So let's talk then about the start of the process, right? Because you mentioned a little bit, hey, we go and we, you know, ingest a lot of what's going on so that you know, oh, what is that one library off in the weeds that should be used for this? So what does that look like at Blitzy?

Yeah, so if you look at how far models have come, right, models are really intelligent these days.

But where do they fall down? They fall down at the context level.

They have 1 million tokens of context, which maps to about 100,000 lines of code.

But here's the kicker, right? Every token in the context window needs to map to every other token by a dot product in the matrix.

And there's no amount of compute or trick that you can apply that does this effectively across the entire context window.

So most of the model providers that you have there, Anthropic, OpenAI, they have the effective context up to less than 300,000 tokens, right? And they're applying techniques like sparse attention, sliding window attention, or something else across the rest of the window.

What's like the frontier? What are the things coming down the pipe?

The alternative is just, it just doesn't get done.

I think software in general is unique and special.

It's one of the reasons why we're seeing AI making its first and early marks in software is that it is... completely verifiable in most cases, right? So you can add verifiability from a standpoint of security, from the standpoint of coding standards.

You can define rules at an org level that you can objectively verify and test software against.

But the key aspect here is that unlike some other process, like I've worked in big tech for several years, the processes we followed for writing code and getting it into production are... completely different from something like financial services company like State Street would do.

between getting the code out and getting to production.

I think what we've seen is that the agents and the tools are great at writing code, but it takes a lot more than that to get code into production.

Appreciate