<?xml version="1.0" encoding="UTF-8"?><ns2:project xmlns:ns1="http://gtr.rcuk.ac.uk/gtr/api" xmlns:ns2="http://gtr.rcuk.ac.uk/gtr/api/project" xmlns:ns3="http://gtr.rcuk.ac.uk/gtr/api/fund" xmlns:ns4="http://gtr.rcuk.ac.uk/gtr/api/person" xmlns:ns5="http://gtr.rcuk.ac.uk/gtr/api/project/outcome" xmlns:ns6="http://gtr.rcuk.ac.uk/gtr/api/organisation" ns1:created="2026-08-26T13:36:10Z" ns1:href="http://gtr.ukri.org/gtr/api/projects/97B33314-D88A-46BB-BFAB-B4CEC3D14DAA" ns1:id="97B33314-D88A-46BB-BFAB-B4CEC3D14DAA"><ns1:links><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/persons/C6A3E53E-5078-49C7-9255-FCCC5ACDFD89" ns1:rel="PM_PER"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/F522A9B5-BA3B-49ED-8154-CBD9E10229F8" ns1:rel="LEAD_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/F522A9B5-BA3B-49ED-8154-CBD9E10229F8" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:end="2026-04-29T23:00:00Z" ns1:href="http://gtr.ukri.org/gtr/api/funds/AF90BD79-0639-47BE-A1C2-E5CC04AB547B" ns1:rel="FUND" ns1:start="2025-11-01T00:00:00Z"/></ns1:links><ns2:identifiers><ns2:identifier ns2:type="RCUK">10172822</ns2:identifier></ns2:identifiers><ns2:title>Intelligent Risk Identification System for Construction</ns2:title><ns2:status>Closed</ns2:status><ns2:grantCategory>Fast Start Response</ns2:grantCategory><ns2:leadFunder>Innovate UK</ns2:leadFunder><ns2:abstractText>Construction projects generate vast amounts of documentation, including site diaries, meeting minutes, RFIs, emails, contracts, schedules, and cost breakdowns. This information often contains references to risks - both current and potential - that can impact project delivery. However, due to the volume and fragmentation of data across systems and formats, these risks often go unnoticed until they cause delays, cost overruns, or disputes.

The IRIS-C project aims to further develop Constructer, an AI-powered platform that automates the detection and reporting of project risks in real time. Unlike existing construction platforms, which rely heavily on manual input for risk tracking, Constructer uses advanced language models trained on construction-specific data to scan project documentation, extract risk-related information, and make it accessible through a natural language interface.

Once risks are identified, Constructer consolidates all related data and links it to core project information such as schedules and cost structures. This allows project managers to understand not only the nature of the risks but also their likely impact on time and budget - supporting more informed and proactive decision-making.

Through IRIS-C, we will build three key capabilities to bring Constructer to market readiness:

* A user interface for structured and intuitive risk reporting.
* A natural language interface for efficient retrieval of risk-related information.
* A scalable, cloud-based technology stack to ensure performance across large, complex projects.

By improving visibility of risks and reducing reliance on reactive processes like claims and rework, Constructer will enhance project outcomes, protect margins, and support stronger client relationships. The platform is being validated with international industry stakeholders and has already shown positive early results in pilot applications.

The project addresses a critical need for smarter risk management in the construction industry by harnessing the potential of artificial intelligence and natural language processing. Our goal is to deliver a tool that empowers project teams with real-time insights, transforming how construction risks are identified, tracked, and managed.</ns2:abstractText></ns2:project>