LY Corp, a joint venture between Japan’s SoftBank Group and South Korea’s Naver Corporation known for its flagship messaging app LINE, has detailed how it uses an internal ChatGPT implementation to keep its quality assurance (QA) tasks on track.
A post on Thursday revealed that the organization has turned to generative AI to support its quality assurance efforts.
One reason for adopting this technology is that engineers were having difficulty extracting information from documents and Slack threads.
As SooGwang Chae, Quality Engineer at LINE, explains, the QA team had difficulty tracking changes in frequently updated planning documents.
“Previously, with each update, QA engineers had to identify the most important features and compare and organize the changes,” he wrote. Now, a Plan Advisor tool uses ChatGPT to summarize documents, present progress in a structured format and “also allows various forms of summaries through additional conversations.”
Another tool – Thread Summarizer – reads Slack threads and turns them into meeting minutes.
“At LY Corporation, Slack is the main communication tool and such discussions usually take place in thread form,” Chae wrote, adding that QA engineers spend “a lot of time” understanding the content of the threads once planning and development discussions are over.
If QA engineers had further questions, they could end up participating in or monitoring every thread. Chae wrote, “This would consume a lot of QA resources and is not realistic.”
And we thought Slack was the future of collaboration after Salesforce bought it for $27.7 billion.
It turns out that the future for LY is ChatGPT, which aggregates these threads to create logs that record the initiator of the issue, the title of the thread summary, key discussion points, conclusions, issues, and action points.
ChatGPT is also used to derive new test cases for LY Corp products and describe defects.
In another use case for generative AI, the Japanese-Korean organization analyzes reviews of its products published in app stores. To do this, it takes into account opinions written in different languages in the many countries where LINE users live.
This is done using a tool called App Reviewer, which Chae says translates reviews and analyzes sentiment in each country, as well as summarizing key topics by country in a tag cloud format.
“You can also distinguish whether the review is a feature improvement or a feature defect and get opinions on which parts should be further tested from a testing perspective,” he wrote.
Chae’s post concludes that ChatGPT and generative AI are making a positive difference for LY’s QA team.
“Thoughtfully integrating generative AI into QA tasks will enable companies to not only streamline their workflows but also achieve higher quality results,” he explained. “As the technology continues to evolve, the potential applications and benefits will only increase, making it an exciting time for QA professionals to explore and innovate with new technologies.” ®
