This workflow is centered around creating conversational assistants using sample dialogs from user personas. The approach allows for a very user experience centric design, making it easy for team members to work in parallel across different user actions. However, reconciling and grouping flows together can be challenging due to overlaps and duplicates of intents, utterances, and entities. To conquer this challenge, automated import tools, prototyping inside existing tools, and NLU management tools can be used. The workflow also includes creating conversational assistants from existing data, enriching existing designs with real-world user behavior, and visual conversation design. These approaches allow for a data-driven approach to improve the conversational assistant with every release. Additionally, intent-driven designs, NLU-driven designs, and end-to-end driven designs can be used to overcome challenges such as managing relevant data, iterating on flows, and synchronizing data between teams. By using these workflows, teams can create conversational assistants that are user experience centric, efficient, and effective.