1027: Building an Always-On AI Agent for Busy Parents, with Dr. Dilani Kahawala

What if you could hire a tireless personal assistant for your whole family for 20 bucks a month? My guest built one, and parents are lining up to hand over their inboxes. Welcome to episode number 1027 of the Super Data Science Podcast. I'm your host, John Cron. Today's guest is Dr. Delani Cahawala, co-founder and CEO of Anna, an always-on AI assistant that handles the mental overhead of family life, the school emails, the calendar clashes, the soccer practice changes, all over text, WhatsApp and voice, no app required. Delani's background is room-markable, a Harvard PhD in physics, followed by McKinsey, and then a decade of product leadership at Etsy, Mehta and Atlassian, where she led a 150-person product organization before leaving to found her startup. In this episode, she reveals what it takes to build a long-running consumer agent that works for you around the clock and can't afford to get things wrong. Enjoy. This episode of Super Data Science is made possible by Anthropic, Groby and the Open Data Science Conference. Delani, welcome from down under to the Super Data Science Podcast. How's it going today? Great, thank you for having me, I'm so excited to be here. I actually had you on my list, I didn't tell you this, but I've had you on a list of people to invite to be a guest on the show for a couple months now. Ever since I became aware of Anna, your AI product? I feel really privileged because you've had some pretty incredible people on here. Well, we're going to help a lot with that today. Delani, tell us about Anna. What is Anna? Well, Anna is a personal assistant for busy parents and we think of it as one of the most advanced AI assistants out there. I'm pretty excited to be able to pretty much on the edge of what's possible with an agentic tech. You can basically talk to Anna like a human and we want that experience to pretty much be like you've hired a human on the other side and you text her or you like talk to her while you drive on voice. She proactively handles a lot of the mental overhead and the admin that kind of plagues families and takes up all the time in the world. Basically, and it's the second job. It seems like an invaluable tool. I suspect pretty much every parent is like, wow, this is a lot. I suspect there are a few out there that are like everything's under control. So having tools that can help with that, there's got to be a lot of demand for this. Is that what you've experienced? Yeah, I mean, honestly, the story was kind of crazy because we, I have three kids and so we built this to kind of initially to solve my problem and one other person on the team was family. And then like, let's finger out if anybody else wants this and like, it posted about it in a Facebook group and it kind of blew up. And so like, parents have been like, oh my god, please, please, please, like, I'll like give you all my personal information. You're a tiny startup. Like, when we were building our beta and it's been, it's kind of like overwhelming amount of like, hey, I just please solve my problem. We've definitely had a few people like, no, I have under things under control. Don't need you guys. But most of the time, we're like, no, please help. Walk us through a typical user journey. Like, what is it? What is a typical problem that a parent might encounter that Anna solves and how does Anna, do you say, how does she solve it or how does it solve it? It doesn't really matter. We say she, but like, people, I think people have not figured out how to refer to their AI assistants yet. So, so typical, like, I think we solve like two big problems with parents. One is this information overload that you get when you're a parent from all these sources. Like, the school app sends you, like, it's costume day tomorrow. I need to come dressed up as like a teddy bear or your favorite book character. And then like your soccer match changes location. And then your spouse doesn't know that you already figured out how to handle drop off and who's picking up the kid today. So, there's all this like logistics. So you end up becoming a PA for your kids and your parents. So, Anna, the thing that Anna does really well is it pays attention to all the information that comes into your life, like Gmail, email, so calendars, school apps, WhatsApp, like you're getting bombarded with all of this. And then it will proactively figure out what needs to go on your calendar, what what changed, what needs to go on your task list. And we'll kind of serve that up to you at the right time as if a human was behind the scenes kind of paying attention to all of that. So, parents typically come in, they plug in their email and WhatsApp and school apps. And I think the magic moment is that the first time, and I was like, oh, hey, I saw this match, like your soccer match changed time on Sunday. Do you want me to update your calendar? And they're like, oh my god, I wouldn't miss that. And that's kind of that's kind of the magic moment. But we have seen people use Anna for all sorts of incredible things, which has been part of the fun. Like they will use Anna to manage their email or unsubscribe from expensive subscriptions or like plan their holidays, figure out what to eat during the week, track their kids growth, which I think is like the amazing part of having, I think, what AI enables that wasn't possible before. But it's kind of blown our minds honestly. And so what's the interface like? So it sounds like if it's connected to your messaging apps, it's connected to the school systems. Does it also, yeah, I've seen from, because you created like a kind of like a homemade ad, I guess, like that I saw on social media. And so it looks like it works by your phone. Is there also like a desktop version? Or is it primarily phone based at this time? Yeah, I mean, we, a commission is for it to feel like you're working with a human. And so if you are an assistant