back_office_ops · realestate · workflow
NTT DATA builds GenAI POC to classify and prioritize work orders for international infrastructure company
A leading international infrastructure company manually processed roughly 1,500 work orders per day using 70 employees, creating significant opportunity for error and inconsistency in categorization across more than 500,000 annual maintenance requests.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Work order request submitted
Operators or technicians enter information and notes into the work order management system for each maintenance request.
Tools used
large language model (LLM)
Outcome
The GenAI POC demonstrated the capability to classify work orders more quickly, accurately, and consistently than the manual approach, with the LLM providing an audit trail explaining each classification; the company plans full deployment once the LLM consistently demonstrates its usefulness.
Results
Time savedabout 1,500
Volume500,000-plus
Grounding & classification
Source type: vendor customer story
20 fields verified against source quotes.
content generationdocument classificationknowledge basesupport ticketmetric backedtools describedvendor confirmedworkflow describedreal estateaccuracy improvementcycle time reductionvendor customer storyback office opsticket triageextract classify route