Key Takeaways
- Korean golf-tech company AGL launched Tabi Golf on July 2, 2026 — an AI travel agent that goes from itinerary design to booking and payment for golf trips with a single sentence
- AGL has supplied golf course booking and payment systems to Google since 2024, and it is this real-time inventory and payment foundation that makes an "AI that does not stop at recommendations" possible
- The design — vertical focus, inventory connectivity, and payment execution — offers a realistic model for travel and booking businesses stepping into Agentic Commerce
Tabi Golf: From a Single Sentence to Booking and Payment
AGL launched Tabi Golf, an AI travel agent that plans, books and pays for global golf trips from a single sentence using real-time inventory and prices.
en.sedaily.com"Create a one-week golf trip itinerary in Scotland centered on the world's top 100 golf courses." Enter that single sentence, and the service organizes flights, hotels, golf courses, restaurants, tourist attractions, and travel routes by budget and preference — then completes the bookings and payments on the spot. According to Seoul Economic Daily, AGL, a global golf and travel platform company, officially launched its AI travel agent Tabi Golf on July 2, 2026, delivering exactly this experience. The name "Tabi" comes from the Japanese word for travel.
Here is how it works. When a user enters a desired trip, the AI analyzes the destination, budget, travel period, number of companions, and preferences to build an itinerary. Up to this point, existing generative AI such as ChatGPT can do much the same. What sets Tabi Golf apart is the agent capability that executes booking and payment in one flow. Given an instruction like "Plan a 54-hole golf itinerary in Da Nang for two people with a budget of 2.5 million won and book restaurants too," it goes beyond presenting a plan and proceeds to the booking itself.
Nor is it limited to golf. The service also handles general travel requests such as "Recommend a five-day, four-night trip to Hokkaido with my family next month," and covers destinations worldwide including Japan, Vietnam, Thailand, the United States, and Europe. It currently supports Korean and English, with multilingual expansion to Japanese, Chinese, and other languages planned.
Tabi Golf is not an AI that simply recommends travel itineraries, but one that builds schedules based on bookable real-time inventory and prices. It will become an era in which, rather than users searching and comparing, the AI understands the traveler's intent, designs the entire trip and then carries out the booking.Source: Jim Hwang (AGL CEO)
The Next Move by the Company That Supplies Golf GDS to Google
Viewing Tabi Golf as just another AI travel planner misses the point. AGL's starting point was not conversational AI but booking and payment infrastructure.
Founded in 2019, the company built TIGER GDS, which brought the Global Distribution System — the mechanism long used for airline and hotel distribution — to golf course tee-time reservations. According to Global Golf Times, by the time of its 30 million dollar Series B round in March 2024, it was handling real-time reservations at more than 1,300 golf courses across over 30 countries. The investor list included venture capital arms of Korea's four major financial groups: KB, Shinhan, Hana, and Woori.
The depth of its Google relationship also stands out. In July 2024 it went live with Reserve with Google, enabling real-time bookings at golf courses in more than 25 countries via the "Book Online" button on Google Search and Maps (Golf Business News). The design shows the total price upfront — including green fees and cart fees — and completes payment on the spot. In February 2026, it extended the same booking capability to iOS Maps.
Against this backdrop, Tabi Golf's positioning becomes clear. Long before the AI boom, the company built up the transactional foundation of "inventory that can be queried" and "payments that can be executed," and only then layered a conversational interface on top. The order matters. As CEO Hwang put it, "Thanks to close cooperation with the golf course, hotel, airline and rental car industries since the company's founding, we were able to stay one step ahead in developing a travel agent."
Vertical Focus That Targets the Blind Spot of General-Purpose Agents
In 2026, the travel industry's push into agentic booking is accelerating fast. Google has begun agentic reservations for restaurants and event tickets in AI Mode in the United States, and has announced partnerships with Booking.com, Expedia, Marriott, and others for hotels and flights. Travel distribution giant Sabre has teamed up with PayPal and Mindtrip on what they describe as an end-to-end agentic flight booking system that completes everything from search to payment within a conversation. IDC forecasts that up to 30 percent of travel bookings may be executed by AI agents by 2030.
The numbers describe a massive wave, yet consumers remain cold. According to Skift's reporting, only 2 percent of leisure travelers are willing to let AI book a trip on their behalf. The absence of a framework for who bears responsibility when a booking goes wrong stands as the wall of trust.
A realistic way to close this gap is the vertical-specific approach that Tabi Golf embodies. Golf travel has characteristics well suited to delegating transactions to an agent. Tee times are structured inventory; requests translate easily into concrete conditions like "54 holes" and "a budget of 2.5 million won"; and every trip requires bundling flights, lodging, rounds, and dining. The more complex the arrangements and the more specific the demands, the higher the AI's precision — and the stronger the user's motivation to delegate. While general-purpose agents wrestle with the infinite question of "where to go," a specialized agent can build trust by reliably completing this customer's specific transaction.
What Booking and Payment Businesses Should Take Away
What Tabi Golf's design demonstrates is that competitiveness in agentic travel is determined not by conversational polish but by connected inventory and the ability to execute payments.
The prerequisite is real-time API access to inventory. For an AI to present only "bookable options," availability and prices must be machine-queryable. AGL spent seven years building exactly that in the form of a GDS. For hotels and booking businesses that want to capture agent-driven demand, inventory connectivity is becoming less a marketing tactic and more a condition of participation.
Whether to go as far as payment is another dividing line. An AI that stops at proposing itineraries and an AI that executes payment differ completely in business model and scope of responsibility. Only agents that can complete transactions capture fee revenue and customer transaction data — while also taking on the heavy responsibilities of mis-bookings and cancellations. Tabi Golf chose to cross that line.
Then there is the question of where to start. AGL solidified inventory and payments in the bounded market of golf, and is now extending into general travel such as family trips to Hokkaido. Establishing transactional trust in a vertical before expanding horizontally is a sequence worth referencing for any business entering Agentic Commerce.
Conclusion
AGL's Tabi Golf is an AI travel agent that executes everything from itinerary design to booking and payment for golf trips from a single sentence. Behind it lie the TIGER GDS inventory connections built up since 2019 and the booking and payment infrastructure supplied to Google and Apple Maps.
At a time when trust in general-purpose AI agents has yet to mature, starting transactional delegation in a vertical where demands are specific and arrangements are complex points to a realistic path for agentic travel. Whether the multilingual rollout and expansion into general travel proceed as planned, and how far the inventory and payment foundation built in golf can extend horizontally — as a service that directly touches the Japanese market, it is one worth watching.