today, the way you'll be working with that assistant is you'd be like pulling them or you'd be texting them or what's having them. And so the primary way, when you onboard Anna, you'll spend like a minute connecting your Gmail on on the app or on the web. So you get set up. But then the primary way that most of our parents work with Anna is by texting her or what's having her. And then also while they're doing something they'll talk to her. There's like a button that puts you on voice mode and you're literally just having conversation with her. There's an app, but that's more for when you actually want to see like what is my full task list? What are the things that Anna's made for me? What have these that Anna's done for me? But we just wanted it to feel like, Anna, just is there, just like a friend, just like you message your other friends. It's a person showing up in your WhatsApp chat or in your iMessage chat. Is that easy to do? You can just kind of create that and how hard is that to build? It's quite hard from like the infrastructure is there and it's it's possible and we we basically it's not trivial like making sure that Anna can smoothly talk through WhatsApp or SMS or tap and have that old sync so your like conversation wherever you go is continuous is one challenge. Then there is like the other challenge of well every time we send you an SMS it goes through the carriers in the US and we need to make sure that we abide by spam laws and all of that. So there's like an interesting challenge there. A lot of the time to like iMessage for example is very difficult to actually for a third party to get into. It's like Apple makes it quite difficult. They're just beginning to open it up but I would say the bigger challenge is actually like the product manager challenge of like when you don't have an app UI to rely on how do you create this like experience for a user that feels magical through a text-based system you're like managing a whole life through a text-based system or a voice-based system that's been I think the more interesting problem for us to crack. Yeah it is an interesting problem to be able to tackle and so with your extensive product management background and so to to go through the CU after doing a Harvard PhD in physics you then went to McKinsey as an associate at C is a senior product oh well product manager then senior product manager at at C lead product manager at Facebook and then group product manager head of product head of product management at at last year and so a decade of experience in senior product leadership positions and now your full-time creating in a you're the CEO of the business but you're surely also the head of product. That's kind of all we do so it's been the funny thing is we've we've had I've had to pretty much throw away a decade of how we think production would be built for people really. And that's been really fascinating. So we've had to like think very first principles from when you don't have the crutch of a user interface. That's one problem to solve. The other problem is the average person doesn't really yet regularly interact with AI agents. So like I'm on code everyday all day and in my mode is if I I just ask and it will have an answer for everything and and the mode is use ask and like it gives. But I don't think the average person is yet familiar with like deterministic set of options that you can tap and drop down to things like that. You just are seeing an agent to do things for you is still a different like a mental model. And so the second challenge of like how do you get someone to that operating model where you just ask? And then I think that third thing is how do you when you work with code it's it never like it's not inaccurate but some you need to correct it right like it's it will give you an answer but you'll have to like cross check it and be like what did you think about this would you think about that most of the and these models are like optimized for coding they don't have they're not trained on like household data so it doesn't inherently know what to do with like where does this switch calendar does this go in like it doesn't have that understanding but consumers don't have that much patience for like your assistant getting something wrong it's to constantly be correct you don't want to be constantly correcting it so those are the three things that I think we've had to really think about how to like reliability the interface and and just teaching users how to work with an agent have been the three biggest challenges. I guess something that's quite different about a agentic interface like cloud code and what you're building is that in cloud code it is still a turn-based conversation where yes it goes off it's agentic because it spins up it figures out how to tackle a task spins up sub agents as it needs to but ultimately when it's done what it's doing it just stops it gives you an output and then waits forever and if you never come back to that chat nothing ever happens again in that chat it seems to me like with Anna you would need to there will be times where Anna needs to reach out where maybe Anna has sent the last message and needs to send another one before you've responded because something has changed with your kids football practice or you know an important email has come through or a a reminder of an upcoming appointment or something like that and so there's so it seems like it's more discursive more back and forth it's not it's not as linear or or just turn based back and forth conversation yeah and this is I think the biggest change so I think when like Anna is like a long-running agent meaning that it doesn't kind of stop and wait it is constantly working every every second every minute working for you behind the scenes so when you know like the open calls of the world the Hermann's agents and now we see maybe like Rockbot all these agents are trying to tackle the same problem of like how do you just continuously