The director of data for a Seattle civil and marine contractor outlines problems his company faced to fix data inconsistencies in its effort to embrace AI tools, in a Construction Dive column.

Because of unclear nomenclature, AI couldn’t deduce simple issues such as which submittal revision was current. “AI couldn’t answer that question with confidence, since we didn’t know the answer ourselves,” he notes.

The same document was saved in multiple places, under several names, with no information about which one was up to date. Only the project supervisors knew which file was the most current.

AI cannot work when there is such unclear information. The answer is to develop an ontology, a digital model of the company that harmonizes the way the field and the back office speak using a shared language.

“It starts with what a folder is called, what goes in it, and how a file gets named when someone saves it from a jobsite trailer at the end of a long shift,” the column says.

The article offers these tips:

• Treat your first months of AI use as a data audit. Every bad answer points to a file, folder, or naming problem.
• Agree on the folder names, document types, and file-naming rules that your AI will use.
• Pilot your naming convention on one live job with a PM who owns it.
• Decide what’s authoritative and put a person between working files and the material AI treats as the truth.
• Train and hire for adaptability. The skill you’ll need most is a willingness to change how work gets filed.