The Generative AI solution “Charla,” developed by MadeinWeb with support from Amazon Web Services (AWS), is transforming the licensing process at the Port of Açu, offering a scalable, secure, and efficient platform. The use of AI for automated queries in Environmental Impact Assessment (EIA) documents has enabled the Port of Açu to improve accuracy, reduce response times, and ensure continuity of operations, reinforcing its position as one of the leading port complexes in Latin America.

 

The Port of Açu faced significant challenges in searching for information within EIA documents, which include data in different formats, such as .txt, .pdf, .xlsx, .docx, .tiff, .json, .jpeg, and .png. The process of searching and extracting information was time-consuming, which impacted response times for regulatory inquiries. In addition, keeping the virtual library up to date and managing information efficiently required a robust solution that could handle these challenges in a scalable and accurate manner.

 

MadeinWeb developed a Generative AI solution supported by AWS infrastructure, creating a Generative Chat “Charla” that optimizes the environmental licensing process. This solution allows for quick and accurate queries to a virtual library composed of technical manuals, standards, and EIA data. The solution is based on a Generation Augmented Retrieval (RAG) system, which searches a vast set of data provided by the Port of Açu, facilitating access to relevant information with precision.

 

Results:

Increased Productivity: The implementation of the solution centralized and automated queries, reducing response time in licensing processes and increasing team productivity.
Greater Operational Efficiency: The Generative Chat “Charla” provided a more agile query experience, eliminating the need to manually search multiple databases.
Scalability and Reliability: The combination of AWS Lambda and Amazon S3 allowed the solution to handle a large volume of data and requests without compromising performance, while ensuring the integrity and security of the information.
Error Reduction: Automation and accuracy in data retrieval reduced the risk of human error and increased security in the licensing process.

 

As part of this presentation, we will show an exclusive video about the project, highlighting how the virtual assistant works, its main features, and the results achieved so far. The aim is to provide an overview of the project.