Case Studies

We have helped 200+ companies transform their business with top-notch tech solutions.

AI Automation Agency Service - Gen AI in Financial Data Project

Services: AI

We helped a Japanese client unlock financial insights using generative AI through a cost-efficient, Azure-based solution. By integrating hybrid search (full-text + vector) and advanced prompt engineering, we enabled accurate, natural language data exploration—delivering scalable AI automation for finance with optimized performance and reduced ChatGPT costs.

This case study showcases our end-to-end AI Automation Agency Service, which tackles both the technical and financial challenges of deploying large language models. By combining full-text and vector search into a hybrid retrieval system and fine-tuning prompt engineering techniques, we delivered a cost-optimized, Azure-native solution that empowers users to query financial data accurately through ChatGPT—all while maintaining scalability, speed, and affordability.

Client Problem:

Our Japanese customer possesses a wide range of financial data and seeks to harness the power of generative AI to explore these data through natural language conversations.

Challenge:

Conducting hybrid searches (combining full-text search and vector search) to ensure accurate data input into OpenAI's prompts poses a significant challenge. Furthermore, considering the cost of ChatGPT, optimizing expenses becomes crucial to provide the product to customers at an affordable price.

Tech Stack: Python, Azure native services (Cosmos DB, AI Search, OpenAI, App Service, Function Apps...)

Our Solution:

We have developed a production solution residing on Azure that cleanses and ingests financial data into a vector database. Moreover, we have implemented hybrid search, which combines full-text search and vector search, resulting in accurate data retrieval. Additionally, we have actively participated in prompt engineering to enhance ChatGPT's completions.

Case studies

Intelligent Document Processing with AI Agent and OCR on Azure

Tinhvan Software built an Azure-based AI Agent and OCR tool to automate document search and image text extraction, enabling fast, secure, and structured data access. We developed an intelligent AI Agent and OCR pipeline to help enterprises query internal documents using natural language and extract structured data from image files. Built on Azure with infrastructure-as-code, the solution improves knowledge access, streamlines document processing, and enhances efficiency through secure, scalable cloud-native architecture.

AI Enterprise Management

Machine Learning System for Geophysical Reservoir Property Prediction (Phase 2)

Tinhvan Software built a machine learning platform to help geologists automate reservoir property analysis. The solution uses boosting models, domain-specific preprocessing, and interactive visualizations—empowering experts to interpret large-scale geophysical data faster and more accurately, with minimal technical overhead.

Petrology Prediction Model – AI for Geoscience (Phase 1)

Petrology Prediction Model, developed by Tinhvan Software for the Vietnam Petroleum Institute, applies machine learning to well log and core sample data, enabling accurate geological insights while reducing reliance on costly manual sampling and accelerating model testing in real-world exploration.