Aug 20, 2026 · 1 hr 38 min · 14 segments
In this episode of the *Smarter by Design* podcast, I’m joined by Nicole Chavas, President and COO of Greenprint Partners, and Hillary Thompson, Principal at MBH Architects, for a candid conversation…
Nicole ChavasGuestChristopher ParsonsHost
Hillary ThompsonGuestYou know, firms getting started with AI in general, but like maybe s- more specifically agents, like their eyes get super big and they're like, "Oh my gosh, I could do everything.
I can change all the ways that we're working." But then they kind of like hit a little bit of a, a downsl- like, "Oh, but we..." Like, "Where do I begin?" Or, "Do I have the knowledge I need in order to be able to build these agents?" And I'm, and I'm curious, as you've been, you know, doing your initial work with-- You're both in the private beta for the Synthesis Knowledge Agents.
Like how did you start figuring out what problems that you were gonna go after and what, or, or opportunities you were gonna go after in terms of building, building agents?

I think the most, the most obvious answer is probably frequency times pain, right? If you're looking at a problem.

Like something that happens 50 times a month and wastes 10 minutes every time is gonna beat something that's m- miles and happens twice a year.

But for me, there's also a different layer worth considering to ar- to like really understand what the possibilities were and how they fit into our workflows.

For me, it was really impor- important to start with something that I knew super well.

I've personally touched thousands of proposals in my time at the firm, so it was one of those things where I knew the pain points, I knew the data, I knew where the information lived, and I had a team that I knew would really adopt it and-

... iterate on it and, you know, come up with new ideas about how it could be better.

I knew I could socialize it, and also important, I knew I could analyze the results myself, which really helped.
Versus like trying to streamline somebody else's work that you don't, that you don't know as well.

And, and really quickly it became like a matter of is it faster and better for me to do this, or is it faster and better for me to build an agent to maybe do this and have it be like a repeatable piece of ins- infrastructure for us?
What was the first one you built where you're like, "Oh, I see how this is gonna change the way I'm working"?

I think, you know, three or four years ago when we, when we all started using the chatbots.
You know, firms getting started with AI in general, but like maybe s- more specifically agents, like their eyes get super big and they're like, "Oh my gosh, I could do everything.
I can change all the ways that we're working." But then they kind of like hit a little bit of a, a downsl- like, "Oh, but we..." Like, "Where do I begin?" Or, "Do I have the knowledge I need in order to be able to build these agents?" And I'm, and I'm curious, as you've been, you know, doing your initial work with-- You're both in the private beta for the Synthesis Knowledge Agents.
Like how did you start figuring out what problems that you were gonna go after and what, or, or opportunities you were gonna go after in terms of building, building agents?

I think the most, the most obvious answer is probably frequency times pain, right? If you're looking at a problem.

Like something that happens 50 times a month and wastes 10 minutes every time is gonna beat something that's m- miles and happens twice a year.

But for me, there's also a different layer worth considering to ar- to like really understand what the possibilities were and how they fit into our workflows.

For me, it was really impor- important to start with something that I knew super well.

I've personally touched thousands of proposals in my time at the firm, so it was one of those things where I knew the pain points, I knew the data, I knew where the information lived, and I had a team that I knew would really adopt it and-

... iterate on it and, you know, come up with new ideas about how it could be better.

I knew I could socialize it, and also important, I knew I could analyze the results myself, which really helped.
Versus like trying to streamline somebody else's work that you don't, that you don't know as well.

And, and really quickly it became like a matter of is it faster and better for me to do this, or is it faster and better for me to build an agent to maybe do this and have it be like a repeatable piece of ins- infrastructure for us?
What was the first one you built where you're like, "Oh, I see how this is gonna change the way I'm working"?

I think, you know, three or four years ago when we, when we all started using the chatbots.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.