May 15, 2026 · 10 min · 7 segments
If you’re listening to this episode while nervously glancing at your laptop wondering if ChatGPT is about to write your performance review, well… you’re in good company. Today we’re diving headfirst…
The other thing, Brian, is that what you're describing requires an AI to be able to handle Brownfield, right? You're doing multiple versions, feature by feature.
Yeah, this is a, you know, when people say, well, it can only do Greenfield or it can only do prototypes.
Well, no, I use it to maintain an existing relatively large code base for my day work.
Now, here's the skill when you're using agents like Cloud Code who are looking at your code base is to narrow the scope of what you're...
I mean, it becomes even more important to make sure it's a small problem because you can spend money really fast if you don't.
If I narrow the scope to a small problem, I can spend a few cents and get some really good work done.
But yesterday I was working on something where I wasn't exactly sure how to do it, and I gave it too big of a scope to look at, and I spent $15 in a heartbeat.
So you need to understand how to break things down small and leverage tools correctly, or you're going to spend a lot of money and not get good results.
That's cool because you're kind of like in that boat that all product owners end up in is like, oh, I have a team.
How come you're charged by the token? Aren't you taking one of those monthly charges for
The other thing, Brian, is that what you're describing requires an AI to be able to handle Brownfield, right? You're doing multiple versions, feature by feature.
Yeah, this is a, you know, when people say, well, it can only do Greenfield or it can only do prototypes.
Well, no, I use it to maintain an existing relatively large code base for my day work.
Now, here's the skill when you're using agents like Cloud Code who are looking at your code base is to narrow the scope of what you're...
I mean, it becomes even more important to make sure it's a small problem because you can spend money really fast if you don't.
If I narrow the scope to a small problem, I can spend a few cents and get some really good work done.
But yesterday I was working on something where I wasn't exactly sure how to do it, and I gave it too big of a scope to look at, and I spent $15 in a heartbeat.
So you need to understand how to break things down small and leverage tools correctly, or you're going to spend a lot of money and not get good results.
That's cool because you're kind of like in that boat that all product owners end up in is like, oh, I have a team.
How come you're charged by the token? Aren't you taking one of those monthly charges for
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.
