Session Abstract

AI agents are only as trustworthy as the guardrails you build into them. In this hands-on session, we walk through the design and implementation of a custom Cowork skill that separates reading from acting, surfacing findings for human review before touching a single calendar, mailbox, or document. Using a real-world award-winning example from Blis Digital's proposal-to-project handoff, you will learn how to structure a skill in two distinct phases, write instructions that prevent the model from inventing data it cannot find, and handle edge cases like unknown external contacts gracefully. We will look at where the behavior lives and why a well-placed "are you sure?" does more for adoption than any clever automation. You will leave with a set of mental models for skill design, concrete instruction patterns you can apply immediately, and the confidence to pick that one recurring task you have been putting off automating.

Albert-Jan Schot

As a senior cloud architect Albert-Jan Schot enjoys stepping up to the challenge of designing, developing and building innovative cloud solutions. He is a valuable source of knowledge for his colleagues, customers and the worldwide Microsoft-community. With his no-nonsense and can-do mentality he brings a unique combination of in-depth hands-on experience and consultancy skills on all levels to any team. As a CTO within Blis Digital Albert-Jan is responsible for the technical vision and strategy within the low-code practice.