How AI workflows can help teams navigate complex construction disputes
Last Updated May 6, 2026
Shauna Hurley
9 articles
Shauna is never short of questions when it comes to construction, tech and science. A professional writer, researcher and podcast producer, she loves sitting down with industry insiders for in-depth interviews that uncover the latest developments, debates and emerging trends. Having worked with organisations like Microsoft and the European Bank of Reconstruction, Shauna joined Procore to explore the complex issues facing construction and share fresh, research-rich insights that help professionals navigate a rapidly evolving industry.
Theodore Galanos
Generative AI Leader
Theodore Galanos is Generative AI leader at Aurecon and Chief Science Officer at Infrared City, working at the intersection of AI, design and engineering. His work focuses on the “missing middle” of AI — the workflows, systems and orchestration layers that turn model capability into reliable, real-world outcomes, helping organisations apply AI with greater structure, accountability and impact. He regularly shares his latest research and thinking on his industry blog The Harness.
Construction disputes are notoriously costly, time-consuming and difficult to navigate, but as Theodore Galanos explains, AI workflows are starting to change that.
“Every organisation we work with faces the same paradox,” he says. “They have terabytes of documentation, thousands of precedents and decades of accumulated knowledge. But when a complex problem lands on their desk, they scramble to find the one or two senior experts who can make sense of it all.”
This challenge is particularly clear when it comes to construction disputes. A single major project can generate more than 100,000 documents that collectively hold the answers to critical questions about who made agreements and what caused delays. But who has the time, expertise and budget to uncover them?
We know this information exists, but to identify genuine insights, senior professionals with decades of experience need to synthesise across multiple areas, spot patterns and piece together answers from fragmentary evidence.
These experts are usually rare, expensive and overwhelmed with work.
Theodore Galanos
Generative AI Leader
Aurecon
Traditionally, that means one expert working through one problem at a time.
AI workflows are now being designed to solve this bottleneck -- not by replacing human expertise, but by structuring, encoding and scaling it.
Take a complex construction dispute involving tens of thousands of emails, reports, RFIs and meeting records.
The expertise needed to resolve disputes is usually scarce and localised. One senior expert tackles one complex problem at a time, junior staff wait for review, and knowledge transfer is slow and uneven.
It might require around 40 hours of senior expert time. That’s one expert, one project, one week.
Theodore Galanos
Generative AI Leader
Aurecon
This is where specialised AI workflows come in to change the equation, providing a structured way to work through complex problems step by step. Instead of one person piecing the whole picture together, the work is broken into focused steps that reflect how experienced professionals already approach the problem.
In practice: Experts design these workflows, and AI applies them at scale.
Domain experts design AI workflows by encoding the logic, decision-making criteria and quality checks they already use in their work. So the result is each workflow delivers answers, not information dumps, built on years of deep human expertise.
In our work at Aurecon we’ve shown this now takes 4 to 6 hours of combined human time, mostly involving review and judgment, compared to around 40 hours of senior expert time in a traditional approach. The senior expert can handle 8 to 10 such matters in the same week. Their expertise is effectively multiplied by ten.
The real transformation isn’t the time saving. It’s what becomes possible when expertise is no longer the constraint.
Theodore Galanos
Generative AI Leader
Aurecon
And as Theodore highlightsthrough a deep dive into his AI workflows, the potential goes well beyond contract disputes.
Think of a design review on a sprinkler system, for instance. Our AI team won’t start from a point of understanding what that particular system is or what it involves, but our engineering experts do have all that knowledge.
So they design the review guidelines, the logic and even the systems required to execute it. Our AI team then works with them to apply that consistently.
In this way we encode expertise into specialised AI workflows for problems experts can clearly define and know how to solve. We’re already seeing organisations building these kinds of workflows across legal, financial, operations and commercial areas.
Across construction and AI in general right now, the focus is on agents and chatbots, while workflows are often treated as a ‘nice-to-have’ add-on. But in the next year, I think we’ll see almost all valuable work will happen within AI workflows.
The organisations using them today are set to define the future of industry transformation tomorrow.”
Theodore Galanos
Generative AI Leader
Aurecon
Categories:
Written by
Shauna Hurley
9 articles
Shauna is never short of questions when it comes to construction, tech and science. A professional writer, researcher and podcast producer, she loves sitting down with industry insiders for in-depth interviews that uncover the latest developments, debates and emerging trends. Having worked with organisations like Microsoft and the European Bank of Reconstruction, Shauna joined Procore to explore the complex issues facing construction and share fresh, research-rich insights that help professionals navigate a rapidly evolving industry.
View profileTheodore Galanos
Generative AI Leader | Aurecon
Theodore Galanos is Generative AI leader at Aurecon and Chief Science Officer at Infrared City, working at the intersection of AI, design and engineering. His work focuses on the “missing middle” of AI — the workflows, systems and orchestration layers that turn model capability into reliable, real-world outcomes, helping organisations apply AI with greater structure, accountability and impact. He regularly shares his latest research and thinking on his industry blog The Harness.
View profileExplore more helpful resources
From quick wins to workflows: How AI is changing construction on the ground
AI tools like ChatGPT, Copilot and Claude have become a familiar fixture of everyday life and work for millions globally. In construction, conversations about AI often focus on the “quick...
Types of Construction Estimates: A Practical Guide
Project budgets, approvals and risk positions are often set early, before the scope is fully defined. Different types of construction estimates are used at different stages to guide those decisions...
4D BIM: Integrating time into construction planning
BIM programmes can look solid on paper, but sequence risk often isn’t properly tested until work is about to start on site. Traditional programme tools show dates and durations, but...
What is a Construction Feasibility Study? A Practical Guide
The most expensive problems on construction projects rarely appear at the start. They surface months later, when approvals stall, redesign becomes unavoidable, or budgets no longer hold. By then, the...