0:01I've never cooked a steak with a fork before.
0:06If Arthur's watching this, I'm sorry for putting you on the spot. Yo, can we address the critics?
0:13Hey guys, welcome to the late space cooking show where we invite founders and researchers and just let them cook. Today we have a very special guest, co-founder and CEO of Reductto, Adit.
0:25Hey, thanks for having me.
0:26Yes, of course. And we actually got connected through Adele after a tweet went viral, right? Where you could I thought a really good looking piece of steak.
0:36I thought it was incredible, but people were ratioing you. Is that correct happened?
0:40Yes. There were some allegations made um that we'll address today.
0:43Okay. Yeah, we'll redeem today and we get started. So today we have steak and we also have chim cherry that we'll make and so yeah, we can get started. Do you want to hand me the parsley and we can start cutting it?
0:54Yeah. Um, and before we start as well, I was kind of curious. You initially joined YC with this company called Remember All. That correct?
1:02And even today, your company's called Reduct. And so I was wondering, are there any ties with Harry Potter? Are you We get that a lot.
1:10Um, yeah. So the story here is uh we knew we were going to pivot from remember all. The day we got into YC, we told Diana like, "Hey, we don't think this is what we're going to pursue." Um, and we we didn't know what we would pivot into specifically. Um, there was this like general idea of we'll make magical tools for developers and we made like a a poll in a group chat saying here are the names and the domain names available for each
1:39and this one the name got some horrible names in there. But yeah, but I guess you know a lot has changed uh going from at that time it was long horizon memory or just memory for memory for agents agents and then today you're working on document parsing or processing.
1:57Um and I guess to contextualize for the audience do you want to u provide some more like breakdown of the core crux of the problem and even maybe some history going from OCR to IDP and now today with VLNs and agents.
2:10Yeah. So, I mean there's um a few decades worth of companies that have worked on PDF processing.
2:17Like I I met this guy that had worked on PDF processing longer than I've been alive. Like quite literally he worked on the original drivers for printers to print PDFs.
2:27Um the context in which people process documents is obviously very different though in that like these are just horizontal formats that a lot of people will use for you know cataloging information. and it's a a unified set of data that people will use across enterprises. And so if you're going to have models do a lot of human work, it becomes really important that you have human level of fidelity when you're reading it.
2:51And the tricky thing is I I hinted at this with the guy that's um worked on printer drivers. Like the original context for PDF as a file format was for printers to be faithful to the original, right?
3:03And so it wasn't really designed around this sort of problem of agents are going to read it. And so we just got really really deep in this rabbit hole of how can you read these documents the way that a human would.
3:13Um which is a really hard vision problem.
3:16We liken it a lot to self-driving car research.
3:20Uh and that there's been, you know, lane assist in cars for a long time and it's a very different thing to say that your Whimo will drive fully end to end autonomously.
3:30That's the sort of bar that we want to get to with Reductto.
3:32Gotcha. Okay, that makes sense. And I guess you guys are also an agentic platform. Mhm.
3:37Um, and I guess what does that generally entail beyond just being interactable with a lot of agents? Like do you see it also being like a horizontal platform where you cover beyond processing and parsing to even editing and having a noode studio that clients can use?
3:51Yeah, the way to think about it is any sort of interaction that a model has with a document or unstructured files in general, we want reductive to be the best way for that interaction to happen. Gotcha. That means reading the document like parsing it, classifying that information, editing it. So much of human work is people reading from documents and writing into documents.
4:11Yeah, that will take care of everything from extracting that data, reconciling it against other documents and then getting the end output that they needed.
4:18Gotcha. And do you guys consider routing because I read on the website Redu under the hood has 12 plus models and so what's the decision framework between choosing a cheaper model, let's say, versus a more expensive one for different tasks and files. So the tricky thing here is that a lot of it is ultimately a longtail problem, right? And so you'll have a lot of pages that look like they're just text and then every once in a while you'll have this really complex table and you're not going to know exactly which page had that or anything like that.
4:47And so we started with this idea of okay, we'll use a lot of smaller traditional CV models for the baseline and then we'll use larger models for the really hard tasks. Um over time though we've been able to have this like pretty interesting approach to just the model architecture. We're going to announce this on Monday uh which is our new like in-house model.
5:09We're calling it R1 which is going to be able to do this end to end. So that components of you know capturing the layout and all that but also the last mile corrections that you'd want to make sure that you're at as close to 100% as possible.
5:21Gotcha. Okay. That's pretty great. Are you We could probably add the parsley now. feel like just have it relatively chopped and then add the other elements.
5:29But yeah, I guess going on to what you mentioned with this new model, what is your framework or even mental models behind determining whether to own your intelligence versus rent it? Um because last year, even though it was for a test, you had ROM OCR, which is built on top of the Quen VLM. Um and with this new one coming out, it seems like you're maybe focusing on that and not depending on providers.