work with someone but with like not that much success because most people like set up an open poll and then they kind of give up on it after like two weeks because what we have to have happening behind the scenes Anna is constantly working for you on a set of things whether it's like checking your email or figuring out if a piece of information is noise or if I've handled this before or is it already on your calendar have you already tackled this task which kid is this relevant for this constantly working in the background and you're at the same time having conversation with it where like Claude we will have a team of you know domain specific experts agents who are going and doing a bunch of things for you but Anna will be like oh I picked up that your meeting change and it's gonna clash with your school pickup I need to interject and give you that message while you might be asking Anna to you know book a restaurant reservation so we have we had to have like handle that so a few things up in the correct way it's like a whole layer of ops that code doesn't have deal with you machine learning predicts and Genai creates but neither is built for complex constrained decisions that's where mathematical optimization comes in giving you explainable trustworthy decisions you can act on with confidence Grobe is the fastest most reliable solver organizations rely on for their high stakes decisions want to see it in action join the twenty twenty six Grobe decision intelligence summit September 22nd and 23rd in Las Vegas for training expert insights and Genai enabled accessibility discover why 70% of the world's leading enterprises trust Grobe and start achieving optical outcomes yourself had to super data science comm slash Grobe for the conference details that's super data science comm slash g-u-r-o-b-i yeah that's a really interesting use case that I hadn't even talked about in that you know the way that I was like oh this must be more complex not just having back and forth but it is also interesting that you could be yeah you could be having a conversation you're in your car talking to your car your car phone but your car phone is Anna like and on the other side and you're saying you're you're having a conversation about scheduling some upcoming event and then it has to actually interject and say we're going to have to take applause in the conversation that we're having because this important thing is come up that is a really interesting and yeah I have never experienced anything like that in any conversation with a non-human today so this is like really obvious in voice mode so when you put voice mode on you could be if you ask Anna do something complex like go find me a dentist she has to go do some research and she has to like look up where you are like who's best reviewed that task takes sometimes like a minute or two because that's a complex task in the meantime you might and voice goes pretty fast you might have fired four or five things at her and so she's like so we like fanned out a bunch of agents who are doing multiple things for you but it's it has to be then like queued up in the way that the conversation piece of it is understanding okay you ask me this first then you ask me this thing this thing is finished okay now I'm gonna like finish what I'm saying to you and then get back to you that was a fascinating challenge and I don't think what's interesting is like when we started and it was only a few months ago the voice models then were not good enough to do that to even handle that like upfront conversation and it's only like three months ago that like Gemini live changed substantially it could handle like the conversation piece while we have like the agentic brain behind the scenes doing all the fanny out and so Gemini live is a like a it's a voice platform that you can develop on so actually there are many voice models like 11 labs is probably like the most famous in in that space a lot of the voice models are like speech to text and then text to speech like it it you know that's how voice models evolve Gemini live is one of the first I would say voice to voice models it understands your voice directly and like responds without converting it into like text in the middle and we found as there are many more voice models out there and we we experiment with a lot right now it's it's our preferred one really cool all right so I think we now have a pretty good understanding of the Anna product how it works and some of the tricky nuances of building a product like Anna it seems like based on the conversation we've already had I maybe have some understanding of how this came about like it sounds like you built a solution for yourself for your family you maybe didn't at any point in the early days have any kind of commercial expectations or did you given how commercially oriented you are as an individual it may be it occurred to you right from the beginning as you're kind of playing around with this idea it's funny because we were it gives a little bit at the start story but like we were in the middle of a pivot we did not start out building Anna we were in the middle of a pivot we were pivoting actively but we were pivoting like we were experimenting with the old sorts of enterprise ideas because that's kind of my background but then like our lead engineer who's like part of all built this thing on WhatsApp and he's He's like, this is my assistant that manages all my ass. and I'm like, I need that, I need that in my life. And so like, I got it. And I was like, hmm, just kind of interesting. It's just like a different way to work with an agent because it was literally on WhatsApp. And it was like vastly different from having an interface that I needed to have a conversation with. I just posted about it in a Facebook, like a mom's group. And it kind of blew up. And I think that's the point where we're like, of all the ideas we've been testing, this was like a very clear spike in like, oh my god, I need