AI use case · Construction
AI tender and BOQ analysis for contractors, with pricing left to the estimator.
For estimators and tendering teams who read every tender pack line by line against a fixed submission date. AI turns the BOQ into structured items, summarises the conditions and flags gaps. Your estimator prices and decides.
What is AI tender and BOQ analysis?
AI tender and BOQ analysis reads a tender pack, including the bill of quantities, specifications and conditions, into structured items. It compares BOQ lines with your past jobs and rates, summarises penalties, retention, payment terms and key dates, and flags missing scope. Each finding links to its source. The estimator reviews it, prices the work and decides whether to bid.
The problem
Tender packs are large, and the submission date does not move.
UAE tenders often arrive as a mix of Excel and PDF BOQs, specifications, drawing lists and contract conditions, sometimes with Arabic forms from a government client. The estimator has to read all of it, build a priced BOQ and raise clarifications before the submission date.
The risk sits in the details. A provisional sum, a liquidated damages rate, a retention clause or an item missing from the BOQ can decide whether the job is worth bidding. When several tenders overlap, the reading gets rushed and those details are found after award.
Re-keying BOQs
BOQ lines are copied from PDFs into the estimating sheet by hand, with units and quantities checked line by line.
Conditions read under pressure
Penalties, payment terms, retention and insurance requirements are spread through the pack and summarised from memory.
Scope gaps found late
Items shown in the specification or drawings but missing from the BOQ surface during the project, not during pricing.
How it works
One tender pack, from download to a reviewed bid summary.
An illustrative workflow. The cost database, rate sources and summary format are agreed with your commercial team.
Intake
The tender pack is uploaded as received: Excel or PDF BOQs, specifications, conditions, addenda and drawing lists.
BOQ extraction
AI reads each BOQ line into item number, description, unit and quantity. It keeps the bill and section structure and links every line to its page.
Comparison with past work
Lines are matched to similar items from your past jobs or cost database, so the estimator sees reference rates where they exist. Where none exists, the line says so.
Conditions summary
Penalties, retention, payment terms, insurance, bonds and key dates are summarised, each with a link to its clause.
Gap flags
Items in the specification or drawing list but not in the BOQ, unclear units and conflicting quantities are flagged as possible clarifications.
Estimator review
The estimator checks the summary, prices the work, decides which clarifications to send and makes the bid or no-bid call.
Who does what
What the AI does · What a person checks.
What the AI does
Reads Excel and PDF BOQs into structured lines with units and quantities
Links every line and condition to its page in the tender pack
Matches BOQ items to similar items in your past jobs or rates
Summarises penalties, retention, payment terms and key dates
Flags missing scope, unclear units and conflicting quantities
Drafts clarification questions for the estimator to edit
What a person checks
Every rate, mark-up and price in the bid
Risk judgement on conditions, penalties and programme
Which clarifications go to the client and how they are worded
Any BOQ line the extraction marks as low confidence
The bid or no-bid decision
First pilot
A first pilot on tenders you have already priced.
We test on your own tender packs before anyone talks about results. Scope, timeline and price are confirmed in a written proposal.
Past tenders as the test set
Use tenders your team has already priced, so the extraction and gap flags can be checked against what the estimator found.
One trade or project type
Start with the work you bid most often, such as fit-out or MEP packages, where BOQ formats repeat.
One rate source
One cost database or set of past BOQs as the reference, clean enough to compare against.
Agreed acceptance
Agree line-level checks and what counts as a useful gap flag with your estimators, before the evaluation runs.
Data, hosting and Arabic
Where tender data goes, and how Arabic is handled.
Hosting
The application and stored data can be hosted on Azure UAE North, on private servers managed by Vloud, or in your own cloud account. The AI model is used through a provider agreed per project, and its processing region may be outside the UAE.
Confidential rates
Your rates and past bids are commercially sensitive. They stay in the agreed environment, and access is limited to your tendering team.