5:52Yeah. So our thesis or like mandate for us as a team is we want to be the best possible provider no matter what like our customers don't think in terms of is reductive using in-house models or something else. Um they just want incredible results.
6:08And so we don't want to look at it as is it in-house or not. The thing that's happened naturally over time is we care a lot about that sort of perto frontier of accuracy, cost and latency.
6:20Yeah. And we keep finding that if you are looking at a specific type of task, a post-trained model on that task outperforms on all three dimensions.
6:31And so our stack has shifted more and more towards in-house over time. There are still like really horizontal tasks where uh Frontier just foundation model makes sense, but that's limited in scope today.
6:43Great. Okay. And so for the next thing, do you want to cut the peaches so we can maybe get some grilled and I can Do you want to take this new cutting board?
6:51Yes. Thank you. And then I'll just take this so that I can.
6:54Also, you weren't joking about uh it being distracting to talk while you cook.
6:58Yeah. And you guys recently launched the deep extract um and had the benchmark showing that the harness outperforms a lot of the base models. Yep. Um, and I guess how do you view the people come to you and say, "Why can't I just wait for these base models to get to the performance level and not need this harness and just use that compared to going to you guys?"
7:17I think one of the most interesting things with the new launch was uh I I don't know if you had a chance to read the blog, like we found this really weird trade-off between precision and recall. And so a lot of these specialized document processing platforms were worse than frontier models uh when you set uncap reasoning time.
7:39But the failure mode for the frontier models was on recall. So they were silently dropping rows um missing bits of context like those sorts of things.
7:47And if you're thinking about your extraction layer just missing information altogether, that's the sort of loss pattern that you're just not going to find in production, right? like you don't know what you failed to extract in the first place.
8:00Um and those are the sorts of things where having a harness around making sure and auditing the results becomes really really important.
8:07Um where I don't see it as either or like there are certainly tasks where a frontier model is great.
8:12But if you're looking for the most efficient tool for the task, you should probably specialize in terms of the task you're doing.
8:18Yeah. No, that makes sense. And I guess even for the announcement, you work with micro one to create benchmark.
8:25Yeah. Yeah. And I guess how do you think about um eval benchmarking tied with performance and even the concern of jagged performance for like benchmark benchmaxing y um across like the different tasks compared to like real world tasks.
8:40So we obviously do a lot of benchmarking internally and something that's frustrating for me is benchmarks largely have become marketing material. M um everybody's number one on their own benchmark and so there's just this it becomes really really noisy really quickly.
8:56Um and so the reason why we worked with micro one was we just wanted this like clear line drawn of reducto is not choosing the documents. Redduck is not setting the ground truth. Product is not you know manipulating the results in any which way.
9:08Um just so there's this baseline of it's an independent benchmark. Um even that obviously is not perfect. I think at the end of the day, the thing that matters most is for people to try things on their own documents.
9:20Um but at least it gives like a directional sense for people to start thinking about these sorts of things which is all we care about.
9:28Gotcha. And I guess tying in your recent launch R1 um does this indicate a change in how you guys will um do things? Is there anything interesting that you guys discovered while working on it?
9:41Uh I think R1 is a really big step forward for us because for a while we had the sort of anchor points of reductive is going to be the most accurate thing that you've tried, right?
9:53Um and especially as we start doing larger volume work like today reducto processes a little over a billion pages every single month.
10:02Um and that number keeps changing really quickly.
10:04Yeah. it becomes really important to have that sort of perto frontier conversation of making this available for all sorts of different use cases.
10:12Um, the reason why I like R1 so much is it's not just an improvement from the lens of accuracy. It's also going to really simplify our pricing and the way that our customers get to adopt the product in production.
10:26So for a while we would have these multipliers if you were turning on aic features and things like that. Yeah, that's all going away. Um, our one is just you send us the documents, it it'll be less than the per page cost of our base models for better accuracy than our most accurate models.
10:42Oh wow. Okay. Yeah. So like the pricing is definitely a lot better um by far and away. Like it's multiples cheaper than where we used to be.
10:49Gotcha. Dang. That is pretty exciting if you use Redducto at the scale that a lot of your customers do.
10:55Yeah. Which reminds me, you mentioned that a lot of your clients are in industries that have very low margin of error. Mhm.
11:01And I was kind of curious how you maybe think through um evaluating or even setting metrics for systems or even performance where let's say 99% accuracy may still not be enough if it fails on like the few use cases that um an enterprise really needs in let's say healthcare or a very low margin error industry.
11:22Like asymmetrical um use cases. How do you like think through evaluating that and considering that? So the first order problem is ideally our first pass should be as accurate as possible. Um and obviously that's where a lot of our head space is.
11:38But the second thing is there's never going to be a line for truly perfect.
11:42Like even if you get really really good at reading what's on the page, maybe you have ambiguity or things like that. Um and so traceability becomes really important. like being able to know where something was extracted from, being able to say uh exactly what a human should look at if they're reviewing it. Um and also having things like accurate confidence scoring so they know when to look at a certain thing.
