Success stories

Prestigious Private University

What if... AI-powered assistants could enhance academic experiences while reducing faculty workload and operational costs?

SERVICE

AI Engineer

INDUSTRY

Education

TECHNOLOGY

FastAPI, Python, Azure, OpenAI models

The client

A prestigious private university in Latin America, known for its commitment to academic excellence and innovation, sought to enhance its student and faculty experience through AI-driven solutions.

Benfits

Improved Student Experience: Students benefit from a reliable, fast, and up-to-date AI assistant, enhancing their learning process.

Increased Faculty Efficiency: Professors can delegate a significant portion of student inquiries to the AI assistant, reducing their workload.

Cost Savings: AI-powered assistants provide a cost-effective alternative to hiring additional teaching assistants, optimizing institutional resources.

Challenge

As part of its continuous efforts to enhance the academic experience, the university sought to modernize its AI-driven assistant solutions. While it had been developing chatbot-based initiatives for years, the evolving AI landscape required an upgrade to existing services. The main challenge was optimizing AI response times while ensuring accuracy and scalability, allowing professors to personalize the bots with course-specific content.

Solution

The project focused on two major AI solutions:

Academic Bot: A customizable AI assistant that acts as a general-purpose chatbot, which professors can tailor for their classes by uploading specific materials such as papers, complementary readings, and lecture notes.

Regulations Bot (Upcoming Development): A planned AI assistant designed to help students and faculty navigate university policies and regulations.

The AI Engineer collaborated with the university’s team using Agile and DevOps methodologies, ensuring seamless integration and continuous improvement of these AI solutions.

Benefits

Improving product descriptions on the online store to enhance the customer shopping experience and increase sales.

Substantial reduce the time needed to input product attributes by leveraging cutting-edge technologies.
The process of completing product attributes was cumbersome and time-consuming. It also resulted in incomplete or error filled product descriptions, impacting the user’s shopping experience.
Using computer vision, we generated product descriptions which contain information about attributes such as color, material, dimensions, size, etc. This information is published on the ecommerce along with the product images.
The project is based on the use of AI generative models, specifically Gemini Pro Vision, to achieve three main objectives:
  • Create new product descriptions by extracting attributes from product images.
  • Enrich these product descriptions using previous information from other products
  • Perform a retroactive process to update the product descriptions when new attributes are found when compared to embeddings generated by Gecko (Google model), i.e., add this information to existing similar products.
Staff Augmentation
Google Cloud Platform (GCP) was chosen for its robust cloud computing capabilities and built-in machine learning services, providing a reliable infrastructure that is highly scalable for heavy computational tasks.
Python was selected as a high-level, interpreted language with an abundance of AI-related libraries, allowing for easy readability, quick prototyping, and sophisticated AI and machine learning projects.
Docker was utilized to automate deployment and scaling of applications, ensuring the consistent operation of the AI model across various environments.
The Gemini Pro Vision Model and Text Embedding Gecko Model were used to offer specialized functionalities in computer vision and natural language processing respectively, providing capabilities such as sophisticated analysis of visual content and representing text data as normalized numerical vectors.
Scroll al inicio