Max Junestrand

So after we got accepted into Y Combinator, we deleted all of that code.

I think we made some good product decisions by very early adopting, basically, Langchain was too bad at the time.

So we built our own agent architecture and we did that very early, which I'm very proud of.

And that was like the right direction to continue on.

No, it's been completely rebuilt many times.

I last committed code in October 2023.

Yeah, I think we're not the size of Revolut or Deal.

And so it probably doesn't make sense for us to do that.

And Langchain and a lot of their surrounding tools have gotten a lot better.

And so I think we're in the job of and our engineering team is in the job of picking the best third party things.

The other right product decision we made or wrong was that we were doing too many things.

So in 2024, we were 12 engineers and we were trying to build six or seven different things at the same time.

And that was creating a lot of confusion because I was very involved in the product decisions at the time and I was basically just out doing go to market.

And so we'd make a lot of product decisions without me in the loop.

And then it kind of looked like a Frankenstein monster.

There's actually a pretty funny doc from October or November 2024 that was called the Leia Product Manifesto.

Oh, I remember.

Yeah, we were Leia.

In 2025, we were still called Leia.

Yeah, I remember.