12:04Um that becomes really really important if you're going to do something like healthcare document workflows.
12:09Um and so internally when we do benchmarks, we don't only measure ourselves on extraction accuracy. We say like of the things that weren't perfect, how reliably could we escalate to a human that this is not perfect? All of that kind of stuff really matters too.
12:22Okay. And so do you I guess keep track of all the hardest failure instances and then put that in like a data set that you could run to make sure that there are no regressions with like your harnesses.
12:34We do a lot along those lines. Yeah.
12:35Okay. Can you double click into that like are there specific infrastructure tools that you use or frameworks that I should have asked before. How do you want me to choose features?
12:44So this is completely up to you. So if you want to do it slices like that that's fine. You want to do it thinner. I should have done thin vertical slice. Okay, we also have a lot of peaches, so we can eat those and then use the thinner ones to grill and put on your sandwich.
12:57Um, but yeah, again, back to like your framework or tools or how you think about um catching these failure cases and then benchmarking against them.
13:05Yeah, something we don't talk about as much publicly is our ML team puts a lot of time into continuous evaluations. So being able to spot things that are maybe not incorrect but even just imperfect in production um which gives us the ability Mhm.
13:22to start understanding what is out of distribution for real world use cases.
13:29Um and it's not about the individual data point itself. It's more so about patterns of failure modes. Like we care a lot about being able to know in healthcare.
13:39Yes, you can say that you care about handwriting and maybe you benchmark your handwriting performance. Um, but you might not have a lot of data points that are handwriting on a tilted page where you know somebody scribbled outside the grid lines. Um, and those just knowing where you're falling short is the first step for you to be able to catch the sorts of things that you want to include in your next training run too. Mhm.
14:03And do you have industry specific um I guess criteria cuz I assume the needs at a healthcare company may want versus a law firm will probably differ. Um but like the law firms may have closer similarities and the healthcare companies may have closer similarities as well. Even though the industries are different.
14:21Yeah. Um this was a debate we had a lot in the early days especially because uh it's a lot easier to build a vertical specific document processing platform.
14:31Yeah. Um, the trade-off that you make there is I think a lot of documents ultimately boil down to very similar primitives.
14:40Like people take this for granted. You as a human when you look at a page make a lot of fundamental judgments that are just snap judgments, right? Like every time there's a gap between two paragraphs, you know, okay, this is a new semantic block of information. You don't like consciously perceive that, but it's intuitive.
14:58Yeah. And everything else kind of boils down to a similar thing like you naturally understand you know how a table structure is associating two dimensions of information all that kind of stuff.
15:09Um and the work that we do on making sure that we are resilience to you know messy tables and healthcare that were faxed means that we are naturally better at offering a reliable solution for our customers in finance as well.
15:24Um and so it's like a a harder undertaking overall. Yeah, I think in nets it just means that we can serve the most challenging cases across these customers.
15:34Gotcha. So all the learnings that you have from different industries kind of have that overlap since you're focused on the same primitives and like Yeah. Um basically building the intuition that a human has when they look at a document into like your models.
15:47That's the goal. Yeah. And obviously there are going to be nuances like if you're in legal you probably care a lot about something like strikethroughs and underlines um matters a bit less in healthcare but just having that baseline intuition is really really important for us.
16:02Yeah that makes sense. And is that kind of the future vision as well of reducto where which won't ever become verticalized will be horizontal through and through um so that any industry any company will have a very specialized or very general solution that performs well.
16:19Yeah. We don't want to be in a situation where for objective tasks like parsing you can very clearly say on a given page like hey this is exactly what was on the page right um we want that to be horizontal we want that to be zero shot for things where it's a matter of opinion like maybe a finance team has a different definition of a certain metric yeah those things should be promptable and steerable and improve over time true okay that makes sense and I guess
16:48Just overall with respect to reductto um how have you kind of perceived this whole boom of agents and LNS? Um is it something that you've kind of made a lot of cultural changes to to I guess adopt and like force your engineers to use coding agents um or even like internally have a lot of tooling or is it mainly like you're trying to focus all of these efforts towards a product that your customers will use or even a mix of both? Yeah, my
17:14co-founder um is very young. Um this is his first job out of college and so I think he he happens to be one of the most LM native people you'll meet. Um like you'll send him a message and it'll be like sent by a chat GPT back. Um and so given that I I think he just naturally it's not that we're mandating our engineers and saying like you must use cloud code or anything like that.
17:42Um it is very natural for people to see the sorts of things that he and others on the team are doing and like want to do it.
17:49One of the most interesting things for me is like our sales team now uses Devon a ton. Um Wow.
17:55Like people will make custom websites for prospects and things like that.
17:59Um and it wasn't really a top down push. I think people just started seeing like, hey, I'm spending a ton of time in Google Slides and it turns out that cloud design can just make a proposal better than you know what you put effort into.
