Sessions

Stop guessing and start optimising. Nova Southeastern University transformed its institutional budget by $100 Million through AI-driven occupancy analytics. By leveraging the Wi-Fi infrastructure they already owned, NSU avoided $70 million in new construction costs and slashed HVAC runtimes by 21%—all without sacrificing comfort. This session will provide a blueprint for facilities leaders to achieve operational excellence, right-size real estate portfolios, and lead the hybrid learning revolution by turning underutilised space into strategic capital.

As smart technology increasingly becomes commonplace in buildings, it’s crucial to ensure all these different systems work together as one cohesive, secure ecosystem before construction. The WSP technology test lab approach provides a controlled environment to check this, reducing risk and helping teams protect timelines and costs.

This session will explore practical ways to reduce risk and improve outcomes across the smart building lifecycle, including how to:
• De-risk delivery by validating systems and integrations early, before issues reach site
• Strengthen cyber resilience by testing solutions against your security requirements before deployment
• Procure with confidence using independently verified performance data rather than relying solely on manufacturer claims
• Protect programme timelines and budgets through pre-validated technologies that reduce commissioning effort and costly rework

Smart buildings generate more data than ever before, yet many organisations still struggle to turn that information into meaningful action.

Drawing on Bellrock's experience delivering smart engineering, remote building optimisation, predictive maintenance and Net Zero consultancy, Andre Bothma will explore how data, AI and engineering expertise are reshaping facilities management. The session will discuss how building owners can procure technology more effectively, avoid common implementation pitfalls and focus on creating measurable operational outcomes rather than simply deploying more technology.

“Most commercial buildings are not truly operated.”

Despite increasing investments in smart building technology, organizations still struggle to manage portfolios at scale due to fragmented systems, outdated BMS, and lack of operational capacity.

This session introduces a practical approach to autonomous building operations using hybrid AI models, combining real-time data, domain knowledge, and scalable infrastructure.

Drawing on real-world deployments, the talk demonstrates how buildings can be transformed from passive assets into self-optimizing systems—without costly renovations.

Key insights include:
• achieving 20–30% energy savings without upfront capex
• reducing onboarding from weeks/months to a single day
• scaling optimization across hundreds of sites and thousands of buildings

The session moves beyond dashboards and analytics to show how buildings can actively optimize themselves through AI-driven control and anomaly detection.
Attendees will gain a framework for transitioning from “smart” to truly autonomous infrastructure.

Smart buildings have never generated more data. Energy and sub-metering, BMS and plant performance, occupancy and space utilisation, comfort and environmental conditions, maintenance history and helpdesk activity: most estates now collect far more than any facilities or workplace team could reasonably act on in a working week. AI is meant to close that gap, reading the building, surfacing what matters and telling operators what to do next.

And the pilots often go well. That is part of the problem. A proof of concept lands on one site, with one use case and one enthusiastic team, everyone can see the potential, and then it stops there. A year on, the estate has more dashboards, more vendors and more pilots, but the same decisions are still being made the same way they always were.

This session looks at why that happens, and at what the organisations who get past it do differently.

The harder problem is rarely the model or the sensor. It is the gap between buying smart building capability and giving the people who actually run the building enough confidence to use it, under time pressure, with an occupier on the phone. Facilities, workplace and estates teams are handed new tools and new dashboards without the data foundations, the operating norms or the decision frameworks that would let them trust what those tools tell them. So they verify it manually, or quietly fall back on the way that has always worked. Neither response is irrational. Both of them end adoption.

Commercial real estate is a massive global asset class, but its operational performance is bottlenecked by the "Implementation Gap." Modern buildings generate petabytes of telemetry, yet 90% remains "dark data"—cryptic, unstructured legacy shorthand trapped in silos. Traditionally, deploying intelligent analytics required months of manual tagging and mapping, killing project ROI before it began. 

This session details a new approach: replacing the manual data-tagging bottleneck with autonomous, agentic processors. We will walk through the architecture of a Memory Twin—a system that fuses real-time stream data, metadata, and static building documentation (such as manuals and historical logs) into a unified semantic graph. We will explore how to ground LLMs in building physics to prevent hallucinations, how non-deterministic agents reason over mechanical anomalies (distinguishing sensor drift from physical valve failures), and how to capture the transient diagnostics of on-site engineers into a persistent, self-improving operational memory.

