This demo showcases a hybrid method that leverages a Deep Learning classifier and heuristic rules to identify requests that place an obligation on a recipient, usually within the context of textual conversations. If a sentence is identified as task, the Task Annotator generates a list of possible actions predicted as necessary to address a request (for example writing back an email, making a call or opening your calendar), as well as a priority label of the task, inferred from dates or urgency patterns.