Skip to main content
Brian Clark

Brian Clark

Member of Product Staff at Databricks, leading Lakebase; previously VP of Product at Neon (acquired by Databricks)

Jun 9, 2026

5:28
Is there any downside besides the token spend to letting the AI spinning it up?
5:34
Yeah.
5:34
Yeah.
5:34
I think, like, the AI can spin it up and just like spinning it down, uh, you know, agents, um, are gonna hit the command, like the API call to spin something up, and then wait for the response, uh, and know that then they can start using it, and that's the same thing on the, uh, on the destruction of these things, right? When they, uh, they have to go say, "Hey, destroy this database," and then wait around for the, like, the compute to shut down and then delete the branches afterwards.
5:59
Um, it's all just kind of extra time.
6:01
Uh, and that's the thing, if you're doing a fan-out strategy of 10 different agents-Your goal is not to basically save money at this point.
6:09
You're actually trying to save time.

18 MINS LATER

23:48
Yeah

We value your privacy

We use cookies to understand how you use our platform and to improve your experience. Click “Accept All” to consent, or “Decline non-essential” to opt out of non-essential cookies. Read our Privacy Policy.