South KoreaManufacturing2024 – ongoingHL Mando
Generative AI classification of quality claims and customer requirements
HL Mando reported about 80% less claims-classification effort after introducing generative AI
Problem
Engineers manually classified customer requirements and quality claims. Unstructured descriptions produced inconsistent classifications and took time to interpret.
Approach
HL Mando developed a model for automotive engineering language in a protected environment. It generated draft requirement classifications and classified incoming claims, which engineers reviewed and corrected.
Results
Takeaway
The reported labor reduction came from shifting engineers from manual classification to reviewing AI output.
Categories
- Size
- Large enterprise
- Industry
- Manufacturing
- Business function
- Production and qualityIT and R&D
- Innovation type
- Process innovation
- AI technology
- Generative AI
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
An HL Mando researcher described deployed AI classification of requirements and quality claims. He reported about 96% classification accuracy and about 80% less effort, with engineers checking the results.
Full details are in the original sources.
