Vasco Furtado

Delivering judicial decisions demands interpreting complex texts, analyzing evidence, and reasoning through jurisprudence and law. Recent advances in generative artificial intelligence, particularly large language models (LLM), have shown potential to automate parts of this process, but practical benefits in real‐world courts remain limited. This paper introduces SARA, an LLM‐powered platform deployed in a Brazilian court, which demonstrates significant efficiency and quality gains through the integration of LLM agents with knowledge models on jurisprudential and basic legal concepts. SARA extracts key elements from documents, including claims, requests, and evidence, and generates reasoning grounded in retrieved precedents. The Jur‐KG, modeled through an ontology of concepts such as LegalRelation , LegalGrounds , and LegalClaims , enables semantic matching and retrieval of relevant case law. By representing cases according to the Legal Case Ontology for the Brazilian Judicial System, SARA supports traceable reasoning and addresses competence questions to assess coverage, coherence, and justification of AI‐generated outputs. Deployment results show measurable improvements in processing time, consistency, and explainability while ensuring compliance with Brazil's National Council of Justice guidelines. Combining LLM‐based agents with domain‐specific knowledge graphs yields innovative capabilities and proven impact in judicial decision‐making.

This article presents the design, implementation, and evaluation of MarIA, a GPT-3.5-powered virtual assistant integrated into a messaging platform to support patients with type 2 diabetes mellitus (DM). MarIA employs a multi-agent architecture that enables varying dialogue styles and degrees of personalization. In a 3-month longitudinal study involving 35 participants, personalized interactions increased engagement by 26%, while message length more than quadrupled—yielding a richer understanding of patient context. This deeper contextualization enabled MarIA to initiate more relevant, meaningful conversations, fostering a positive cycle of sustained engagement. Safety was critically assessed. While MarIA did not generate factual hallucinations, some general health suggestions—though accurate in isolation—could be inappropriate for users with specific clinical constraints. This underscores the need not only for comprehensive patient profiling but also for an embedded safety layer capable of detecting potentially unsuitable recommendations before or even after delivery. The multi-agent architecture proved essential in enabling proactive behaviors, nuanced context detection, and dialogue adaptability, ultimately enhancing both engagement and user safety in AI-supported chronic care.

This work presents the design, implementation, and evaluation of an intelligent agent developed to support the State Health Attorney’s Office of Ceará (PROSAÚDE) in managing over 3,000 monthly legal cases related to public health. The agent automates key decisions on legal contestation by interpreting court documents and applying internal legal norms. Built under the Judiciary vertical of Ceará’s Chief Scientist Program, the system combines large language models (GPT-4o), regulatory rule sets, and robotic process automation to extract medical/legal data, retrieve external sources (e.g., ANVISA), and generate official dispatches. It ensures consistent application of PROSAÚDE’s Internal Ordinance, which defines when appeals are required. Results show 98.4% precision in rule application and 93.8% recall in medication detection. In human-in-the-loop validation, 98.7% of dispatches required no revision. The solution highlights the potential of AI-driven legal automation to improve efficiency and accuracy in high-volume public workflows.