this, like this is a massive problem. And you see all this like latent demand, which is like, I've been trying to build this with Claude code or I've been trying to build this with OpenClaude. I've been trying to hack this together. So you have all these parents who've been trying to hack this together and you're like, okay, now there's something there. That's quite a group that you're hanging out with if they're trying to get Hermes agents. - It's a mom's and tech group. So it is definitely self-selecting. - I see, that makes sense. - And they were like, okay, let's give this a month of our time. Like if we go really hard at this and we build out a prototype, is there something here? And very clearly there was. And that's when we're like, okay, I think this is, this is such an interesting space. It's a massive market. Obviously they're like millions of millions of parents and a lot of them have this problem like, and it's such an exciting space. And it's also lovely to actually just wake up in the morning and the AI thing you're building is like, giving people their life quality back. And so it just like, I think it fell into place pretty quickly for us. - That is really cool. And it sounds like the way that you're building it is with Cloud Code. Is there a development team or is it mostly you developing this? - It's a pretty small team and many more Cloud Code accounts than team members. - So we're all building, but the development pace is incredible now, obviously. But you also have this like new set of problems that you didn't have when you were building five years ago that you're constantly just like trying to keep up with. And that's been fascinating. - It must be so much fun to be getting better and better tools to work with all the time. Like it is wild. To me, I am always paying for Fable 5 for any development that I'm doing, any book rating that I'm doing. 'Cause it's totally worth it to me. Like that increment, it's not incremental. It's a big performance improvement in terms of understanding the context of what I'm looking for. And yeah, really fun time to be building the way that you're building for sure. How do you evaluate what you're doing? Like when you're building something that parents are gonna be working with that are gonna be impacting kids, even if kids aren't using it directly. So they are probably hearing their parents interacting with Anna. And so there must be like a relatively high bar for evaluating what gets output, what kinds of actions get taken. - The Evalid measurement and the improvement loop is kind of everything. Basically, because when you're a consumer, exactly what you said, you can't afford to be wrong like 20% of the time. That bar is the way, like in a turn-based conversation with cold code, you might like course-correct it. That we don't have that luxury. So for example, Anna needs to know pretty quickly if, or with high accuracy, if a piece of information for your family that you're getting from an email is noise or signal. Which calendar does it go on? Have I already handled it? Is it for you or for your spouse? Is it something I need to inform you about now or like later? And that there are hundreds of these things that you could let a model do on its own, but it will get wrong. At like 30% incorrect. So we have a really solid test suite, basically an Eval suite, that is constantly evaluating, you come up with the answer for like, hey, this is an email that represents a school email. From this, you have to extract like dates and times. For example, did you do that correctly? And then like if it didn't, we will then have an automated loop that kind of iterates on it until it does pass that test and we have like thousands of these tests. And so the, and we actually like running our test suite is one of the most expensive things that we do because it's, we just need to cover so much space 'cause people do lots of different things with Anna that they wouldn't do in like a non-agentic product. And then I think the most important part that I think we've now figured out is when people get frustrated with using Anna, that means something that she did was not meaning their expectations. How do you figure that out and then like add that to your Eval suite in an automated way? So like, it's constantly like self-improving. And this is kind of really at the heart of what what makes Anna good. And I think it's the thing that sets us apart in many ways. - Sure, sure. Yeah, it really sounds complicated. You're talking about expensive there. I assume we're talking about kind of like computationally expensive, which also literally does mean dollars. It does mean money being spent. You might not be comfortable answering this question and so you don't have to. Like this is potentially your secret sauce. But I'm kind of, I'm curious how you choose like what large language models you use in the back end and how you control token cost from being, and I'm gonna have to ask you about like pricing model and how you'll eventually make money. But if this is earlier in the episode, you talked about this being always on. You're kind of always consuming tokens. And if I think about, I can spend tens of dollars seemingly in a few minutes with Fable 5. And so, you know, if you make the wrong model choice for a task that sprawls into tons and tons of tokens, you could very quickly have these sprawling costs. And yeah, I don't know what your business model is, which I guess you might need to tell us about it now, but I am suspecting it's something like a monthly subscription fee that's kind of a fixed cost. And so it's your responsibility as the designer of this solution to make sure that you're not underwater for providing the solution. - We did not expect this to be a problem so early on, like startups at our stage don't really have to think about like running costs so early. So our business model is a simple subscription. At this point, it's like a two week trial and then it's $20 a month and