
AI Concierge for a Regional Resort Group — 91% Self-Service, 321 Leads in 5 Weeks
An AI concierge live across Facebook Messenger, LINE, and the brand website for a hot-spring resort in a regional hotel group — handling 91.1% of guest conversations on its own and capturing 321 booking leads in its first 5 weeks.
All Case Studies
AI ChatbotAI Concierge for a Regional Resort Group — 91% Self-Service, 321 Leads in 5 Weeks
AI AutomationAI Agent for Automated Expense Entry — Import/Trading Business
AI ChatbotLINE AI Chatbot for an Industrial Valve Distributor — 90% Self-Service Across 3,260 SKUs
AI AutomationCross-Company Accounting Automation — Multi-Property Hospitality Group (Phase 1)
AI ChatbotLINE File-Memory Assistant — MVP Delivered 23 Days Early

Cross-Company Accounting Automation — Multi-Property Hospitality Group (Phase 1)
Full Case Study
The Client
A hospitality group running several companies under one ownership structure, all bookkeeping handled by a single accountant using a mix of accounting software and manual Excel across properties.
The Challenge
The Solution
Phase 1 built the foundation. The system pulls automatically from 8 sources on the client's own OneDrive on a schedule, unifies everything into one master data structure common to every company, runs a rules-based three-way reconciliation — bookings vs. accounting software vs. bank — rather than letting AI guess at matches, and has AI write a daily plain-language summary that leadership reads straight from LINE, no accounting jargon and no waiting on the accountant to translate the numbers. The system flags itself automatically if a source file doesn't update or a run fails.
Why Safety Came Before Speed
This group was handling highly sensitive cross-company financial data, so the client set data-security conditions before agreeing to the project at all: no real data would be seen during development — only self-made simulated data standing in for the real thing — and when it came time for the first real-data test, the client ran the system themselves, on their own machine, sharing only their screen rather than the data itself. Every account the system runs on stayed in the client's name throughout. Out of the group's several companies, the client chose to prove the system on one pilot company first, using simulated data, before expanding to the rest — reducing risk on both sides: the client saw it actually work before committing further, and no real data needed to be touched until the architecture had already proven stable.
Key Technical Decisions
The Results
An Honest Note on What Comes Next
As of this case study, the client has since extended the system to real data across all 5 companies in the group, with daily automated runs checked and showing no issues, and a related sales-tracking module now verified working against real deals. That expansion is still actively in progress, not a closed deliverable — a full real-data test, a training walkthrough, and a final handover of system access back to the client haven't happened yet, so this project isn't being described as fully complete. Phase 1, the foundation described above, is the confirmed, tested result this case study stands behind.
Lessons Learned
Project Information
More Like This
AI ChatbotAI Concierge for a Regional Resort Group — 91% Self-Service, 321 Leads in 5 Weeks
96% MatchAn AI concierge live across Facebook Messenger, LINE, and the brand website for a hot-spring resort in a regional hotel group — handling 91.1% of guest conversations on its own and capturing 321 booking leads in its first 5 weeks.
AI AutomationAI Agent for Automated Expense Entry — Import/Trading Business
96% MatchAn AI agent that reads, classifies, and enters roughly 10 expense documents a day into the client's PEAK accounting system — validated against 45 of 48 real documents (93.75%) before go-live, self-hosted with no ongoing platform fee.
AI ChatbotLINE AI Chatbot for an Industrial Valve Distributor — 90% Self-Service Across 3,260 SKUs
96% MatchA LINE chatbot that answers pricing questions, drafts quotations and invoices, and reads product photos and payment slips for a one-person industrial valve and pump distributor — handling 90% of routine questions across a 3,260-item, 52-brand catalog, built in 7 days.