ARTIFICIAL INTELLIGENCE


National Guidance


Academic Journals


Practitioner Journals


Regulations Government Reports


Problem Queries


Healthcare Facilities Knowledge Hub


Proprietary Partner Knowledge Hub


Ventilation


MGPS Water


Fire Safety


Pressure Systems


Confined Spaces


Figure 1: Overview of the pilot setup, showing how DRLC’s proprietary database integrates into a centralised knowledge hub, with access restricted to DRLC staff, to streamline information access for DRLC staff.


and handle ambiguous or incomplete sentences. This ability is key to making interactions with AI feel more natural and intuitive, mimicking human-to-human conversation.


Maintain conversation history The ability to keep track of previous interactions within a conversation to maintain continuity and reference past exchanges as needed. Maintaining a conversation history


allows the AI to remember details from earlier in the conversation, which is essential for providing consistent and relevant answers. This capability is particularly important in extended interactions, where the context builds over time, such as in customer service, technical support, or complex problem- solving scenarios.


Learn from feedback The system’s ability to improve its responses over time by incorporating user feedback, corrections, or new data. Learning from feedback can happen in


various forms. In some cases, users may directly correct the AI, and the system can adapt its future responses based on this feedback. In more advanced systems, this learning can occur at a larger scale through updates to the system based on aggregated user interactions, helping to refine accuracy, tone, and relevance. This continual learning process is vital for improving performance and staying current with evolving language and knowledge. These capabilities collectively enable


this AI system to effectively engage in meaningful, dynamic conversations with estates and facilities staff when they are seeking answers to technical questions.


IFHE DIGEST 2025


Limitations of the innex.ai system Current limitations of the system include:


Guarantee real-time updates The ability of an AI system to provide information that is current, reflecting the most recent data, events, or changes.


Connection to search engines The ability of the AI system to integrate with search engines to retrieve real-time information, enhance its knowledge base, and provide more accurate responses. These capabilities are currently being


discussed by the innex.ai development team.


What innex.ai is not intended to do Replace staff Engineering is a professional service which focuses on high level engagement with people in a quest to solve complicated problems. Some of the processes that this involves are amenable to AI, as described above. Professional services can use AI to improve their efficiency both internally and in the way they serve their clients.


Make decisions The current incarnation of AI can answer questions and give useful pointers to sources of information. The system, however, does not have the capability to weigh pros and cons of real world problems and thus make decisions.


Understand context implicitly The experience and knowledge of an engineer understands both the problem and the situation in which the issue is taking place. These human qualities are not a facility that current AI systems supply.


Answer and Reference


•Contractors •Staff •Clients


•NHS Trusts


•Private Hospitals •FM Contractors •Expert Services •...(no access to DRLC knowledge)


Very old AHU.


Overview of pilot programme As suppliers of authorising engineers to the NHS, we have partnered with innex.ai to carry out a pilot of the AI system in healthcare engineering. This initiative aims to validate and refine the functionalities of the innex.ai system within the NHS. DRLC benefits from the pilot by reducing the time that our engineers spend on searching for information and broaden the scope of accessible knowledge. For the innex.ai team, the pilot provides an invaluable platform for gathering regular feedback which will help to refine the user interface and ensure it meets the real- world needs of healthcare professionals. As shown in Figure 1, DRLC connects


its own proprietary database to the innex.ai platform, which will enable only DRLC staff to access the company’s own database of information.


Looking forward DRLC and innex.ai are excited to launch this pilot programme, showcasing the potential of AI to streamline workloads and reduce administrative tasks for engineers in the healthcare sector. Carl reflects on how he sees the future: “In the future, innex.ai is set to become the focal point (nexus) for innovation. Imagine a platform where hospital staff and others working in highly regulated built environments can swiftly find the latest guidelines, share best practices from across the globe, and connect with peers to solve complex problems together. Our AI copilots will also help staff effortlessly manage writing, compliance, and other administrative tasks, making their workload more manageable. “Our AI insights dashboard will provide national bodies, regulators, and professional organisations with up-to-date information on emerging risks and ongoing staff challenges. They can address these risks and knowledge gaps with proactive guidance updates and tailored training courses. In this way, everyone in the healthcare ecosystem stays informed and prepared. innex.ai is not just transforming how information is shared – it’s shaping the future of healthcare innovation, making it more responsive and interconnected than ever before.”


IFHE 65


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64  |  Page 65  |  Page 66  |  Page 67  |  Page 68  |  Page 69  |  Page 70  |  Page 71  |  Page 72  |  Page 73  |  Page 74  |  Page 75  |  Page 76  |  Page 77  |  Page 78  |  Page 79  |  Page 80  |  Page 81  |  Page 82  |  Page 83  |  Page 84  |  Page 85  |  Page 86  |  Page 87  |  Page 88  |  Page 89  |  Page 90  |  Page 91  |  Page 92  |  Page 93  |  Page 94  |  Page 95  |  Page 96