance, energy efficiency, and smarter decision-making without requiring a technical background to follow along.

This session was designed to help viewers build a clear foundation for understanding what AI can do, what it cannot do, and how it is already shaping the future of smart buildings.

Speakers

Robbie Davis

Robbie Davis

Director, Product Management, Johnson Controls

Irina Koitz

Irina Koitz

Senior Director, Digital Product Management and AI, Johnson Controls

Reuben Petty

Reuben Petty

Digital Solutions Director, Johnson Controls

Key takeaways

Understand the AI Landscape
Understand the AI landscape

Gain a foundational understanding of artificial intelligence, machine learning, generative AI, and how these technologies work together.

Separate hype from reality
Separate hype from reality

Learn where AI is creating measurable value today and where expectations often exceed reality.

Real-world building applications
Explore real-world building applications

See how AI is being applied across building operations, maintenance, energy management, occupant experience, and portfolio optimization.

What's next
Prepare for what's next

Understand the trends shaping the future of AI and how organizations can begin laying the groundwork for adoption.

  • Summary

    AI 101: Foundations and Real-World Applications

    Welcome

    Jennifer Heath, Product Marketing Lead, OpenBlue

    Welcome to AI 101: Foundations and Real-World Applications. This webinar explores how artificial intelligence is transforming building operations through predictive maintenance, energy optimization, and autonomous decision-making.

    Joining today's discussion are:

    • Reuben Petty, Director of Digital Solutions Sales
    • Robbie Davis, Director of Product Management, OpenBlue
    • Irina Coitz, Head of Product & AI, OpenBlue

    The Evolution of AI in Buildings

    For more than a century, Johnson Controls has helped transform buildings from static structures into intelligent, high-performing environments.

    Today, the industry is moving beyond simply monitoring building systems. AI enables organizations to:

    • Predict equipment failures before they occur
    • Recommend corrective actions
    • Optimize energy consumption
    • Automate operational decisions
    • Interact with building data using natural language

    The vision is to move from buildings that tell you something has broken to buildings that can identify issues, recommend solutions, and eventually take autonomous action.

    Understanding the AI Journey

    AI in buildings has evolved through several stages:

    Reactive Operations
    Building operators monitor systems and respond to alarms after issues occur.

    Predictive Analytics
    Machine learning identifies patterns and forecasts potential failures before they happen.

    Prescriptive AI
    AI recommends specific actions to improve performance and reduce operational risk.

    Agentic AI
    Systems are capable of autonomously executing workflows to achieve predefined goals such as energy optimization while maintaining occupant comfort.

    Key AI Concepts Explained

    Machine Learning

    Machine learning enables systems to learn patterns directly from data rather than relying solely on predefined rules.

    Examples include:

    • Identifying equipment anomalies
    • Detecting fault conditions
    • Predicting maintenance needs
    • Forecasting energy usage

    Predictive Analytics

    Predictive analytics uses historical data to forecast future outcomes.

    Examples include:

    • Anticipating equipment failures
    • Forecasting energy demand
    • Identifying operational inefficiencies

    Prescriptive AI

    Prescriptive AI goes beyond prediction by recommending actions.

    Rather than simply identifying a problem, it helps determine the most effective response based on business objectives and operational constraints.

    Generative AI

    Generative AI creates new content and enables conversational experiences.

    Examples include:

    • Natural language interfaces
    • Automated reporting
    • Knowledge assistants
    • Conversational building management

    Why AI Matters for Facility Operations

    Traditional maintenance approaches are often reactive and costly.

    AI enables organizations to:

    • Reduce unplanned downtime
    • Extend equipment life
    • Improve labor efficiency
    • Lower energy consumption
    • Reduce greenhouse gas emissions
    • Improve occupant comfort

    Predictive maintenance helps facility teams address issues before they escalate into costly failures.

    Customer Example: Stanford University

    One example of AI-powered optimization is Stanford University's energy transformation initiative.

    To support ambitious sustainability goals, Stanford implemented advanced optimization technologies that combine:

    • Model Predictive Control (MPC)
    • Machine Learning
    • Utility Cost Optimization
    • Greenhouse Gas Reduction Strategies

    Results included:

    • 17% reduction in peak energy demand
    • Approximately $500,000 in annual cost savings
    • 81% reduction in greenhouse gas emissions

    The project demonstrates how AI can optimize complex energy systems while helping organizations achieve long-term sustainability objectives.