In recent years, augmented intelligence systems have advanced to provide humans with insights for knowledge discovery and decision making. Using a cooperative approach, these systems use powerful artificial intelligence (AI) to augment human cognitive activities. To do so, the AI capabilities have to complement human actions and therefore be explainable and controllable, while still providing implicit insights based on statistical models. Semantic Artificial Intelligence (Semantic AI), as the combination of machine learning and knowledge models, provides such a methodology. In this industry presentation, we demonstrate a Semantic AI system for augmented intelligence as an integration of two powerful AI platforms. Squirro, the Insight Engine for Cognitive Search and PoolParty, the most complete Semantic Middleware, combine on a methodological level to fuse knowledge graphs and machine learning capabilities into a unified functionality. We then demonstrate how this approach can be applied to solve a smart assistant use case where we provide recommendations for emails. These recommendations are created using a combination of natural language processing (NLP), text classification, and a knowledge graph. This results in high-precision contextual information about email content, directly in the inbox. With this integration we bring a novel approach to augmented intelligence for an effective cooperation of humans and AI.||