In my last post I introduced my side project, BEAR - a tool that tries to show how agentic development may be done in a safer way, by creating boundaries for agents as they develop, and allowing humans to be alerted when agents try to expand these boundaries.
But I want to focus on something else in my project. I want to focus on the “my”.
Because while “I” was “developing”, I kept asking myself - is it “my” project?
This new world of agent-assisted development creates some discomfort for those of us who still remember the time when we wrote code by hand. But it’s more than writing code. The whole process - brainstorming, designing, defining tasks, managing the roadmap, all of it was done using my team of agents.
Now, it’s not that this process is new to me. I have been working for years as a software architect, so my day-to-day has for a long time been about talking to people and not writing code. This is what I do. I talk to people to brainstorm, design, manage the roadmap, plan, and review implementation.
So you can say - people, agents, what’s the difference?
But somehow, there is a difference.
With a team of humans, there is shared ownership of the product. It’s not “mine”, it’s “ours”. But what is this ownership when your coworkers are a team of agents? When there isn’t really a “they” in the sense that we are used to thinking about what “they” is?
This is beyond the simple question of ownership, of how much you actually understand the code, how much you know what’s really going on under the hood. That’s an important and practical question that teams will have to tackle as agents start to write more and more code.
I’m talking about a more existential question. About that boundary of what is human, what is creativity, and how they correlate when creation is done with so much automation by a non-human.
Those boundaries are getting blurred, and it feels like we need to calibrate ourselves again, redefine how we perceive what we do, what we own, and what it means when, in that human-nonhuman collaboration, the non-human part is getting bigger.
I started with a project that tried to understand and create boundaries for agent development, but it ended up questioning my own boundaries, and the boundary between me and the machine.