AI for Procurement: Optimizing Vietnam's Largest IT Giant
Customer
A global tech leader and Vietnam's largest IT services provider, with $1 billion USD in revenue (2023) and over 30,000 employees. Facing rapid growth, the company needed to streamline its procurement processes amid complex, high-volume transactions.
Business Needs
The customer relies on two purchasing forms: Business and Non-Business. Our initial focus: analyzing Non-Business data from the e-Purchase system, which aggregates items purchased across member companies. This enables precise determination of optimal pricing and supplier comparisons per transaction.
Key challenges include:
- Inaccurate user inputs leading to flawed data.
- Fragmented product descriptions requiring consolidation into unified profiles.
- Diverse input types for a single shopping purpose (e.g., varying formats across teams).
- Multilingual barriers complicating global sourcing.
Solution
We delivered an AI-powered platform to transform e-Purchase workflows:
- Comprehensive Reporting : Insights into purchase history, effectiveness metrics, and anomaly detection for unusual transaction behaviors. -User Experience Optimization : Reduced data entry time by 40%, streamlined approvals, and automated multi-source data comparisons for enhanced efficiency.
Solution detail
Leveraging QaiDora's innovative tools—like our NEW Synthesis Data feature (using LLMs to extract and customize image-based product features for precise matching)—the system ingests unstructured data, normalizes descriptions, and recommends suppliers in real-time. Paired with Crawler and Extract Information for web-sourced vendor intel, it ensures seamless, multilingual integration.
Technical Stack
- Natural Language Processing (NLP) : Parses multilingual descriptions and detects inaccuracies.
- ML Recommendation Models : Suggests optimal suppliers based on historical patterns.
- Semantic Search : Enables fuzzy matching across diverse inputs for 80%+ accuracy.
Explore our NEW Serverless RAG on AWS for scalable, document-driven querying—deployable in days via Streamlit interfaces.
Results
- Users now source high-quality items at the best prices with intuitive search.
- Product recognition rate >80% for commodities, slashing manual reviews.
- Overall: 25% faster procurement cycles and deeper supplier risk insights.
Conclusion
Deploying AI for Procurement empowers rapid violation detection and cost optimization. Beyond efficiency gains, it unlocks actionable intelligence on suppliers and risks—driving performance, cutting expenses, and boosting profitability in Vietnam's dynamic tech landscape.
Published: September 19, 2024 (Updated for 2025 trends)
Ready to AI-optimize your procurement? Contact QaiDora for a tailored demo.
9/26/2025
NEW
"Use a large language model (LLM) to identify descriptive features from a reference image.
Based on these features, users can customize specific attributes and use the customized information to search for or generate images with similar characteristics."
NEW
Crawl data from websites and use a large language model (LLM) to extract and summarize information that aligns with the user's needs.
NEW
Deploy a Retrieval-Augmented Generation (RAG) system on AWS using a serverless architecture to build an AI application capable of answering questions based on retrieved data. The solution allows users to upload documents, index the data, and interact through a web interface (built with Streamlit) to ask questions, with answers generated by combining information retrieval and the content generation capabilities of a large language model (LLM).
QaiDora Products
QaiDora draws inspiration from the myth of Pandora’s box—a symbol of unexpected possibilities and hope. For us, AI models are like modern Pandora’s boxes, holding untapped potential to turn challenges into opportunities. At QAI, QaiDora serves as an ecosystem of AI products designed to drive innovation and deliver competitive advantages.
Trusted by
Contact us
