Vibe Check: Three Real Agent Setups and How They Collaborate

​This episode of Vibe Check looks at what people are actually running with autonomous agents. Melanie is joined by Abhay Kashyap, Mark Weiss, and Kai Siren, who have spent months building and experimenting with persistent agents. They are exploring how people interact with agents, how agents interact with one another, and what it takes to make these systems reliable and secure. Their setups range from named agents with long-term memories to a collaborative human-agent workspace and a system of eight persistent personas. 

Live, we bring their agents together in a shared Discord for the first time. What can agents from different systems create together? What do they say about their humans when they think nobody is reading? How should permissions work when someone borrows an agent? Can inter-agent drama emerge? We’ll unpack how each setup fails, where the approaches converge and diverge, and where agents are creating real value today. Watch live and bring questions!