Customer Service Automation · Enterprise Knowledge Search
Thailand tourism information was fragmented across multiple websites, difficult to verify, often outdated, and hard for visitors to access across languages, creating poor experiences and inefficient support workflows.
Reported impact
Siam AI created a single assistant that can give tourists more reliable and timely information across languages while also giving Thailand tourism stakeholders a modular way to distribute verified destination knowledge through web, mobile, and API channels.
Siam AI and Wipro built an AI tourism assistant called Sukjai on top of SiamGPT so visitors could get reliable travel information through a single multilingual interface instead of navigating disconnected websites. The implementation starts with tourism content from the Tourism Authority of Thailand and additional curated travel data, which Siam AI verifies and improves before using it to train and ground the model. NVIDIA NeMo provides the framework for building the tourism-specialized language model, NeMo Curator prepares the source corpus, and NeMo Retriever grounds responses in approved tourism knowledge. NVIDIA NIM then packages the model as reusable services that can be delivered through web apps, mobile apps, and APIs, giving Siam AI a modular stack for real-time tourist assistance.
Tourism information from the Tourism Authority of Thailand and other sources is verified and curated, then prepared with NeMo Curator for model training and retrieval grounding. Visitor questions are answered through NIM-hosted services that use NeMo-based models and NeMo Retriever to return approved travel guidance across web, mobile, and API delivery channels.
Before the NVIDIA-powered solution was implemented, tourists struggled with fragmented information spread across multiple websites, concerns about information authenticity, outdated content, and language barriers.
SiamGPT features a modular design and supports multiple usage formats, including web applications, mobile applications, and API integration.
The integration of NVIDIA's advanced technologies-particularly the NVIDIA NeMo framework and NVIDIA NIM-enabled the development of a sophisticated tourism assistant platform called Sukjai.
The training data for this model comprises tourism information provided by the Tourism Authority of Thailand.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
LinkedIn's Organization JSON-LD lists addressLocality "Suan Luang", addressCountry "TH", and numberOfEmployees value 17.
Related
ServiceNow Sample Modified · Jul 30, 2026 ServiceNow ServiceNow wanted to close the gap between consumer-grade self-service and the fragmented enterprise support experience, where customers and employees still had to navigate multiple portals, unclear instructions, and… 2.3 million hours saved in 2025 AI Search · AI agents · Knowledge Management 
In-house Sample May 12, 2026 Cohesity Cohesity needed to reduce friction in enterprise support by replacing manual forms, portal navigation, and low-context case intake that slowed diagnosis and increased customer effort during business-critical incidents. approximately 50% of interactions resolved by customers themselves without ever needing to open a case Cohesity NetBackup · Entitlement management system (VEMS) · NextGen Support Portal 
Mistral Sample Apr 24, 2026 SAP SAP needed to reduce repetitive support demand, break down knowledge silos, and automate business processes for regulated, multilingual customers without sacrificing European data localization or trust in AI-generated… 100% European, locally hosted AI, maintained in SAP-operated infrastructure. Microsoft Teams · Mistral Large · SAP Build Work Zone 