you get to just kind of figure out your subscription. - And you can go, it's at highanna.com, right? H-I-A-N-N-A.com. - H-I-A-I. - H-I-A-I, my bad. - And we kept it simple to begin with just so that, and I'm sure we will experiment with it, we talk about like how pricing is in the space. It's like the world worst in a little bit, but we were going after families, we wanted it to be recognizable as a subscription, like every other thing they subscribe to so they don't have to be like, what is token-based pricing? That is not a thing that people yet have really understood. So we kept the subscription simple and it's quite cheap, right? Like if you think about how much you'll call max costs versus $20 a month, this is like always on called max. So the price to cost is enormous. So you're right that we are constantly like, whether you message Anna frequently or not, we are constantly just like spending tokens, figuring out what's going on behind the scenes for you. So the answer to which models we choose, very slow, we started very simply, like everybody else building with anthropic models, because they were just so much better like eight months ago, I would say there was no one could get close. But over time that's evolved and we use a host of different models for different reasons. So our voice model is different. Our, we have fast models that very quickly classify things. We have fast models that respond to you and carry on a conversation, but then we have our strong models, like strong thinking models that are doing a lot of the, figuring out, you know, how I already handle this, do I need to put it on? on your calendar, but is there a conflict or going to go to research to figure out which restaurants are nearby. So we use a mix of models and that EVA suite is really critical because as new models come out and we want to switch it, like having that EVA suite makes it really easy to be like, "Okay, did we do something bad or did our performance degree by shifting to a different model?" But we do now actually, we have shifted towards using open-source models just because it has become quite expensive to serve our current user base. So we are trying to be smart about how we control the cost because for us what we don't want to do is like calf your usage and be like, "Okay, well, you've run out of usage of Anna." That's like a horrible experience. I'm called quote, "You can turn on extra usage or whatever, but for a consumer, you don't want to do that." So we want to give you the most premium experience of Anna possible for the $20 a month and that means behind the scenes we're just trying to figure out how to get the most powerful models for you without basically burning through all of our own way. For all of you listeners who want to level up your AI career through hands-on learning, ODSC AI West October 27th to 29th in San Francisco is the place to be. ODSC AI West is my favorite conference in what sets it apart is it's all about doing. You'll gain practical skills by working directly with the latest AI tools and frameworks in immersive hands-on workshops and tutorials led by experts who are actually building and shipping AI. I myself will even be doing a keynote at ODSC AI West this year on how individuals and organizations can thrive in the agentic era. The full program covers where AI is moving now, including AI Engineering, AI Powered Software Development, Physical AI Robotics, and Data Science. Beyond the training, ODSC AI West brings the AI community together with networking events, meetups, the AI Expo, and more, giving you the chance to learn, practice, and connect all in one place. Super Data Science listeners can use the code "Super" at checkout on odsc.ai for an additional 15% off your pass. See you there. ODSC AI West looked over 27th to 29th in San Francisco. Sure, and I was talking earlier in the episode about how exciting it is to be developing with Frontier capabilities in like a cloud code environment, but similarly in recent weeks, a lot of my podcast episodes, so I do two episodes a week, so yours will be this long form interview on a Tuesday. On Fridays, sometimes I have interviews or we have like an in case you missed an episode with the recaps at best conversations from the past month. But also, some of those Fridays are just a deep dive on a topic that I think is really important for us to get into, and I do research and write a script and two of those episodes in the past month have been about open source models that are so, yeah, so Quinn and Kimmy models that are just so useful and so close to the Frontier that the American labs are creating, yeah, they're not exactly as good, I would say, yeah, but they're so close, and if you have a good e-vail suite, I think they, they're just like too good, and we've tried a whole host like DeepSeek, Mini Max, Kimmy, and they're like every week something's changing. So just keeping up and testing that has been actually like our new challenge to being like, if we try this model for this, it's changed dramatically in the last six weeks, I would say. And so it's an interesting world to play in right now. For sure. How do you ensure that your whole system is scalable? Like how do you, I mean, maybe there's a bit of a chicken and egg with, you know, you are finding alpha users and then beta users and making sure it kind of each of those stages that your infrastructure can support that growing user base? I guess it's two answers to it. Like one is like managing that cost side that we talked about. Like as you grow, how do you make sure we can like sustainably support people? And I think we're beginning to figure that out quite well. The infrastructure side, I mean, there's the standard sort of like, how do you make sure that you can have a chat service that can serve thousands of customers versus tens of customers? So that kind of thing, I think, is a more like a standard software engineering problem that's been solved before, but you kind of, you