LY Corp, a joint venture between Japan’s SoftBank Group and South Korea’s Naver Corporation, has revealed how it utilizes an in-house implementation of ChatGPT to enhance the efficiency of its quality assurance (QA) operations. The company, known for its flagship messaging app LINE, turned to generative AI after engineers struggled with extracting vital information from documents and Slack threads—a major issue given the frequency with which these materials are updated. To address this, LY Corp introduced the Plan Advisor tool, powered by ChatGPT, which summarizes documents, details progress in a structured format, and allows for various forms of summaries through additional conversations. Another tool, the Thread Summarizer, was developed to manage the extensive communication that takes place on Slack. In response to these challenges, the Thread Summarizer uses ChatGPT to produce concise meeting minutes, recording the issue initiator, thread summary title, main discussion points, conclusions, problems, and action items. This saves time and ensures that critical information is accurately captured and easily accessible. Is it available for test or do you create for your own? — Kamil Tracz (@KamilTracz) August 23, 2024 Additionally, the company employs a tool called App Reviewer, which analyzes reviews of its products posted on app stores across multiple countries. This tool translates reviews, analyzes sentiment, and summarizes key issues by country in a tag cloud format. The use of ChatGPT at LY Corp showcases the growing role of AI in enhancing productivity and quality in the tech industry, particularly in managing complex workflows and large volumes of information. Comment
This strategic integration of AI tools addresses the company’s immediate challenges and sets a precedent for future advancements in quality assurance and collaboration. For more news and insights, visit AI News on our website.
Beyond these tools, ChatGPT is also used to derive new test cases for LY Corp products and to describe bugs, further integrating AI into the QA process.
by from discussion
inQualityAssurance
Drowning in Slack? Asia’s Top Messaging App Devs Turn to ChatGPT for Rescue!
-
Digital marketing enthusiast by day, nature wanderer by dusk. Dave Andre blends two decades of AI and SaaS expertise into impactful strategies for SMEs. His weekends? Lost in books on tech trends and rejuvenating on scenic trails.Dave Andre
Digital marketing enthusiast by day, nature wanderer by dusk. Dave Andre blends two decades of AI and SaaS expertise into impactful strategies for SMEs. His weekends? Lost in books on tech trends and rejuvenating on scenic trails.
Key Takeaways:
SooGwang Chae, a quality engineer at LINE, detailed the challenges faced by the QA team. He explained that previously, QA engineers had to manually identify key features and compare changes for each update, a process that was both time-consuming and prone to errors.
“At LY Corporation, Slack is the primary communication tool, and such discussions usually take place in thread form,” Chae wrote, adding that QA engineers spend “a lot of time” trying to understand the threads’ content once planning and development discussions end.
“You can also distinguish whether the review is about a feature improvement or a feature error and get opinions on which parts to test further from a testing perspective,” he wrote.
Chae concluded by emphasizing the positive impact of generative AI on LY’s QA team, stating, “”By thoughtfully integrating generative AI into QA tasks, organizations can not only streamline their workflows but also ensure higher quality outcomes,” he explained. “As the technology continues to evolve, the potential applications and benefits will only grow, making it an exciting time for QA professionals to explore and innovate.”
Was this article helpful?
YesNo
Digital marketing enthusiast by day, nature wanderer by dusk. Dave Andre blends two decades of AI and SaaS expertise into impactful strategies for SMEs. His weekends? Lost in books on tech trends and rejuvenating on scenic trails.