18:13Um, and so they'll just do that like it's more about showing what the value could be more so than anything else.
18:19Gotcha. So, was it like a lead by example like your co-founder was using it a lot and then your employees were like, "Oh, wow. Like I should maybe try it out as well and become more efficient?" Yeah, it was that plus um we've allowed LLM and on-sites since day one or just interviews in general and our on-sightes are actually like a full day onsite. So, you spend 8 hours uh with the team.
18:43And the problems end up being really difficult to actually solve for unless you use LMS properly. Like I I think just by nature, the people that end up making it through the on-site Mhm. typically are people that know how to use coding tools effectively.
19:01And we'll see some extreme cases where there's this guy on our team named Arth. Uh if Arth is watching this, I'm sorry for putting you on the spot. Um Arth joined us while he was still a student at Berkeley. Um he was like 20 years old when he came on site.
19:20And so he was a freshman when GPT3 first came out. Yeah. Um, and if you watch him coding, it's kind of like watching a crackhead just like in terms of the number of things that he has going on at one point. Um, and the craziest thing with him in particular was I remember we gave him our standard software engineering onsite.
19:42And he did all of it in like 2 hours.
19:45Um, and so Ronic was DMing me on Slack, really stressed, saying like, "Shoot, he's going to be really bored. Like what do we And so we gave him our entire ML engineering onsite, too. Um, and that's the kind of person that we want to make sure we include on the team.
19:59Wow. Yeah, that's a that's a perfect hire. I feel like someone who's very very native with the tools and also moves very fast.
20:06Um, great. Okay. Do you want to try some of the chim chur? Yes.
20:09And then I think a peaches that should be good enough.
20:11Um, there's also a spoon over there if you want to use. And yeah, we got it set up for blowtorrching.
20:17But I guess while we're doing that, I want to double click on this with hiring. So you guys are notorious for hiring very slow and moving with a very lean team. initially your one of your earliest hires. I think your first hire was Ephe who's basically one of the best in the industry um for this specific topic um and even your other like growth hires um very specialized have their own business even Adele others and so I guess now going from just you and Ronic to now being a scaled up team are there traits that you see recurring among like
20:47your top hires that you even today when you're recruiting try to look for our number one cultural value um our number one cultural value is having obsession for your craft M um and I think that like you can think of obsession as just desire, but like the the real thing that I look out for is if you talk to anybody that is really really obsessed with this idea of being great at something.
21:14Um cooks, athletes, whoever, you always find that they have this like rigor to the way that they approach the day-to-day. M um like Yee is an incredible ML researcher, not just because he did a PhD in what we do. Um he is probably one of the most obsessive people about inspecting the data. Like people look through the data set really really closely. Um probably has like individual PDF pages memorized like Oh wow.
21:42I don't know anybody that has spent more time drawing boxes on PDFs.
21:47Um and that matters.
21:49Exactly. Yeah. like it it's really really important even when we had at some point we had more data labelers than we had full-time employees.
21:57Um but he would still be the type to look at the data himself and like really obsess over it.
22:01I think engineers need to be obsessed about things like customer support. Like it's not just about the flashy feature launch. It's about making sure that in production the longtail cases are addressed like all that kind of stuff.
22:12Um and I think that's a really hard thing to force somebody to want to do. Like if they look at their work as this thing that they want to be incredible at.
22:23Um they naturally have this tendency to want to improve in that way.
22:26Got so we try to select for that.
22:28Okay. And I guess how do you assess that or get that out from a prospective employee? Do you just look at their experience? What they've done in the past or are there questions processes in the interview that you kind of are able to determine how obsessive they are with their craft or even in the past?
22:45I think obsessive people tend to be obsessive in many different ways throughout their work. Um, and maybe sometimes it shows up in their full-time job. Maybe sometimes it shows up in like hobbies. Yeah.
22:56I really like asking people about something that they are just world class at.
23:01And you see the way that their eyes kind of light up um when they talk about that thing. Um, could be a video game even like people that are obsessive in that way as long as you orient them towards the right things like the right problems.
23:15Naturally transfer over.
23:16Gotcha. Plenty of peach slices by the way.
23:18Yeah. I'll grab a couple and we could also blow torch them. No, that makes sense. I think obsession does carry over and then we'll talk.
23:32How charred do you want it to be? as as much as you prefer. Honestly, you could put a torch in there.
23:47Honestly, I thought it would count.
23:50You want me to just toss it on a pan?
23:52Yeah, we should just toss I'm struggling a bit here.
23:55And we'll use the impulse stove. Um, you want to try? So, you just turn it on.
23:59I'm so excited for this.
24:01Yes. So, you can just twist it.
24:03Oh. any temp. Um um yeah, I've seen the videos of the founder cooking a steak and I rent my apartment, but if I didn't, I would be purchasing one.
24:15Yeah, I think this stove is very very nice. It heats up super fast. Even boiling water, it's it's very easy.
