E1 / Original estimate
Line 1 Small workshop refurbishment: total planned cost £100,000, excluding VAT.
Defined refurbishment scope; no additional drainage works included.
Licensed business data for AI
Construction data sourcing for AI teams.
We help AI teams find construction records that connect original estimates, project changes and final costs.
Currently at the sourcing stage. Dataset availability and licensing are confirmed case by case.
01 / A worked example
Why did the final
cost change?
One small example of the task a linked set of records could support: reconcile the numbers, cite the evidence and say what cannot be established.
SCRIPTED SYNTHETIC DEMONSTRATION · All records and figures are invented. This is not a live AI system or a real archive.
Where did the extra £12,000 go?
Select a record, then follow the citations. Remove the variation summary to see how the evidence changes.
V1 / Variation summary
Line 1 Additional drainage: +£12,000, excluding VAT.
Line 2 Omitted partitions: −£2,000, excluding VAT.
No supporting approval or invoice is included.
F1 / Final account
Line 1 Total recorded final cost: £112,000, excluding VAT.
No itemised reconciliation accompanies this total.
£12,000 difference between estimate and final account
£10,000 documented changes£2,000 unexplained
What the records support
The recorded final cost is £12,000 above the estimate (F1, line 1; E1, line 1).
The variation summary documents £10,000 of that difference: £12,000 for drainage (V1, line 1) less £2,000 for omitted partitions (V1, line 2).
With the variation summary excluded, neither remaining record documents the reason for the £12,000 increase.
£2,000 remains unexplained. An itemised final-account reconciliation is needed.
All amounts exclude VAT. The records do not establish whether variations were approved or amounts paid.
Discuss a similar task →A founder-led sourcing initiative
Maevar is led by Richard McKay, who holds an honours degree in Quantity Surveying and has worked in the construction industry for over 30 years. That background informs our construction-first focus. We start with the buyer’s task and assess the records against it; any specialist review, preparation and evaluation criteria would be agreed for the project.
02 / From use case to scope
Start with a few sentences.
Work towards a useful brief.
You do not need a finished specification. Tell us what you want a model to do and where the evidence matters.
Understand your use case
Identify the decisions, documents or cost questions you want to test.
Assess potential records
Look at source availability, structure, completeness and links between documents.
Check rights and boundaries
Review licensing authority, confidentiality, personal data and third-party restrictions.
Agree a possible next step
Define any sample, preparation, specialist review, permitted use and commercial terms.
Other sectors considered against your brief: engineering and manufacturing, maintenance and repair, logistics, and commerce.
03 / Useful to know
What to expect.
A clear discussion of what is available, what needs checking and what could come next.
Is this example a dataset I can buy?
No. All records and figures in the demonstration are invented. They illustrate a task, not inventory or evidence of access to a real archive. Potential sources, scale, formats and delivery would be assessed against your requirements.
How are rights and confidential material handled?
Each source needs review of ownership, authority to license, third-party restrictions, confidentiality and personal data. Exclusions, redaction or other controls may be necessary. Access to files does not itself establish permission to use them.
Can we explore a small evaluation first?
Yes. Where a suitable source and permissions can be established, we can discuss a bounded sample or evaluation. Its scope, preparation, access and permitted use would be agreed before material is shared.
Are historical decisions treated as correct answers?
No. A recorded decision shows what happened, not necessarily what should have happened. Any expert-reviewed tasks would distinguish source facts from retrospective annotation, preserve uncertainty and use an agreed review and scoring process.
04 / Let’s talk
Discuss your use case.
You don’t need a finished brief. A few sentences about your task are enough to start.
We’ll review your requirement and reply about fit and possible next steps.
For business owners and authorised archive holders: discuss potential records with McKays.