Back to blog
AI for Architects3 min read

DCE document consistency check with ChatGPT: method and checks

Compare drawings, CCTP, DPGF and CCAP in a source-linked discrepancy register.

By Educasium

Install the ChatGPT skill: DCE document consistency check

Compare drawings, CCTP, DPGF and CCAP in a source-linked discrepancy register.

Prepare the documents

Named tender documents, revisions and dates, trade codes and available measurement evidence.

Name files with dates and revision IDs. Identify approved documents and templates. The pack supplies a method; project facts must come from your documents.

Organize the work with ChatGPT

Inventory revisions first. Map trade, element, CCTP article, DPGF item and drawing reference. For each discrepancy request two precise references, a possible consequence and a proposed correction. Separate confirmed anomalies from unverifiable points.

A fictional example to test

Fictional example: drawing P02 revision B shows a 90 cm door while CCTP article 4.2 specifies 83 cm. Record a referenced discrepancy; do not pick the correct dimension or change source files.

Review the deliverable

Review both sources for each discrepancy and actual review coverage. Finding no discrepancies does not show that all documents were checked.

Request the editable file, open it and compare it with sources before approval. File creation depends on tools available in your session. This pack uses French instructions and deliverables; the linked skill page explains importing it and includes a copyable request.

ChatGPTarchitecturecontrole-coherence-dce

Want to go further?

Discover our specialized AI training for your profession.

View training programs