24:22Yeah. Okay. Going from very early stage now, series B, congratulations again.
24:27Thank you. Um, have there been any things you've had to unlearn or even change going from such a small team now to I guess growth stage?
24:34Yeah. Um, one I I think the number of problems at a company assuming things are going well never actually decrease in size.
24:47Um, you just get to work on different problems over time. And so like day one a lot of my job was just whatever in the weeds thing I needed at that moment. Um and so it's like an individual deal or like an individual support ticket. Obviously that changes as you have more people.
25:05Um and it's weird to let go of that. I think as a founder like for a long time I would have this anxiety if I wasn't constantly available on Slack.
25:15Mh. Um because it just felt like if I'm not looking like something could go wrong.
25:21Um that's been less true over time. Like you start to realize that the company has a life of its own on some level.
25:27Um but you always still spend a lot of your time with your top customers. Um you start having more like people related things over time. Like I never thought I would be the type of founder to write culture documents, but weirdly a lot of your job starts being things along those lines.
25:44Yeah. Um, but it's all fun. Like I constantly find that I suck at the current phase of my job and then you get good at three months and then you start doing a new job.
25:55Yeah. It constantly evolves as as you grow and scale.
25:58Is the process generally the same? Cuz I recall hearing you say in the early stage you would give one priority to an engineer for a week.
26:05That would kind of be maybe the direct directly related to the goal you want to achieve. Yeah. And now that the team has scaled up, do you still try to enforce that um one priority get it done in a week or is it a little more like an organization like a big tech company?
26:19Yeah. Um we still meet as a full team every single week. Um so like engineering should have good context on our top deals and vice versa. Like all of that has not changed. Um, I do think some of our important projects are hard to dismiss into like one week and so maybe time horizons for some things have changed and there are still things that are on the order of you know like it's a
26:47priority of the day not even priority of the week.
26:50Um, but we do try to make sure that there's clarity on like what are the set of things we really care about.
26:56Yeah. Uh and my thinking has shifted a bit more from weekly to more so like monthly priorities and quarterly priorities as well.
27:05But it's not quite like big tech organization like like we don't have a annual set of things like OKRs that we're going up against or anything.
27:12Yeah. We're still trying to operate it lean like a startup and great cuz you're constantly learning new information, right? like the market changes so quickly today that if you don't adjust as a function of whatever the current thing is like you're behind no s there especially in this age of AI and coding it's moves very fast um but kind of then to pivot more to the business aspect um I know that you guys um are in a space that
27:41is somewhat crowded you have other competitors and everyone is going as fast as possible to improve the performance Yeah. So how do you kind of think about defensibility um in the case where you may not be able to train out all the data of your customers um and so maybe the performance can't scale as the volume scales um and how you differentiate and kind of stay ahead of pack.
28:03Yeah. So I mean things like what I mentioned earlier of being really good at continuous evaluations um ends up being a key part of how we think about your processing a billion pages per month like how do you have a flywheel around that.
28:17Mhm. Um I think a lot of our work is not just on you know an individual type of layout or anything like that. It's this like horizontal nature and a really nice thing is the more the broader our customer base gets the better our intuition around the range of problems becomes too. Got it.
28:38Um I ultimately think that competitive markets are really nice because like it's very meritocratic. Um and so serving you know some of the leading AI native startups uh like a Harvey just means if we don't continue being the best like they will look for the best themselves.
28:57Um and our stance has always been like we just need to rise to that challenge.
29:02Yeah, that makes sense.
29:03So you would say you're probably competitive first. You want to win and and yeah have a level playing field.
29:09Great. Yeah, that makes sense. I think yeah especially these days too um with how the landscape is yeah a lot of markets will be very crowded and it's just a matter of can you be the one to move that fast and u compete so yeah it's good to hear I think more so than ever before it's less about like systemic modes and more so on execution yeah constantly for sure for sure great okay I think the peaches look good to transfer them to the plate and then you see get started on this steak so yeah
29:39kind of going back on what we touched before about the future of reductto.
29:43Damn, can I get some more oil?
29:48Yeah. on the future of Reducto, do you kind of yourself maybe taking the role like a rippling where you have a lot of different products that are horizontal um and kind of having this like compound startup that provides a lot of services and maybe even taking over like file storage or um yeah other needs that your clients may have beyond just extraction, parsing, editing.
30:11Yeah, we care the most about the actual actions with the document itself. Okay. Um, so the the way that we think about it is less so focused on file storage and things like that like the question for us is always can we be the best in the world at that task. Um, and as you think about things like classification on documents and parsing and editing like the answer is yes.
30:37Um, at least as of today things like you know just storing the data is less interesting for us.
30:43Yeah. Um, we would only really push on those sorts of directions if it in that leads to a better experience for our customers.
30:51And so whenever you get your customers, I also heard that um they usually come with a set of documents that have failed all the previous tests y before and somehow it works with reductto. Do you have any fun stories to share I guess about instances or like whatever you can um of like moments where something was just very magical that happened for?