Buildings are often called compliant, but compliant with what? Regulations are just one slice. True operational compliance is whether a building is actually performing as intended. Comfort, efficiency, cyber resilience and design intent. Inspired by Schrödinger's famous thought experiment, this session looks at the gap between assumption and verification. We'll explore how continuous commissioning, digital twins, and governance automation keep compliance alive day to day. Then we'll look ahead, where AI agents monitor drift in real time, explain causes and trigger fixes. So compliance becomes a continuous intelligence function, not a periodic audit. Attendees will leave with a practical view of today and an exciting sense of how AI will reshape assurance tomorrow.

Buildings generate vast quantities of operational data, yet most of it remains trapped in disconnected systems and beyond the reach of the people who manage them. This presentation explores how semantic digital building twins, which give operational data shared meaning and structure, are becoming the foundation for a new generation of AI agents capable of overseeing building operations. Moving beyond dashboards and conventional BMS workflows, we will show how agents reason over a building's semantic model to detect faults, verify performance against design intent, and support asset and portfolio decisions, with live demonstrations drawn from research at UCL and its commercial translation through Tacit Analytics. We will examine what it takes to create these semantic foundations at scale, the technologies that make agentic operation practical today, and what this shift means for how buildings will be managed, operated, and valued.

Today's buildings are shaped by increasingly sophisticated occupier expectations, ambitious landlord visions and a rapidly advancing technology landscape. Yet there is no universal blueprint for a smart building. Every asset has its own story, purpose and audience. The most successful technology solutions are those that support and enhance that narrative rather than define it. While the emergence of data, automation and AI presents extraordinary opportunities, these capabilities can only flourish when they are built upon the right operational, digital and cultural foundations within the property itself.

In this session I will use real life examples of challenges and opportunities and how the engineering and technology solutions will make building narrative a reality.

In one UK university's own survey, 44% of timetabled hours saw an empty room. In the same week, more than a quarter of the hours in which rooms were in use had no booking at all. The plan was wrong in both directions.

Most buildings are still managed from a half-complete version of the truth. Timetables, booking systems, floorplans, and capacity assumptions describe how a building is supposed to be used. They don't describe how people actually use it. That gap matters when estates teams decide which spaces to keep, consolidate, or refurbish, where to invest, and how much energy goes into conditioning rooms that may be empty.

This session tests the plan against reality using two sources. Universities' own space utilisation surveys, released under the Freedom of Information Act, produced by whatever method each institution used: clipboard headcounts, timetable analysis, Wi-Fi and sensor data. And continuous sensor data from live university deployments, hour by hour, set against the bookings for the same rooms.

Where a figure comes from the timetable, teaching rooms appear 65% to 75% full when in use. Where an actual count is available, the same rooms are 22% to 48% full. Institutions surveying twice a year saw their headline figure swing by eight points between waves. Others have stopped surveying because counting cost more than it was worth, and now report timetable-derived figures as it’s all they have.

The same questions apply to any large estate. Are decisions made on how people are expected to use the building, or on how they actually use it? Is the evidence a week's sample or a continuous record? And who, if anyone, is counting?

Delegates will leave with three tests to apply to their own occupancy data, the headline figures from the research, and a view of what continuous, privacy-first occupancy counting adds alongside booking systems and other building data.

The entrance to a building is no longer just a door. It is the first moment a resident, visitor or delivery interacts with the building — and in premium residential and mixed-use developments, that moment sets the tone for everything that follows.
This session explores how smart access infrastructure — from IP intercoms and e-locks to cloud management and third-party integrations — is transforming the way buildings are experienced, managed and valued. Drawing on real projects across EMEA including residential, assisted living and hospitality developments, this presentation shows how access technology connects the physical and digital layers of a building into a seamless, scalable system. From smartphone entry and elevator integration to remote access management and visitor flow — all the way to the cloud platform that ties it together.

