He describes it like this.

You know, when teams go from like, oh, here's a big pile of data, like aka our warehouse, and here's an agent, and we're just going to throw it on top and expect it to like,

it's like nothing.

The answer every possible like use case under the sun.

Right.

So, you know, I think selfishly I have a unique viewpoint just because of where I'm at at Kumo.

You know, like I talked about our whole like thesis, essentially the structured relational data warehouse is oftentimes the highest signal context in the business.

You know, so we're built to connect to that, turn relational context into, you know, real life, like kind of business outcomes and push those into operational workflows with explainability.

I mean,

I think what we were seeing looked polished enough to be operational.

At first glance, you know, the scores look precise.

The summary sounded coherent.

The recommendations felt data backed.

But the moment you ask like the simple follow-up questions, like, and that's why explainability is so important.

Like, okay, well, why did you choose this account? Or why is that happening now? Or what data drove this decision? You know, the logic started to thin out.

But Jason Dobbs, he describes what the layer of our context bundle has to include before any agent gets real authority over a workflow.