In this session we will talk about when and how to inject NLU into your bot using LUIS. We are launching a new set of features in (LUIS) that enable a more integrated experience for building end to end bot intelligence with NLU interfaces. LUIS is fully integrated with Speech, Text Analytics, and machine translation from Cognitive Services to enable bots that you can text or talk to, converse with in multiple languages, and even further get sentiment and do key phrase extraction. LUIS is releasing several features to enhance the core language understanding capabilities including patterns, regex entity, and the conversation state as a feature to the intent and entity models for more accurate prediction. The session will focus on the best practices to build an effective LUIS application, integrate it with your bot, and finely tune it over time. We will show each of the new features in the LUIS portal and in the bot code through a demo scenario.