31:11Yeah. Um, my favorite type of just like customer demo loop is when they find a use case that previously could not work.
31:21Um, and they end up just like being able to solve for that thing. Like they start introducing things that they just seen as out of scope.
31:29Um, there's also a few things where we find that like parsing accuracy ends up translating into downstream effects that people don't consider. Like one of our legal tech customers ended up finding that customers interact with documents twice as much when it's parsed by reducto.
31:47Um like they ask more questions. Um and it was something that like it's obviously not a feature that we sell. Um but they just found that like answer quality improved and citations precision improved such that overall customers were more likely to engage. Yeah.
32:02And that's huge. Like that's the kind of thing that we ultimately want to drive, but maybe it doesn't show up immediately in an email process.
32:08Gotcha. Okay. Yeah. And I guess even now on the team with you, Ronic, you guys both went to MIT, right? And then you met through a class that he was RA for or like being a TA.
32:21Um, and yeah, when he was a freshman. Yeah.
32:24Yeah. And you have said in the past that you're very impressed by just his ability and his talent and then work together. And I guess over the course of now it's been like two two years. Two we're coming up on three.
32:34Yeah. Like during those entire three years, have there been moments where you realized like you guys really clicked and these traits are very important for co-founders to have or is the moments where you know seem non-intuitive that the conventional startup advice they give that you guys kind of go against?
32:50Yeah. Um, I think one of my favorite things about our founding relationship to date is, uh, we still have never had what I would truly classify as like an argument.
33:03Um, like we've had plenty of discussions about things and talk through deferring opinions. Um, but we have a really really good dynamic of talking through things on their own merits uh, and like resolving disputes. Well, okay. And to me, that's honestly the most important thing outside of there needs to be this baseline if you really respect the other person. You think that they bring a complimentary skill set and all that.
33:30Um, but startups are really hard and it's really important that you feel like you can go through the ups and downs with your co-founder without being resentful.
33:39Um, and that's special. Like I I think that's hard to force or forecast when you're first meeting somebody.
33:46Yeah. And do you and Ronic have complimentary skill sets?
33:50I'd say so. Like I did my entire undergrad in CS at MIT, but um in comparison, I might as well be non-technical. Um yeah, like typically we will overlap on product. Um he just leads a lot of our engineering work across the board. Um and like is a type to have a lot of strong opinions there. And then vice versa for go to market on my side.
34:20Gotcha. Okay. But both technical enough where he can u conversations but I'm not going to I would never enter a hackathon against Ronic. Um I don't think he's lost a hackathon in his life actually.
34:33You guys also did a hackathon together right?
34:36The anthropic one when quad the early quad model came out.
34:39They were uh giving early access to Quad. Um that's actually sort of how our founding journey started.
34:46Um yeah, so back then that's where the whole like framing for Redto came in where models were already really impressive.
34:56Um but they had horrible context window limits and so that spiraled into this like long-term memory idea. Yeah.
35:02And everything else that reductive became after. Gotcha.
35:06Yeah. Times have definitely changed because for sure like then rag was a very big thing and you guys still do a lot of chunking right with your processors it less so now with less windows are okay yeah like I think chunking is less of maybe what piques somebody's interest um but a lot of problems ultimately are search problems okay and whether you call it rag or you call it something else like plenty of products are still some form of search and then some form of inference on top
35:35of the search results Gotcha.
35:36Which I personally see as like definitionally it's kind of retrieval augmented generation.
35:42Yeah. Right. That's true. Can you double click on that with the notion of every problem kind of being still down to a search problem. Um because I know like even with coding like ref and file search kind of became next thing after rags and I guess for document parsing for processing is the framework the same do you differently? Are there like insights that you can share? Of course.
36:02Yeah. So um I mean a lot of times when people think of rag they think of like the more traditional you chunk things um you embed them and then you use cosign similarity search to figure out what to pass into your models context.
36:20Um and people have an aversion to rag on the basis of like oh I'm not building a chatbot. Mhm.
36:27Um, a lot of our customers will still have, you know, like a file system for an agent and the agents is crawling through the file system to figure out where the relevance contextes context is and like it's reasoning on that context and piecing together information for multiple documents.
36:40Yeah. Um, what I mean is just like that process, whether it's the agent doing it or whether it's, you know, clearly visible in your search product, is you're searching for information, piecing together that context, synthesizing it, and making some sort of action at the end of it all.
37:00Okay. Yeah, that makes sense. It's like a pretty intuitive process. Um, let's see if Great.
37:07Okay. I think my stake is done. I feel like you can probably start looking at but yeah and I guess now going towards more how people can find you and what you're looking for. I assume you're hiring across different roles. Are there I think we have like 40 roles open at this point.
37:26Okay. What what are you bottlenecked by right now? Is it mainly sales or is it you still trying to find a lot of researchers?
