Okay. So far, we have manually selected repos and sessions, but we don't have to, all right? Instead of selecting repos by hand, I can also tell the agent what I want. Remember that graph has all this intelligence, right, about how repos relate. I could tell my agent, "Find every repo that depends on a particular version of a library and update it." Right? >> [snorts] >> I mean, it knows, right? I I didn't have to select them. It knows a lot of metadata about what's going on. I can also ask loose questions. Things like, you know, uh "What if I I want to write a blog post, right, or an article?" I could describe it and it will figure out which repo is the most relevant based on relationships between repos and what's in them. Another example. Let's say I want to add vector index into the PR collection. And I want to know if anyone at any point did something relevant in any repo that I can draw from. So, in this case, if I do it, I'll see that it will find several sessions that appear to be relevant. >> [snorts] >> And I can load one of them or both of them, right? Um it's useful for many reasons. Uh let's just one small example. It helps with best practices and consistency. Instead of doing stuff from scratch, where, you know, every single implementation is bespoke, I can make it replicate the approach used in the session by an engineer I respect. Now, our code cross repos is consistent. That's a big deal.