Human in the loop is a critical part of building AI Applications. As agents become more autonomous, and do more things for us -- we need to adapt how we interact with agents. In this talk Abhishek will talk about how to build a human in the loop system which can accommodate authentication, authorization and rich consent, built using Open Standards. In the end you'll be able to build agents, the can request approval from users in a user friendly way, and conforms to the strongest requirements of assurance levels, ensuring that your users are secure.