37:32It's across the board. Um so we're hiring a lot on engineering like infrastructure problems really matter to us especially as we start to scale. Um also I do want to wash my hands after.
37:42Yeah. Um mistakes in the washing hand.
37:44Yeah. So we're hiring for our product engineering team, ML roles, um platform as well. On the sales team, we started the year with one AE and seats.
37:56And we now have 30 people on the sales or Wow.
37:59Um so a lot of hiring overall.
38:02Um I expect that's not going to slow down in the near term. Like we still feel capacity constrained as a team.
38:11Well, that's a good place to be in. I feel like challenge of growing rather than the challenge of being in pivot hell as you mentioned in the past of um not being able to sit down and solve a problem. Yeah.
38:21Uh is a lot harder than being at the moment where you just kind of grow. So yeah, it should be good, I think.
38:26Yeah. So you can transfer here and then we could wash.
38:30I've never cooked a steak with a fork before.
38:34first for everything.
38:40Great. And we're back. So, our steaks are ready and we can start cutting. Do you want to cut the bread and I'll cut the steaks?
38:46But yeah, I guess more so again on reducto uh you guys have made this transition from being the place where companies can come to extract and parse documents to even now handle editing, right? And so do you see a lot of opportunities or transitioning to taking on this whole use case because I assume going from reading to now like actually analying the editing and the knowledge work is can cover a lot of use cases.
39:10Yeah. My general view here is I don't think white collar work has quite had the equivalence of like um a quad code moment. Um, and I think if you think of a lot of white collar work, it's not just information synthesis, like people pulling from documents, but also how big are we making these sandwiches?
39:30Um, as big as you want.
39:32We could just cut it.
39:34Um, it it's not just people pulling from documents, but also like at the end of a lot of these processes, you write into a spreadsheet or you write into a word doc, whatever it is, right? Um, and so we really wanted to make sure that we are not just thinking about that initial layer of parsing and extraction. Like we want to make it possible for models to redline contracts as reliably as possible. Um, we want them to be able to fill out loan applications, do whatever
40:03a human would have had to do, right?
40:06Um, and there's a range of problems that comes up there that is just really hard to do. That's a great stake.
40:11Yeah. Um, like one of the things we were talking about earlier is humans spend billions of dollars per year on document localization.
40:21Uh, and so if you're a business in the US and you want to do business with a a company in the Middle East, um, you probably are going to want to translate your content into Arabic, right?
40:33And if you think about that today, it's very manual. Models are great at the translation.
40:38Yeah. But applying that edit to a document is really hard because you're going to need to take a document that was generated in English and change the layout. Like when you change it to a right to left language, now you need to consider like maybe the text flows over onto the next page.
40:53Formatting is different.
40:55Um and so there's a whole set of problems here that ideally we can abstract away for our customers.
41:00Um we're still early in that phase. We launched a form editing endpoint not too long ago. um close to like 6 months at this point.
41:09Um but we have a lot that we're about to release soon that I think will be a sub function change here.
41:14Gotcha. This kind of sounds like a pretty different problem though. It sounds very like computer usees like if you're filling out there's some parallels for sure. Um there's definitely a lot of work that's closer to codegen here as well. Um, but I think fundamentally being really really good at understanding things like visual structure makes it possible for us to also be really good at things like the edit application.
41:40Gotcha. Okay. So, do you kind of treat the problem or do you have like separate teams for these different problems or is it all under one umbrella?
41:49Uh, we don't really separate teams that meaningfully. Maybe this touches on what we were talking about earlier with, you know, how do we structure prioritization for the engineering team and all that.
42:00Um, we have an ML team, but within that ML team, people work on all sorts of different problems.
42:08They're definitely people that specialize in certain types of things. We just made a a really awesome hire. Um, his name is Leang. You might have seen he went super viral on Twitter for open source office agents.
42:20Oh, I think I saw this. Yeah.
42:21Yes. um really hard hire to make. He just moved over from Singapore, but like he's really excited about this sort of editing problem and so he's taking the lead on a lot of that. Like those sorts of just person problem enthusiasm alignments is really important.
42:38And how do you find the right people who are um as ambitious, let's say, for the mission? Is a lot of outbound or inbound? Um do you kind of like filter out folks like a specific way? Yeah.
42:49Um so that they're very like mission driven. I assume that's like a very big thing you consider in hiring.
42:53Yeah, we have steady state hiring. Like we have recruiters in house, we work with agencies, all of that. But every once in a while you find somebody on Twitter that is weirdly obsessed with PDFs um at a more frequent cadence than you would expect.
43:07And so like anytime we see something like that, like it says a lot about the person that they're spending their time thinking about document processing just willy-nilly. Yeah.
43:16We'll always try to get in touch.
43:17Yeah, that makes sense. Yeah. And I guess when you're talking about you haven't had a cloud code moment.
