Searching...
12 results for “product testing”
...and testing the application as if it were a user. Right. So the system can't actually tell, whether it's a user or if it's our AI. Right? So a platform is separate. The other kind of strategic importance, I feel, is separation of concerns. As you kno
53:14 / 54:21
from transcript53:14 – 54:21
...product is doing. You ask it a question. It gets back with something. One way to test if it's giving you the right answer is if it's consistently doing the same thing that you could write a code to to tell you this is true or false. For example, will
49:30 / 50:35
from transcript49:30 – 50:35
...production monitoring? What does it matter? So I feel, again, we go back to this problem first approach of what is your what is it that you're trying to build? Like, you're trying to build a reliable application for their customers that's not going t
35:15 / 36:25
from transcript35:15 – 36:25
...but unit testing. So every step of the way, you have an explicit plan, and every step of the way you want to, as well as as best you can, validate
4:32 / 5:34
from transcript4:32 – 5:34
...production. You And it's like a daily, hourly sort of thing you could be running. Totally.
50:57 / 52:10
from transcript50:57 – 52:10
and and then you correct it from there. Yeah. And one thing we talk about, which very aligned is what you're thinking is, like, they're kinda like two problems as these things get better. One is, like, how do you specify what you want? And the other
38:58 / 40:10
from transcript38:58 – 40:10
After zero to one, next, we will build their identity on our platform. They already have friend on our platform. So next, they want identity. So that's why our AI can help us Because we only had two people now, all engineer. So now we are using, AI t
47:50 / 49:05
from transcript47:50 – 49:05
...testing top to bottom. Right? So this generating of a site readiness report is one workflow we have. Right? So agents run workflows. So I would like to show you what it looks like to run and train agents running workflows. This is how I deal with the
50:53 / 52:01
from transcript50:53 – 52:01
...a product engineer, but we also have designers, we have ML engineers, we have researchers, a ton of infra people, and together we, one, think that leads to better ideas, but we also think it truly helps making these features great and keeping them up
17:57 / 19:10
from transcript17:57 – 19:10
laser focus, like, on everything we do, on having the best independent metrics and making sure that no one can manipulate them in any way. There are quite a lot of processes we've developed over the last couple of years to make that true for, like, t
13:25 / 14:36
from transcript13:25 – 14:36
...is testing in software solved problem. We sort of know how to do it. We can come up with a list of edge cases. We can run through tests. We can even automate our tests. But with AI, it's not a deterministic software. It's really hard to know, is this
30:46 / 31:57
from transcript30:46 – 31:57
...Our first product is AirTest. It's using agents to test websites. Right? So you provide a URL. And then with this URL, about fifteen minutes later, you get a link. And this link is in or you get an email. And this email is a deep, deep dive into your
49:30 / 50:30
from transcript49:30 – 50:30
Have a podcast?
Run your podcast through Clypt
Get ranked clips, hooks, and ready-to-post copy from your own episodes. Free to try.