Juan Vieira·Dec 16, 2025Como reduzi alucinações de LLMs usando Injeção de Contexto e Redis (sem fine-tuning)Ás vezes, a solução para uma IA mais inteligente não é um modelo maior, mas uma arquitetura melhor.
Juan Vieira·Oct 31, 2025Separation of ConcernsIf you follow the world of AI/ML, you’ve probably noticed that the buzzword is “agent.” The idea is that, with complex function calls and…
InGoogle Cloud - CommunitybyJuan Vieira·May 8, 2025Automating ML Models Deployment with GitHub Actions + Cloud RunA few weeks ago, I decided to do an experiment: instead of focusing only on building machine learning models with good performance, I…
InGoogle Cloud - CommunitybyJuan Vieira·Apr 30, 2025Pub/Sub Messaging in Machine Learning Systems: more than communication, it’s architecture — Part 1
Juan Vieira·Apr 28, 2025My Home Server: building my own server with an old laptopIn December 2024, I started studying different ways of deploying, monitoring and infrastructure. I admit: all paths eventually lead to the…
Juan Vieira·Apr 25, 2025Supervised or Unsupervised for Anomaly Detection?My last project, I faced a question that most data scientists will eventually need to answer throughout: Should I go with a supervised or…
InGoogle Cloud - CommunitybyJuan Vieira·Apr 12, 2025Evaluate and Deploy an LLM Agent with ADK on Google CloudIn my previous post, I showed how I built a development agent using Gemini and the Agent Development Kit (ADK), a powerful tool that makes…
InGoogle Cloud - CommunitybyJuan Vieira·Apr 12, 2025From Zero to Agent: Getting Started with the Google Agent Development Kit (ADK)Google has released yet another new tool. With the launch of the Agent Development Kit (ADK), developers now have a new way to create…A response icon3A response icon3
Juan Vieira·Apr 9, 2025Qualidade de dados no TensorFlow com tf.data: o que todo modelo precisaEm projetos de Machine Learning, na maioria das vezes o foco está na arquitetura do modelo ou na escolha dos hiperparâmetros. Mas a verdade…