WideLabs Justice Intelligence platform makes legal services more accessible for 8 million citizens in Rio Grande do Sul, Brazil
Public Ministry of Rio Grande do Sul (MPRS) · Brazil
WideLabs built the Justice Intelligence platform for the Public Ministry of Rio Grande do Sul (MPRS) in Brazil, consisting of two AI agents — the TORI Investigation Assistant and the Archiving Intelligence Assistant — plus a Citizen Access Agent for the public. The platform uses NVIDIA NeMo Retriever for RAG pipelines, NVIDIA NIM microservices for deployment, NVIDIA NeMo Curator for document preprocessing, NVIDIA NeMo Customizer for domain-specific model tuning, and NVIDIA NeMo Guardrails for safety and consistency. The system went into full production in January 2025, serving more than 8 million citizens across 497 municipalities, and per MPRS deputy attorney general João Cláudio Pizzato Sidou, procedures that could last months or years can now be resolved or advanced in less than a day.
Overview
WideLabs built the Justice Intelligence platform for the Public Ministry of Rio Grande do Sul (MPRS) in Brazil, consisting of two AI agents — the TORI Investigation Assistant and the Archiving Intelligence Assistant — plus a Citizen Access Agent for the public. The platform uses NVIDIA NeMo Retriever for RAG pipelines, NVIDIA NIM microservices for deployment, NVIDIA NeMo Curator for document preprocessing, NVIDIA NeMo Customizer for domain-specific model tuning, and NVIDIA NeMo Guardrails for safety and consistency. The system went into full production in January 2025, serving more than 8 million citizens across 497 municipalities, and per MPRS deputy attorney general João Cláudio Pizzato Sidou, procedures that could last months or years can now be resolved or advanced in less than a day.
The challenge
Brazil has a massive backlog of legal cases, with over 82 million pending in the courts as of late 2023. In Rio Grande do Sul alone, about 60,000 police inquiries are archived each year, and the MPRS processes around 39,000 public service requests annually, a number that continues to rise — overwhelming volume that slows down the justice system and delays outcomes for millions of people.
The solution
WideLabs built the Justice Intelligence platform for MPRS, consisting of the TORI Investigation Assistant (natural language query over the TORI database using NVIDIA NeMo Retriever RAG pipelines deployed as NVIDIA NIM microservices, with NVIDIA NeMo Guardrails ensuring consistent behavior), the Archiving Intelligence Assistant (analyzes judicial process archiving promotions and generates accessible explanations), and a Citizen Access Agent with secure authentication, intelligent case routing, document management, and appointment scheduling. Document preprocessing used NVIDIA NeMo Curator, and models were customized to the MPRS legal domain using NVIDIA NeMo Customizer and NVIDIA NeMo Aligner.
Reported business value
The Justice Intelligence platform was tested with a small sample of prosecutors and went into full production in January 2025, serving more than 8 million citizens across 497 municipalities. Per deputy attorney general João Cláudio Pizzato Sidou, the system can find inconsistencies in huge databases within minutes, and procedures and investigations that could last months or years can now be resolved or advanced in less than a day.
Sources
Open any source and check the claim yourself — that is the point of the register.
Other government & public sector entries in the register.
Estonia rolls out Bürokratt, an AI-guided virtual assistant network for public services
Bürokratt is a network of chatbots deployed on Estonian public sector institutions' websites, letting people obtain information from institutions and use public and information services via virtual assistants. It is a state-created, AI-based digital assistant that helps institutions deliver modern, efficient, around-the-clock customer service using large language models.
Austrian Academy of Sciences unlocks Ancient Greek with Mistral
The Austrian Academy of Sciences (OeAW), together with its Austrian Archaeological Institute, partnered with Mistral and services partner Reply to build Apollo, described as the first advanced large language model for Ancient Greek. Apollo is trained on a specialized corpus of 600 million words of historical Greek text plus tens of thousands of published inscriptions and papyri, helping researchers reconstruct damaged texts and identify thematic connections across collections. The OeAW reports Apollo turns work that once took years into hours, addressing over one million unread Greek papyri worldwide, with future phases planned for semantic search and handwritten inscription decipherment.
MITRE's Federal AI Sandbox accelerates government AI research with NVIDIA DGX SuperPOD
Nonprofit MITRE built the Federal AI Sandbox, powered by NVIDIA DGX SuperPOD, to give federal sponsors an affordable, centralized space to test and deploy AI and machine learning across domains such as weather forecasting, cybersecurity, and public benefits administration. The DGX SuperPOD delivers a 300-fold performance increase over MITRE's previous AI computing capabilities and supports thousands of researchers; MITRE is using it with NVIDIA Omniverse and NVIDIA Earth-2 to develop 1-kilometer precision weather forecasts with NOAA and the National Weather Service, plus a foundational model for cybersecurity threat analysis across 190 nations.
Israel's Meteorological Service Predicts the Weather Using NVIDIA Earth-2
The Israel Meteorological Service integrated an AI weather model called F3, powered by NVIDIA Earth-2 and NVIDIA PhysicsNeMo (including the CorrDiff neural network), into its forecasting system to achieve hyperlocal 2.5-kilometer resolution precipitation forecasts. F3 achieved 90 percent lower computational costs compared to running a classic non-AI numerical weather prediction model on a CPU cluster, delivering forecasts in minutes rather than hours, and saved 20-30 percent of the Tel Aviv-Yafo Municipality's preparedness budget for things like urban flood safety. CorrDiff was trained to emulate IMS's regional high-resolution ICON model using low-resolution ECMWF IFS input, enabling four high-resolution forecasts per day. Partners including the Israeli Police, the National Fire and Rescue Authority, the Ministry of Transportation and the National Road Company have adopted the forecasts, and IMS used F3 to issue a high-resolution flood map during a January storm that dropped 150 millimeters of rain in six hours.
Was this helpful?
Your feedback helps us improve our use case database