Read the Story in Japanese

TOKYO, Japan – Even with the best planning, unexpected events can occur on a small percentage of flights, such as a passenger falling ill or a prolonged delay.

After attending to these situations, the senior cabin attendant creates a report for ground staff to follow up on, which may include arranging for a wheelchair at the gate or reorganizing onward travel.

Generating a single report can take an hour or more, depending on the complexity, taking away from other in-flight duties. To address this, Japan Airlines (JAL) is developing an AI-powered app that allows cabin attendants to create handover reports by simply typing in a few keywords and phrases and checking a series of boxes, all while in the air, even without reliable connectivity.

Streamlining Reporting

"The JAL-AI Report makes our cabin attendants’ jobs more productive," said Keisuke Suzuki, a senior vice president of JAL’s Digital Technology Department. "They can spend more time on customer service instead of doing administrative work."

Keisuke Suzuki, senior vice president in charge of JAL’s Digital Technology Department, noted that the JAL-AI Report will enable faster report generation, giving cabin attendants more time with passengers. Photo by Noriko Hayashi for Microsoft.

The JAL-AI Report is being developed using Microsoft’s Phi-4 small language model (SLM), which requires less computing power than large language models (LLMs) and can be used offline on a device for specific tasks.

Cabin attendants who have tested the app report that it can reduce report-writing time by up to two-thirds, from one hour to 20 minutes, or from 30 minutes to 10 minutes for simpler cases.

Making an AI App Work Offline

Japan’s flagship carrier operates a fleet of 227 planes flying worldwide and serves 66 countries and regions, including code-sharing. Last year, it ranked sixth among the world’s best airlines for customer satisfaction, according to Skytrax. Its current group chief executive, Mitsuko Tottori, is the first woman to lead the airline, having risen through the ranks from cabin attendant.

The JAL-AI Report is being developed with the help of Microsoft’s Azure AI Foundry and uses Microsoft’s Phi-4 SLM. While LLMs are suited for complex tasks requiring advanced reasoning and analysis, SLMs can handle simpler tasks and run locally on a device rather than in the cloud.

Tech in Flight

Takako Ukai joined JAL as a cabin attendant 35 years ago and enjoys meeting and talking to people from around the world. However, the business has changed over the years, with passengers now expecting more from full-service carriers like JAL.

Ukai, currently a member of the airline’s employee experience team, provides a cabin attendant’s perspective to JAL’s digital transformation team. She notes that reporting incidents has become more formalized, with senior cabin attendants filling out templates on tablets, including free text sections that require typing in chronological order what happened.

Simplifying Reporting

The JAL-AI Report app speeds up the process by guiding cabin attendants through a series of checkboxes and prompts for keywords and phrases. The AI may ask follow-up questions to prevent omissions in reporting. Once complete, the cabin attendant can generate the report with a single tap, and another button translates it from Japanese to English if needed.

The app can reduce reporting time to about 20 minutes from an hour, according to Ukai.

Better Quality Reports

Of the 1,000 flights JAL operates daily, a small percentage involves report creation when an event requiring a handover occurs, said Manabu Yamawaki, manager of security planning in the System Management Department. These reports are sent to relevant departments, from security to customer service and ground staff.

Yamawaki believes the JAL-AI Report can improve report quality, as some cabin attendants currently write more detail than necessary. After the proof-of-concept period ends, the challenge will be ensuring the system works well offline.

In the future, Yamawaki would like the JAL-AI Report to be able to receive verbal accounts from those involved, transcribe and summarize the information, and generate a report.

Generative AI Across JAL

The JAL-AI Report app is part of a broader rollout of generative AI across JAL, which began in mid-2023. All 36,500 employees now have access to AI tools grouped under JAL-AI Home on the Microsoft Azure OpenAI platform for administrative tasks like drafting emails, summarizing and translating documents, and more.

JAL sees opportunities to "put generative AI at the center of the business and bring changes in operations and customer service," said Suzuki. "We are excited to have AI and humans work together."