How is “one” agent composed — what makes it a single individual — and why do we need different “multiple” agents? What should the interaction between agents and humans look like, and how should we understand an agent’s place in collaboration? What relationships should individuals, teams, and even whole companies of humans have with one agent, a group of agents, or even other people’s agents? Ultimately, how do we design institutions and platforms — including software infrastructure — so that we all operate within a unified framework? I will explore these questions based on my implementation work at Dify.ai.
How to Design the Institution & Platform for Agents
KeynoteAbstract
What makes an agent “one” individual, and why do we need many different agents? How should humans and agents collaborate? Drawing on the implementation at Dify.ai, this talk explores how to design institutions and platforms for agents.