The Generative AI solution “Charla,” developed by MadeinWeb with support from Amazon Web Services (AWS), is transforming Porto do Açu’s licensing process by providing a scalable, secure, and efficient platform. The use of AI for automated queries in Environmental Impact Assessment (EIA) documents has enabled Porto do Açu to improve accuracy, reduce response time, and ensure operational continuity, reinforcing its position as one of the leading port complexes in Latin America.
Porto do Açu faced significant challenges in searching for information within EIA documents, which include data in multiple formats such as .txt, .pdf, .xlsx, .docx, .tiff, .json, .jpeg, and .png. The process of searching and extracting information was time-consuming, impacting response times for regulatory inquiries. Additionally, maintaining an up-to-date virtual library and managing information efficiently required a robust solution capable of handling these challenges in a scalable and precise manner.
MadeinWeb developed a Generative AI solution supported by AWS infrastructure, creating a generative chat system called “Charla” that optimizes the environmental licensing process. This solution enables fast and accurate queries within a virtual library composed of technical manuals, regulations, and EIA data. It is based on a Retrieval-Augmented Generation (RAG) system, which searches through a vast dataset provided by Porto do Açu, facilitating precise access to relevant information.
Results:
Increased Productivity: The implementation of the solution centralized and automated queries, reducing response times in licensing processes and increasing team productivity.
Greater Operational Efficiency: The “Charla” generative chat provided a more agile query experience, eliminating the need to manually search across multiple databases.
Scalability and Reliability: The combination of AWS Lambda and Amazon S3 allowed the solution to handle large volumes of data and requests without compromising performance, while ensuring data integrity and security.
Error Reduction: Automation and accuracy in data retrieval reduced the risk of human error and increased reliability in the licensing process.
As part of this presentation, an exclusive video will be showcased, highlighting the virtual assistant’s operation, its key features, and the results achieved so far, providing an overview of the project.