Delegates will learn:

- How access infrastructure connects to the broader smart building ecosystem
- What developers and property managers are getting wrong when specifying access control
- How smart access directly impacts resident satisfaction, operational costs and asset value
- What a future-proof access specification looks like in 2026 and beyond
- How to brief technology partners and integrators to get the right outcome from day one

Smart buildings promise better performance, lower cost and more informed decisions. Yet six months after handover, FMs and operators are still chasing what was installed and how it should perform. 

Phone calls to subcontractors. Repeat surveys. Drives full of PDFs that no-one can navigate. The information exists, but it cannot be found, trusted or acted on. The result is cautious decisions, avoidable cost and a persistent gap between design intent and operational reality. This is the Performance Gap. 

The Performance Gap shows up in four recognisable information states: information lost at handover, fragmented through change over the life of the building, never created in structured form in the first place, or buried in the volume of documents the operator now holds. As investment in sensors, platforms and integration grows, the value of good information increases and the cost of poor information multiplies. Smart building investment runs into all four. Better sensors and dashboards amplify the value of good information and amplify the cost of bad information. 

Asset Intelligence is the discipline that addresses this. It is the practice of finding, trusting and acting on the information needed to keep buildings safe, compliant and performing across the full lifecycle. It sits alongside, and depends on, ISO 19650 for information management in delivery and ISO 55001 for asset management in operation. Standards set the expectation. Asset Intelligence is the operating discipline that lets organisations meet it in practice. 

In this session, Nick sets out why design, delivery and operation have each professionalised inside their own boundaries, and why the discipline gap is between them. He introduces a practical framework for closing that gap, showing how organisations build progressive confidence in their information across two pathways: Create, where new projects deliver information assets that survive into use; and Recover, where existing estates rebuild trust in the information they already hold. This applies across systems, platforms and operational teams responsible for smart buildings in use. 

For anyone responsible for delivering or operating smart buildings, this session reframes the challenge. Smart building performance is not a technology problem. It is a discipline problem, and it has to be solved across the full lifecycle if buildings are to perform as intended.

How smart is a smart building if it cannot speak?

Smart buildings already generate enormous amounts of data. Occupancy sensors, energy meters, climate systems, access control, maintenance platforms and workplace technologies continuously capture information about how a building is performing and being used. Yet much of this data remains fragmented across separate systems, dashboards and databases.

In this interactive session, PLEQ will demonstrate what happens when AI becomes the intelligence layer connecting these systems.

Using BuildingGPT, we will bring a real building to the stage and allow the audience to speak directly to it. Rather than watching another dashboard presentation, delegates will be able to ask the building their own questions using natural language and explore real operational data.

How busy was the building today? Which spaces are consistently underused? Where are occupancy and energy consumption misaligned? Which areas could be cleaned less frequently based on actual use? What changed compared with last week? Where should a facilities team focus its attention?

BuildingGPT demonstrates how these questions can be answered conversationally by connecting data across occupancy, energy, climate, maintenance and other building systems. The objective is not simply to create a chatbot for buildings, but to introduce a reasoning and interaction layer that makes complex building data easier to access, interpret and act upon.

The session will also explore an important development behind this new generation of building intelligence: Model Context Protocol (MCP). Today, connecting building technologies often requires individual API integrations between platforms. MCP introduces a different approach, allowing systems to expose structured data and capabilities in a way that AI applications can understand and work with directly. For building owners and technology teams, this could significantly reduce integration complexity while providing greater control over how building data is accessed and used.

We will demonstrate what this means in practice and discuss how AI could change the way building owners, facilities teams, asset managers and engineers interact with their buildings. Instead of navigating multiple dashboards or commissioning another static report, users can begin with a question and allow the intelligence layer to find, combine and interpret the relevant information.

The implications extend across building operations: identifying underused space, understanding occupancy patterns, investigating energy consumption, improving cleaning schedules, supporting maintenance decisions and providing management with faster insight into portfolio performance.

Most importantly, this will be an interactive demonstration rather than a theoretical presentation. Delegates will be invited to ask questions themselves and see how a real building responds.

The session is relevant to building owners, property and asset managers, facilities and workplace leaders, smart-building consultants, engineers, system integrators and technology teams interested in AI, IoT, building data and the future of property operations.

Come prepared to ask a real building a question and experience what happens when a smart building finally finds its voice.