JapanFinance and insurance2023 – ongoingMeiji Yasuda Life Insurance
Generative AI for internal Q&A content
Karakuri reported about 40% less Q&A creation work at Meiji Yasuda
Problem
Meiji Yasuda needed Q&A content for its internal inquiry search system. Preparing that content from manuals and past inquiry logs required staff work.
Approach
Meiji Yasuda and Karakuri tested generative AI over approximately 3 months. Departments evaluated generated Q&A while the team adjusted document preprocessing and prompts. Karakuri reported that formal adoption was decided for January 2024.
Results
Takeaway
Departments needed different levels of detail in generated answers. The team adjusted prompts and output formats to those requirements.
Categories
- Size
- Large enterprise
- Industry
- Finance and insurance
- Business function
- Internal work and knowledge management
- Innovation type
- Process innovation
- AI technology
- Generative AI
- Adoption
- Partner co-development
- Evidence
- Vendor case study
Sources
Source summaries
Karakuri reported that a pilot generated internal Q&A from manuals and inquiry logs. It claimed about 40% less content-creation work and announced a decision to adopt the system formally.
Full details are in the original sources.