Carl Yeh

I've seen like Innate, Vista,

In accounting, you obviously have Sage ERP.

Some companies use QuickBooks Online.

And then there's companies that have made their own software and run it forever, right?

Like their internal ones.

And that's a big thing.

It's like, we thought MCP could solve it, but MCP only hits like big time connectors to the major SaaS tools that kind of like Asana,

like things that aren't industry specific.

And so it's very hard to, unless you know what you're doing, build an MCP on top of this software.

But if the, if the company has like four or five different ERP or one ERP, one unique software, one bidding soft, whatever that is,

is it worth your time building three or four or five MCPs?

The thing that we're starting to look at, and I think this is where companies like Snowflake, Databricks, and even Google BigQuery make a difference, is like, hey, ditch trying to connect them.

One thing you could do is just build a data lake.

You can make it super simple, use Google BigQuery, and have it pull the data from...

all these different places.

And as long as they have an API, you can do that.

And then, then you put your MCP on top of that data lake.

And that's the key.

Cause I think like one of our clients, we've already done that where they have so many different tools.

You put a data lake in there and they can use their chat GPT to be like, Hey, what did this in, in Sage, we do this, this, we could do this.