AI System for Preparing a Quantity Check Draft from Survey Notes

The problem

In day-to-day operations, site notes may differ from drawings. When survey notes, drawings, revisions, work-item lists and units of measurement are spread across different screens, documents or team records, the issue may not be noticed in time.

This fragmented data delays preparation of the quantity check draft and forces staff to search for supporting records again by hand. Before deciding, the quantity surveyor must complete missing fields and verify each inconsistency individually.

A common exception is that an approved site change may differ from the project design. If this context is not checked, an incomplete or incorrect automation could carry an incorrect quantity into a quotation or progress claim, so the output cannot be acted on directly.

What we set out to improve

• Share of items corrected by the quantity surveyor
• Share of outputs corrected or rejected by the quantity surveyor
• Time between the source record and the review output

How the system works

1. 01 Define the review scope and the authorised quantity surveyor role
2. 02 Collect the inputs: survey note, drawing, revision, work-item list and unit of measurement
3. 03 Check the source identifier, date, version and data freshness
4. 04 Extract the measurement and location
5. 05 Match the record to the revision and work item
6. 06 Check the exception: an approved site change may differ from the project design
7. 07 Place low-confidence or conflicting records in a separate human review queue
8. 08 Write the source identifier, rule, output and timestamp to the audit trail
9. 09 Have the quantity surveyor approve, correct, defer or reject the output

Methods we used

• Extraction with source-page and revision references
• Source, format, version and required-field checks for survey notes, drawings, revisions, work-item lists and units of measurement
• A missing-data alert instead of an estimate when inputs are absent or conflicting
• Separate handling of exceptions and the main rule
• Joint retention of the source identifier, rule result, quantity check draft and human decision

Where people stay involved

Data and security

Access to survey notes, drawings, revisions, work-item lists and units of measurement is limited to the minimum permissions needed for the task. Identifiers and sensitive fields are masked where possible, and only the necessary section is sent to the model rather than the full raw file. Access, output and the quantity surveyor's decision are logged; production use does not begin until the organisation approves the retention period and data location.

Who this suits

Frequently asked questions