Success stories

As part of its modernization and continuous improvement process, ANCAP explored the incorporation of artificial intelligence to enhance the management of case files and administrative documentation.

Through a pilot project, we analyzed different use cases related to document classification, search, and generation. This initiative made it possible not only to measure the technical impact of the solution, but also to estimate its operational benefits, costs, and feasibility within a complex organizational context, with high requirements for traceability, confidentiality, and regulatory compliance.

Technical overview

Client: ANCAP (Administración Nacional de Combustibles, Alcohol y Portland)

Size/location: Public company in Uruguay that operates as a national reference in the production and distribution of alcohol, Portland cement, and fuels, providing services across all regions of the country.

Main objectives:

• Explore the use of artificial intelligence in case management, applying Azure OpenAI models across a set of use cases.
• Evaluate the benefits and costs of incorporating these technologies to support classification, search, and document generation tasks.

Objectives and challenges

The problem faced by the client before adopting the solution:

• Case file headers were created manually, indexing cases by topic, subtopic, or patronymic criteria, identifying key entities such as companies, individuals, agencies, or institutions. The project aims to automate identification and classification using artificial intelligence to improve process reliability.
• The project also seeks to enable data cleansing and normalization of the database.
• Information classification (public, restricted, confidential) was performed by users. Delegating this task to artificial intelligence ensures that decisions are based on content and attachments analysis, increasing traceability and reinforcing compliance with confidentiality policies.
• Users did not use the advanced search functionality due to its technical complexity. To address this, artificial intelligence is proposed to allow queries in natural language, interpreted by the tool to deliver more comprehensive results.
• Resolutions were manually generated from draft resolutions. By automating this process with artificial intelligence, business rules and predefined formats would be applied, reducing manual tasks to result validation only.

Client goals

Through the implementation of artificial intelligence, the client aims to:

• Automate and increase the reliability of processes.
• Improve efficiency and document traceability.
• Reduce manual workload for employees.
• Strengthen confidentiality and policy compliance processes.
• Simplify tools so all users can operate them.
• Reduce validation times.

The solution

The project was planned in three stages. During the preparation phase, the scope was agreed upon, timelines, costs, and efforts were estimated, and the framework was defined.

In the second stage, a pilot project was built and presented to the client for validation.

Based on the pilot results, AI models are refined for progressive improvements, working jointly between the development team and the functional area.

Integration with an MCP Server is proposed.

The tool becomes more accessible by enabling interaction in natural language.

Results achieved

• For thematic and patronymic classification, efficiency improved through the generation of an initial summary.
• Subsequent classification and analysis tasks were simplified.
• Topics, people, companies, and names related to the nature of the case file were correctly identified by the AI, improving the existing database with reasonable suggestions.
• In confidentiality and restricted classification, AI showed strong performance.
• Greater rigor was observed in applying legal criteria compared to usual practices.
• In advanced case search, flexibility for users was maintained without compromising the technical accuracy required by system filters.
• The generated information has a structure adaptable to thematic and patronymic filters within the system.
• In automatic resolution generation, the results correctly respected established rules, optimizing validation times.

Conclusion

The experience confirmed that applying artificial intelligence to case management delivers concrete improvements in efficiency, traceability, and task simplification for users.

The pilot results provide a solid foundation for future evolution stages, consolidating AI as a strategic tool to strengthen document management in large-scale organizations.

The old ePrios was a program with outdated technologies that required installation, meaning much of the process had to be carried out manually. The new ePrios system is a web application that allows for information digitization, process automation, and communication between the different departments involved, making audits more efficient.

Technical data sheet

• Client: Ministry of the Interior – National Directorate of Forensic Police.
• Size/Location: Covers the entire national territory and embassies worldwide.
• Main objectives:
  • Provide better quality of information.
  • Maintain a better record of judicial antecedentes.

Objectives and challenges

The problem the client faced before adopting the solution:

• It was not possible to associate a photo with each record.
• There was no option to mandate the entry of certain data, leading to the loss of relevant information.
• Previously, ePrios was a program that had to be installed on a PC. This meant that it could only be used on the computer where the program was installed, in addition to all the costs and logistics involved in installing the program on that computer.
• Real-time identity verification was not possible, so the person was logged as who they claimed to be, which could be incorrect.
• Different programs were used for logging adults and minors, with separate databases and different functionalities. For example, the minor’s program did not indicate when a person had already provided a DNA sample, leading to repeated sample collection, which resulted in additional costs and excess work for the staff.
• The system did not allow for modifications or improvements to the service.
• The lack of alerts or notifications made collaborative tasks difficult, hindering cooperation between departments.
• It had no interaction with other services.

These problems affected costs, time, and excessive work:

• Logging took approximately 30 minutes.
• In many cases, logs were not done in real-time but were accumulated and later entered into the system. As a result, the information was not available immediately.
• Information from the interior of the country was sent to Montevideo, and only in the capital were the minor logs entered into the system.
• Judicial communications were not digitized, so when a request for a certificate of criminal records was made, the physical files of records had to be manually checked, taking time for an outdated task.

Client objectives:

• Obtain real-time information.
• Minimize identity verification time.
• Unify the databases.
• Unify the record number at the national level.
• Reorganize the numbering of the photographic record.
• Have concise and precise audits.

