
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

AI Agent for Automated Expense Entry — Import/Trading Business
Full Case Study
The Client
An import/trading business buying from Thai e-commerce platforms and overseas vendors, running PEAK Account as its bookkeeping system. Every expense document — receipts, invoices, freight bills, foreign vendor bills — was still being read and keyed in by hand.
The Challenge
The Solution
An AI agent was built to sit in front of PEAK Account. Staff forward each expense document through a private channel; the agent reads it, classifies it against the client's real document taxonomy, applies the correct VAT and withholding-tax treatment, converts foreign bills at the correct daily exchange rate, and drafts the entry directly into PEAK — with the original file archived and linked back to the entry for audit. The agent is instructed to ask rather than guess whenever it isn't confident.
Why Confirm-Before-Key, Not Auto-Post
Before quoting, the client's actual PEAK expense-entry channel was tested directly to confirm it supported everything needed — multiple line items per document, withholding tax, foreign currency, VAT invoices, payment status, file attachments. It supported all of it, with no category hitting a platform limit. The core design decision followed from one fact: PEAK is the client's live production accounting system with no separate sandbox to safely make mistakes in. So every document is written as a draft first, and a human must tap "confirm" over a private channel before anything posts to the real ledger. The agent never writes to the live books unsupervised, no matter how confident it is — the risk is deliberately placed on "wait for approval" rather than "guess and hope it's right." The build was staged across 3 phases, each proving a new capability against real documents before the next phase started: first, correct classification of real documents flowing through the private channel; second, connecting that classification to actually posting into PEAK, verified line-by-line against PEAK's own generated reference documents; third, closing the remaining risk points (credit notes, file attachments, self-hosted migration) before handover.
Key Technical Decisions
The Results
Staying Transparent About What Came Up After Go-Live
During the free 30-day warranty period, running on the client's own computer and network (instead of infrastructure the developer monitors directly) surfaced a few issues that hadn't shown up in earlier testing: brief connection drops when the network hiccuped, some low-quality scanned documents that were harder to read, and a handful of uncommon tax edge cases (like certain shipping fees that don't require withholding). All of it was fixed and re-verified against real documents during the warranty window. The confirm-before-key step meant none of these issues ever reached the real books unsupervised — no incorrect entry was ever posted without a human approving it first.
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 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.
AI AutomationCross-Company Accounting Automation — Multi-Property Hospitality Group (Phase 1)
96% MatchA cross-company accounting automation pipeline for a multi-property hospitality group's single accountant — pulling files from OneDrive, reconciling bookings against bank statements and accounting-software records, and sending a daily AI-written summary to LINE. Phase 1 passed all 9 planned test items in 10 days.