14 April 2026

Disputes are never born big

In UK construction, disputes rarely begin as headline events. They start with something ordinary. A notice served two days late. An instruction buried in an email chain. A drawing revision that never gets linked to cost or programme.

At the time, these feel minor. Nobody treats them as commercial risks.

But small omissions compound. An unclear instruction becomes a disputed variation. A programme impact goes unrecorded and resurfaces months later as a delay claim. Eventually, two parties are telling completely different stories about the same event.

The facts are usually there. But the evidence is fragmented, hard to retrieve, and expensive to rebuild. An extension of time is awarded with no route to recover cost, or lost entirely because the evidence was never structured. Before any formal dispute even begins, the cost is already being absorbed: QSs spending hours trawling emails, reconstructing timelines, cross-referencing drawings to instructions and notices.

RICS guidance is unequivocal: contract administration must be handled contemporaneously, not reconstructed after the event. The industry knows this. It just lacks the tools to do it consistently.

The real problem is not data

Construction generates enormous volumes of information. Emails in Outlook. Documents in SharePoint or a CDE. Site communication in WhatsApp. Programmes held separately. Contracts rarely referenced day to day.

All of it exists. None of it is connected.

That is why disputes become retrieval problems before they become legal problems. The information to defend a position usually exists somewhere across the project record. The cost is finding it, structuring it, and presenting it in a form that proves the point.

The Society of Construction Law Delay and Disruption Protocol makes the same point from the other direction: transparency of records, clear methodology and structured information are central to both dispute prevention and resolution.

This is not a data problem. It is a commercial intelligence problem.

What a private commercial AI actually does

A commercial GPT is not a chatbot, and it is not a search engine bolted to a contract library. It is a private, project-specific intelligence model deployed in a secure environment and connected to live project data: contracts and subcontract conditions, correspondence and minutes, programmes and revisions, valuations and payment cycles, drawings and design changes.

The critical distinction: it does not just store information. It understands the relationships between events. A notice is linked to the contract clause it relates to. A variation is connected to the drawing revision that triggered it. A delay event is mapped to the programme change that followed.

The shift is from "we think this happened" to "here is the evidence trail".

On a live project

A QS asks a plain-language question. When was this variation instructed? Was notice served correctly under clause 2.26? What programme was in effect when this event occurred?

The output is not a list of documents. It is a structured timeline of events, linked to the supporting evidence, with the contractual position referenced. The system checks actions against the contract, notice periods, authority levels and instruction validity, across JCT, NEC4 and bespoke amendments.

The real commercial value sits in delay. The system cross-references programme changes, site events and correspondence to flag potential delay events, missing notices and risks to the critical path. Brickwork delayed by late design information: it identifies when the design was issued, the programme impact, whether notice was served, and the entitlement position, in minutes rather than days.

And because it runs continuously, it flags missing notices before they become missed deadlines. That is the decisive shift: from reactive claims building to proactive commercial control.

Why this matters commercially

Hours of manual retrieval become minutes of structured output. Fewer lost claims and stronger defence positions, because evidence is always audit-ready. Better substantiated valuations and faster resolution protect margin. And QSs spend their time on value, strategy and commercial leadership rather than admin.

A commercial GPT does not replace the QS, the PM or the contract administrator. It removes the non-value work that surrounds them, and gives them something the industry has consistently lacked: a clear, defensible, real-time version of the commercial truth.

The difference between winning and losing a dispute is rarely the facts. It is whether you can find, structure and prove them in time.