The solution

• The system transitioned from a program to a web application, allowing access from multiple PCs in each headquarters.
• The servers are now under the Ministry of the Interior (MI) domain, instead of the Scientific Police.
• Facial recognition is used for real-time identity validation.
• The record format was unified at the departmental level, for both the Scientific Police and other organizations interacting with the information.
• The generation of the record number and photographic registration number was automated.
• By consuming data from the DNIC, the corresponding personal information is pre-loaded, easing the work of the staff and speeding up processes.
• The participation of departments and processes that were previously not integrated into the system was added, improving the record and traceability of information.
• The new system includes notifications to alert users in specific departments about the availability of necessary information, streamlining tasks and preventing rework.
• An audit module was added that tracks modifications made, showing who made them, when, and detailing the previous and new values entered or modified by the user in the record.
• A reporting module was added, enabling access to metrics and indicators that were previously manually extracted, improving response times and the accuracy of information.

Results achieved

• Complete logging in five minutes.
• Real-time identity validation.
• Notification of identity verification by DIIC so that DECA can proceed with DNA association.
• Reduction in spatula costs by receiving notifications for existing DNA samples, whether taken from adults or minors.
• Reduction in response times for criminal record inquiries by having communications digitized and linked to each offense.

Conclusion

It is a complete turnaround for the National Police, making access to information not only real-time but also more reliable.

SmartAccess is a comprehensive system for managing the entry and exit of various products (pulp, chemicals, and waste) in different modes and through various means of transportation (truck, train, barge). With its implementation, 100% of the process was automated, reducing manual interactions and the time for each vehicle’s entry and exit, resulting in a significant improvement in efficiency.

Technical data sheet

• Client: UPM – Leader in forest bioindustry
• Size/Location: With plants in Paso de los Toros and Fray Bentos—and a new terminal at the Port of Montevideo—UPM’s operations in the country are growing exponentially.
• Main objectives:
  • Automate the processes for the entry and exit of products.
  • Consider the operations at each site and the particularities of each transportation method.

Objectives and challenges

Before implementing the solution, the client:

• The processes for the entry and exit of products to the plants were managed manually.
• The process management times were extensive, affecting the performance of operations.
• The operations of the different transportation methods were not unified, with independent criteria developed based on various factors.
• The necessary infrastructure to implement a multi-site system was lacking.

Client objectives:

• Implement a multi-site system that considers the operational particularities of each location.
• Ensure it is functional for the different transportation methods in use, as well as for the various products being transported.
• Minimize the manual management of processes.
• Optimize the entry and exit times of each vehicle.

The solution

• A multi-site software was developed to address the company’s needs.
• In addition to the software application, infrastructure installation (antennas, readers, totems, etc.) was carried out, which was crucial for the system’s functionality.
• The solution was implemented at all three sites simultaneously, gradually extending its scope to the different modes of transportation to address the particularities of each process.

Results achieved

• Automation of 100% of the entry and exit process for various products.
• Implementation of the system across all transportation methods used.
• Reduction of manual tasks in process management.
• Reduction of entry and exit time for each vehicle.

Conclusion

SmartAccess completely transformed UPM’s logistics management, driving operational efficiency by making the entry and exit of products a more agile, accurate, and automated process.

Technical Data Sheet  

Client: UNILAM – retail.  

UNILAM is comprised of several brands:

• GUAPA: Women’s apparel
• Lucce: Pajamas and underwear
• Grecco: Men’s apparel
• Pappolino: Children’s apparel
• Paprika: Home goods

Size/Location: Multiple branches throughout the country

Main Objectives: Automate merchandise management processes, enabling real-time stock updates, real-time information, generation of metrics and reports, and tracking of shipments and product deliveries.

Objective and ChallengeBefore implementing the solution, the client:

• Carried out manual controls for incoming and outgoing merchandise.
• The merchandise receiving process took hours, as each received item had to be manually marked on a list.
• Suffered delays in carrying out the controls and updating the stock.
• Had an outdated stock of merchandise, with unreliable and non-current information.
• Had limited visibility and traceability of stock movements.
• Encountered problems tracking the merchandise and knowing its status and location in a timely manner.

Client Objectives:

• Generate metrics and reports from the gathered information.
• Obtain reliable, real-time information on all stock movements (receptions, transfers, returns).
• Automate controls, including:
  • Registering stock actually received by each branch
  • Traceability of information
  • Ability to track shipments and deliveries
• Generate metrics and reports from the gathered information.

The solution

• The process transitioned from manual merchandise control to automated control through the scanning of item labels, significantly reducing the time required for this task.
• Once the control is confirmed, the stock of the merchandise actually received is updated in SAP, allowing knowledge of the real stock received and a faster stock update process.
• Manual transfers and returns are replaced by system-based processes. This generates records of these movements, enabling tracking of their status and automatically updating the corresponding stock increases and decreases at the various locations the merchandise passes through until reaching its final destination.
• All information is traceable, generating records of which user performs each movement, the date and time, the source branch, and the destination branch. In cases where the movement passes through different branches, all information is recorded each time it enters and exits a branch.

Outcomes Achieved

• The automation of the merchandise management process resulted in substantial time savings. For new merchandise reception, the process was reduced from hours or even days to minutes. Time spent correcting entered stock is also saved, as is the time required to generate reports, thanks to the reporting module included in the system.
• Additionally, the system helped identify areas for improvement in the shipment and reception process that had previously gone unnoticed.