Arabic
Arabic tender forms, conditions and bilingual BOQs are tested as their own sample, not assumed to behave like English ones.
Retention
What is kept after a tender closes, and for how long, is agreed with your commercial manager. Documents from lost bids can be deleted on request.
Honest limits
Where it does not work yet.
- Pricing decisions and risk judgement stay with the estimator. The workflow shows reference rates; it never sets a price.
- We do not quote accuracy or time savings before testing on your tender packs. Results are measured on a held-out sample first.
- Rate comparison is only as good as your cost data. If past BOQs use different descriptions or units, cleaning them is part of the scope.
- Scanned BOQs with merged cells, handwritten amendments or poor print quality need a person to check them.
- It reads documents, not drawings. Quantity take-off from drawings is not part of this workflow.
What drives cost and timeline. The number of tender types and BOQ formats, Excel versus scanned PDF, languages, the size and state of your cost database, the summary format your team needs and hosting requirements. We don't publish a price list; scope, timeline and price come in a written proposal after the discovery call.
Evidence
What we can show you.
Every example is labelled: delivered work, our own product, a demonstrator, or an illustration with synthetic data.
- Our product
ArkanERP BOQ control
ArkanERP, our ERP for construction and project-driven companies, keeps the bill of quantities connected to procurement and project accounting. It is our own product, not an AI tender project, and shows where a structured BOQ goes after award.
- Delivered work
BOQ in ArkanCS at Al Mukab AlFudhi
On Al Mukab AlFudhi Engineering Consultancy's G+5P+15 project, the BOQ is imported from Excel into ArkanCS, validated and linked to variations and payments. It is construction software work; no AI tender analysis is claimed.
- Synthetic data
The illustrative document workflow
A step-by-step walkthrough of extraction, checks and review, shown with a synthetic invoice rather than a tender. The same pattern of values linked to their source and exceptions sent to a person applies to BOQ lines.
Before you start
Questions buyers ask.
Does it read Excel and PDF BOQs?
Yes. Excel BOQs are read directly, keeping bills, sections and item numbers. PDF BOQs are read page by page, and scanned or badly formatted pages are flagged for a person.
Can it handle Arabic tender documents?
Yes, Arabic, English and bilingual packs. Arabic forms and conditions are tested as their own sample during the pilot, since layouts and scan quality vary between clients.
Can it link to our cost database?
If your cost database or past BOQs can be exported or reached through an API, yes. We review the data first, because inconsistent descriptions and units affect the comparison more than the AI does.
Will it price the tender for us?
No. It shows reference rates from your own past work where they exist and flags lines with no match. Rates, mark-ups and the final price are set by your estimator.
Who designs the workflow?
Our founder is a mechanical engineer with a master's in construction management, with experience across MEP, tendering and construction software. The workflow follows how an estimator reads a pack, not how a generic document tool does.
Where is the data hosted?
The application and stored data can be hosted on Azure UAE North, on private servers managed by Vloud, or in your own cloud account. The AI model is used through a provider agreed per project, and its processing region may be outside the UAE.
Who owns the code?
You own the source code and IP of the custom workflow we build for you. Our own products stay ours, and any licence terms are agreed separately.
Related
Related AI use cases.
Supplier quotation comparison
Read supplier quotes into one comparison, align items, units and terms, and flag missing lines and exclusions before your procurement team makes the award.Submittal and RFI first-pass review
First-pass checks on submittals and RFIs against the specification and drawings, with each point linked to its source and the consultant deciding.Contract clause and variation tracking
Find notice periods, variation clauses and obligations in construction contracts, with each answer linked to its clause, and track every variation to closure.AI document processing
The service page for reading documents into checked, structured data.ArkanERP
Our ERP for construction and project-driven companies, including BOQ control.Construction software in the UAE
Project and commercial systems for UAE contractors.
Next step
Test it on your own documents.
Tell us what the work looks like today. We reply with the questions we need answered before a pilot can be scoped.
