logo
EventsNews15.09.2025

WEBINAR RECAP | Turning Private Enterprise Data into Real-World GenAI Solutions

On September 11, 2025, SotaTek and VNG Cloud successfully co-hosted the webinar “Building GenAI Projects with Enterprise Data”, attracting over 80 participants, including CTOs, Data Scientists, and engineers from a diverse range of industries.

The session offered a full-spectrum view of what it takes to turn GenAI from a concept into a working product. From infrastructure to business use cases, attendees explored how to apply GenAI in enterprise settings, powered by real examples, including the development journey of Sotabox, a proprietary chatbot solution built by SotaTek.

From Strategy to Deployment: The Story Behind a Real GenAI Product

Vũ Thế Anh, Head of Data Science at SotaTek and CEO & Founder of Sotabox, kicked off the session with insights into the challenges of building GenAI products from the ground up. He also delivered a live demo of Sotabox.ai, a no-code GenAI chatbot designed to help businesses extract insights, retrieve knowledge, and streamline decision-making using their own internal data.

Screenshot of the Sotabox dashboard interface developed by SotaTek, showcasing a GenAI-powered enterprise chatbot designed for internal data retrieval and smart query handling.
The Sotabox dashboard developed by SotaTek, demonstrating how GenAI can be applied to internal enterprise data for smart, no-code interaction.

Unlike generic AI tools that rely on external models, Sotabox is trained on domain-specific datasets and optimized for enterprise use. Key features include Agentic RAG integration, deep contextual search, and seamless connectivity with internal systems, positioning Sotabox as a true knowledge agent tailored for business operations.

Joining from the infrastructure perspective, Mai Hải Dương, Product Manager of Cloud & AI at VNG Cloud, highlighted how local cloud-native technologies are helping Vietnamese businesses build and scale AI systems securely, efficiently, and with less complexity.

Overview diagram of key components in an AI project, as presented by Mai Hai Duong from VNG Cloud, illustrating the infrastructure, data flow, and deployment layers.
AI project architecture shared by Mai Hai Duong (VNG Cloud).

Addressing the True Cost of Building AI

One key discussion point centered on the hidden costs of AI projects, including infrastructure setup, model experimentation, talent acquisition, and deployment timelines.

Speaking from experience, Vũ Thế Anh described the early days of SotaTek’s AI journey. Building infrastructure from scratch, maintaining DevOps pipelines, and managing multiple model experiments proved costly and difficult to scale. The transition to VNG Cloud AI Stack was a turning point, reducing operational overhead, accelerating development, and allowing the team to stay agile without compromising performance or control.

Local Infrastructure Matters: Performance, Privacy, and Speed

When deploying AI, infrastructure is more than just a backend; it defines the speed, reliability, and security of your solution. According to SotaTek, using VNG Cloud’s managed services, including high-speed file storage, real-time Kafka pipelines, and monitoring tools, has helped significantly reduce operation costs and improve customer experience.

With data centers located in both Hanoi and Ho Chi Minh City, Sotabox.ai benefits from low-latency performance and consistent system availability, outperforming several international providers in key performance metrics.

From VNG Cloud’s perspective, their AI Stack is designed to be an all-in-one AI ecosystem that includes native vector databases, real-time orchestration, and compliance-ready security. This allows Vietnamese businesses to focus on building AI applications while relying on a fully managed and scalable infrastructure layer.

Lean Scaling for Long-Term Growth

The speakers also addressed the challenges of scaling AI systems. Rather than building heavy open-source systems with unnecessary features, SotaTek adopted a lean development approach - only implementing essential components using C and Golang. This has helped optimize performance, reduce overhead, and create a flexible foundation for future AI expansion.

Why Sotabox Matters for Enterprise GenAI Adoption

For many businesses, GenAI remains a buzzword until it’s tied to tangible outcomes. Sotabox bridges that gap, transforming internal data into a usable interface that improves access to information, enhances productivity, and simplifies complex workflows.

Whether deployed as a customer support assistant, an internal knowledge engine, or a smart layer on top of business documentation, Sotabox proves that GenAI doesn’t have to be costly, complicated, or disconnected from reality.

Advanced features of Sotabox, including Agentic RAG integration, contextual search, and enterprise system plugins.
Key advanced features of Sotabox for enterprise GenAI use.

It is designed to be scalable, secure, and easy to integrate, offering enterprises a practical path to test, deploy, and expand GenAI without needing in-house AI expertise.

Looking Ahead: Co-Building the Future of AI in Vietnam

This webinar not only unpacked the real challenges behind GenAI adoption, but also underscored the joint commitment of SotaTek and VNG Cloud to making AI more accessible, applicable, and scalable for Vietnamese enterprises.

Experience Sotabox for yourself at: https://sotabox.ai/
For product demos, infrastructure consultation, or collaboration inquiries, reach out to the SotaTek team today.

We look forward to continuing the conversation, both online and at future events, shaping the future of GenAI.

About our author
Tyler Luu
Co-founder & Group CEO
I’m Tyler Luu, Chief Executive Officer (CEO) of Sota Holdings Group, where I oversee the strategic direction of the organization. I also serve as the Co-Founder and Group CEO of SotaTek, as well as an Executive member of BEESOTA. My passion for science and technology began early during my years at Vietnam National University, where I was honored to receive the Honda YES Award for five consecutive years. Today, I’m proud to lead SotaTek in delivering customer-centric products on time and at scale, driving successful international projects and establishing our reputation for innovation and excellence.