Ep. #12, Agent Orchestration at Scale with Maxime Beauchemin

So, like, what changed kind of your mind like working on traditional BI or even though it's just open source and then, like, a very different option for people who want to consume data? But you were working on something, like, with agents, right? What, what's the, the biggest change?

Yeah.

Well, so I'm a builder, you know, so I love...

The, the only moment when I'm truly happy and, you know, feel good about myself is when I'm building something actively.

And with everything that's been happening, you know, in the agentic space, I felt like building something, like identify the gap.

I think at first, you know, my first realization about this time last year, a little bit earlier last year, is when I started using Cloud Code.

I had my own, like, Cloud Code moment, and I was like, "Oh my God, this is changing everything." You know, we need to completely change the way that we work, and I need...

My first sense of urgency was I need to manage a lot of agents.

Like, what, I need to spin one off and then spin another terminal and created my own little kinda framework using Tmux and Vim and whatever tools that, that I use, so I could manage, like, three agents, five agent, ten agents, twenty agents, and then started suffering from a few things at the time.

So first thing was that just, like, the clarity, like, you know, like, context shift of, like, you're managing twelve agents and you have, like, twelve terminal window or Tmux tabs.

You start getting a little bit lost in your flow.

Like, what PR is associated here? If I need to start, uh, an environment, like a Docker environment for this, what port it's gonna be on.

So I'm-- you know, started to hit some of the, the clarity issue that you get when coordinating, orchestrating more than five agents.

So I was like, "Okay, I need a place, like, that's much more visual," and was kinda inspired to do something a little bit more like Figma.

And then I guess the other pain point was, you know...

And I think it's still a pain point in the, the industry of, like, we're all running, like, multiple agents locally, but then we're all kinda stuck in our own little terminals and set up locally.

There's no way to...

I cannot see what you're doing with your agents.

You cannot see what I'm doing with my agents.

We cannot share a dev environment.

So, you know, realizing that we needed something a lot more collaborative.

I've been kinda disappointed.

There's been some progress around that.

I would say, like, Cursor and Cloud Code, like, enables you to add multiple work trees now, but it seems like a bit of an afterthought.

And then Cloud Code Work maybe is a little bit more collaborative, but the collaboration is still, you know, for, for security type reasons.