Gestern • 31 Min.

In this episode, Michael Dowden sits down with Debbie O'Brien to discuss how AI agents and automation apply to both daily personal tasks and software development, from shopping and scheduling to automated testing, bug hunting, and development workflows. They explore what it takes to make this kind of automation work: breaking down complex problems into smaller tasks, providing agents with the right context, verifying their output, managing cost, and gradually building trust. Rather than replacing developers, agents shift their role toward coordination, delegation, and review. The key challenge is no longer simply knowing how to use AI, but learning how to structure work so that multiple agents can reliably contribute to it. The conversation also considers the boundaries of delegation, from financial and security risks to unreliable information and poorly integrated services. The central message is: start small, experiment with low-risk tasks, learn what agents can and can't do, and increase their autonomy as they earn your trust.