Guaranteed quality and structure in LLM outputs - with Shreya Rajpal of Guardrails AI artwork

Guaranteed quality and structure in LLM outputs - with Shreya Rajpal of Guardrails AI

Latent Space: The AI Engineer Podcast

May 16, 2023

Tomorrow, 5/16, we’re hosting Latent Space Liftoff Day in San Francisco. We have some amazing demos from founders at 5:30pm, and we’ll have an open co-working starting at 2pm. Spaces are limited, so please RSVP here!
Speakers: Alessio Fanelli, Swyx, Shreya Rajpal
**Alessio Fanelli** (0:10)
Hey, everyone, welcome to the Latent Space Podcast. This is Alessio, Partner and CTO in Residence at Decibel Partners. I'm joined by my co-host, Swyx, writer and editor of Latent Space.

**Swyx** (0:19)
And today we have Shreya Rajpal in the studio. Welcome, Shreya.

**Shreya Rajpal** (0:23)
Hi, hi, excited to be here.

**Swyx** (0:25)
Excited to have you too. This has been a long time coming. You and I have chatted a little bit and excited to learn more about Guardrails. So we do a little self intro. We do a little intro for you, and then we have you fill in the blanks. So you got your bachelor's in IIT Delhi, minor in computer science with focus on AI, which is super relevant now. I bet you didn't think about that in undergrad.

**Shreya Rajpal** (0:43)
Yeah, I think it's interesting because I started working in AI back in 2014 And back then I was like, oh, it's here. This is almost changing the world already. So it feels like that meme of almost arriving.
So yeah, it's felt this way where it's almost here. It's almost changed the world for as long as I've been working in it.

**Swyx** (1:03)
That's awesome. We can explore the origins of your interests because then you went on to UIUC to do your master's also in AI. And then it looks like you went to drive.ai to work on perception. And then to Apple SPG, as the cool kids call it, special projects group working with Ian Goodfellow.
And then you were at Pretty Base up until recently. Actually, I don't know if you've quit yet.

**Shreya Rajpal** (1:24)
I have, yeah.

**Swyx** (1:25)
You haven't updated your LinkedIn, but we're getting the vibe breaking news that you're working on Guardrails full time.

**Shreya Rajpal** (1:29)
Yeah.

**Swyx** (1:30)
Well, that's the professional history. We can double back to fill in the blanks on anything.
But what's a personal side, what's not on your LinkedIn that people should know about you?

**Shreya Rajpal** (1:38)
I think the most obvious thing, this is like, this is still professional, but the most obvious thing that isn't on my LinkedIn yet is Guardrails. So like you mentioned, I haven't updated my LinkedIn yet, but I quit some time ago and I've been devoting all of my energy full time working on Guardrails and growing the open source package and building out exciting features, et cetera. So that's probably the thing that's missing the most.
I think another more personal skill, which I think I'm like kind of okay for an amateur ad that isn't on my LinkedIn yet, is pottery. So I really enjoy pottery and I don't know how to slot that in amongst like all of the AI. So that's not in there.

**Swyx** (2:10)
Well, you like shaping things into containers where unstructured things can kind of flow in. Yeah, I love that.

**Shreya Rajpal** (2:19)
I should use that.

**Alessio Fanelli** (2:22)
Maybe for the audience, you want to give a little bit of intro on Guardrails AI, what it is, why you wanted to start it.

**Shreya Rajpal** (2:28)
Yeah, for sure.
So, the need for Guardrails really came up as I was kind of like building some of my own projects in the space and like really solving some of my own problems. So, this was back of like end of last year, I was kind of building some applications, like everybody else was very excited about the space. And I built some stuff and I quickly realized that yeah, I could, you know, it works like pretty well a bunch of times, but like a lot of other times, it really does not work as I, the developer of this tool, like want my tool to work.
And then as a developer, like I can tell that there's very few tools available for me to like get this to, you know, cooperate with me, like get it to follow directions, et cetera. And the only tool I really have is this prompt. And there's only so far you can go with like putting instructions in like caps, adding a bunch of exclamations and being like, follow my instructions, like give me this output this way, right? And so I think like part of it was, you know, that it's not reliable, et cetera, but also as a user, it just, if I'm building an application for a user, I just want the user to have a certain experience using it. And there's just not enough control to me, not enough like knobs for me to tune, you know, as a developer to do that. So Guardrails kind of like came up as a way to just like manage this better.

67 more minutes of transcript below

Feed this to your agent

Try it now — copy, paste, done:

curl -H "x-api-key: pt_demo" \
  https://spoken.md/transcripts/1000651996090

Works with Claude, ChatGPT, Cursor, and any agent that makes HTTP calls.

From $0.10 per transcript. No subscription. Credits never expire.

Using your own key:

curl -H "x-api-key: YOUR_KEY" \
  https://spoken.md/transcripts/1000613154442