43:23Um what do you think would be a catalyst for that like Cambrian explosion? Is it just a matter of seeing how valuable the use case could be or is it like more so diffusion problem of like specific industries and maybe just more adoption for like the editing use case?
43:40Yeah. Um one I think model intelligence is right around there. Um and a lot of the frontier labs clearly hill climbed on codegen before they were thinking about some of the other problems for models to solve.
43:53Yeah. Um I think whereas code is in many cases like a verifiable problem um and engineers are the most likely to adopt there's definitely like a large component of enterprises have their data in all sorts of different places and there are like weird heruristics of you talk to a large financial institution about how like some paper process is done and they'll just have institutional knowledge of like oh if I see this in the bottom left of the screen I know
44:21it's from Kentucky and therefore or I do X.
44:25Um it's rarely the case that that is clearly written down.
44:28Um and so I think there's a ton of work for people in the tooling space to do to like aggregate that context, help them build the appropriate knowledge bases, give models the sufficient context for them to be able to reason on that data.
44:42Um but I don't think that we are far from a point where that happens. Okay.
44:47Gotcha. So it sounds more so like a fragmentation of the data um and context that seems to be the issue more so than performance that models have gotten so good at long horizon reasoning that it feels less and less likely that intelligence is the biggest bottleneck.
45:03Yeah. And so in that case, is that something that we need like a more concentrated effort because I feel like um you know, wrangling all these different sources of data from like this paper in like Ohio where they have all these like older file systems um isn't something that software necessarily can solve. Yeah.
45:21Um so like maybe this is not something that's trivial by approaching it through like a document processing or have you thought about it differently?
45:28Yeah. I mean the cool thing is we get to work really really closely with a lot of the leading teams in all sorts of different verticals. Um and so we've been working with you know the basis team um who's trying to automate N10 tax filing. Um we work super closely with companies like Harvey and Lora who are doing incredible work in the legal space.
45:48And part of the great thing about them specializing is that they start to figure out in a certain context what it takes to deliver that value end to end. Um, which is great.
45:59Gotcha. Okay, that makes sense.
46:08Okay, we could assemble one and then eat it and then call it. Okay. Yeah. And I guess are there any other milestones or things that you're looking forward to outside of this launch? Congratulations again for the rest of the year.
46:21Yeah. Um, across the board, our models are getting much much better.
46:26Yeah. You want to put this on with them?
46:29Um, so we have a a massive improvement to our structured extraction models as well. There, this isn't just accuracy again. Like we're getting better at things like citations performance and schema adherence.
46:42Um, and are doing that at a much more effective cost. We announced this today. Um, historically a page of structured extraction would have cost you all in like over 4.5 cents. And now we're able to do that at half the rate while also improving performance.
47:04Yeah. Wow. That is a big cut.
47:06Yeah. And so those are the sorts of things that we want to push on. Um Gotcha.
47:11Like really driving that Purto frontier across the board.
47:15Gotcha. And you were talking before about cost and performance. So, is this mainly a cost focus or just like bring it down while keeping performance at the level that was before?
47:24Actually, fortunately, this is not even from us trying to drive cost in and of itself.
47:31Um, we're just finding that we can get to better intelligence per dollar while happening to just focus on the performance itself.
47:41Like our main Nordstar is always going to be the most accurate document processing platform out there.
47:46Mhm. and being model agnostic as well like you said.
47:51Okay, how much do you want to put on?
47:53You want to put some more?
47:55We should do like two layers.
47:56Okay, here we can do you want to I could move on this side. Can also add some.
48:02Great. All right. How are you feeling?
48:07Good. I'm thinking about the I'm forgetting his username. Um, but I want to make sure I layer this in a way that's Yeah, you don't get ratio again.
48:18No, not that. These are also very small cuts. So, yeah.
48:22Should pull apart well.
48:23Great. They look great. Yeah.
48:27Yeah. Do you want to put the bara and I'll put on the teacher?
48:31Okay. Oh, wow. That is good.
48:38You put it on top of the steak or on top of the bread? Um, probably the steak. Okay. Yeah. And then we just top it off. Yeah.
48:51Oh, great. That looks so good.
48:59Okay. Then do you want to do Chimmy Cherry? Sure. Yeah. Mix it and then just put it on top.
49:28These action shots are going to be crazy.
49:30Yeah, looks really cold.
49:31Do you also want to do it on top? You could put the bread on top action. Let's get the Yeah, nice.
49:44Okay, perfect. Let's cut it.
49:46Yo, can we address the critics?
49:48Yes. Um, I think we should count the number of steak slices that come out as you bite. It's alleged that it's going to be three.
50:06Good. Okay. Let's cheers.
50:14Mhm. That's so good. Oh my goodness.
50:17Wow. You can never go wrong with a steak sandwich.
50:22Mhm. Man, this is great. We did a great job.
50:25Thanks for having us over.
50:27So, how does this So, what's the metaphor for reducto in this sandwich?
50:32You want me to make a document related comment on