know how to work through it. I think the bigger, and then you have like interesting info issues, like, can you, there are like rates of like, how many messages you can send by SMS through like Twilio, for example. And so those are like interesting problems that we like, okay, I guess we better figure that out. We have to like get approval from a team mobile. But I think the biggest problem we've had to solve when we're scaling is because you're an agent, and you can, in theory, do an infinite number of things compared to like a to-do app say five years ago where, yeah, maybe you have like 20 features, 25 features. You can ask Anna to do anything. And you, Anna might get some of that wrong, and the user might get frustrated. I think the biggest thing for scaling for us is, how do you maintain that quality and accuracy bar as people push the boundaries as like hundreds and thousands of people push the boundaries of what Anna can do? Like we've, we have a way for you to log into pretty much any, like, tool out there. And so at some point, we were seeing people like, log into their notion, and they're like, what, what are you doing with, with notion, but we hadn't optimised for that. So we've had to build this loop, which is constantly picking up people's frustrations. And then fixing those frustrations, which I think like a cold code, for example, doesn't necessarily have to do, because we have a much higher bar for like, you can't get it wrong. And that's, I think, that's where we've like spent all of our, like, cold code accounts trying to, like, get under control this, like, constant frustration fixing loop. It was very powerful, but also, like, how do you scale that as you, as your customer base scales? It's been interesting. That sounds like a part of the IP mode that you were developing, for sure. I think so. Yeah. How do you think about adding in new features? I mean, you just said that, you know, Anna could kind of do whatever, but I mean, not, you know, capability, yeah. There's a lot of capabilities, obviously, when you have an LLM in the back end, kind of interpreting and assigning tasks, there's, you know, infinite flexibility in what could happen. But what when I say features, I mean, you know, being able to support I message or, you know, deciding some kind of new product decision. How do you, how do you decide where to go, what feature to prioritise next? And there's two things. One is like old school product management, and the other is latent demand. Like on the, so we try to make a bet on where do we think, like, what's the vision, what's the dream for this? And so we made an early bet that people were going to be talking to Anna and, and that's quite a different, there were no products, people pretty uncomfortable actually talking to, you know, like whisper flow has kind of set the stage for this, but we made the bet that actually, like in the long term, we think people are going to be in a conversation live because that is so much more efficient. And so we, we figure out what our vision is and we're like, okay, this is the bet we're making. So we're going to make a voice mode of priority, even if like in the early days, we probably had like a couple of people try it out. So that's one side of things, but I would say the primary way, once we've figured out, like, what's the vision here, which is like, and I should feel like talking to a human, and I should be proactive behind the scenes and not you, not you're not having to have a turn-based conversation for everything. The second thing I think, and one of the things that kind of learned at meta really is this idea of latent demand. We see what people are trying to do. And when we see a lot of people trying to do that one thing, we're like, okay, we need to go make that feature much better. So for example, people asking to collaborate with their partners. And so we didn't, we didn't have that early on, and when enough people asked for that, we added that in, or we see people trying to connect outlook, then we ask Anna, like, can you please, like, I want to connect my outlook? And we initially like, who is in that look, but a lot of people do. You. And a lot of people are saying it's like, and then you're like, oh, well, okay, well, that's flow for adding outlook was not very smooth. Now we go and make that smoother. So I think we're going to have a little bit more time to talk about this. We pay very close attention to where is there already demand for that and we can go off for that. Kind of zooming out further beyond, you know, we were just speaking about individual features. Let's now talk about a product idea. So you alluded to earlier in the episode that the company that's now building Anna was doing something else. And so, yeah, I mean, maybe give us a bit more context on what was happening. Like how long were you and a team of people developing product ideas and how many kinds of pivots or, you know, yeah, what was the journey like to finally get to a point where you're like, cool, now we're confident we have something that works. It sounds like you kind of, I guess you told us a little bit of this story kind of at the end of the story where you, it seemed like there was a lot of demand. We were like, OK, let's invest a month in trying to build something relatively robust and see how that goes. But what was the journey up to that point? When we started, we were called Brave and that's still like the parent company name. And we're building project management agents for software teams. And that's kind of what I was doing at the last scene. We're doing a lot of project management for, you know, with JIRA. And when kind of the AI wave came about, I was like, there is a very different way to do this than, you know, with like a con button board. So we started out doing that like an enterprise software project management agent product. What happened was that like when we talked to customers, they seemed like there was a lot of demand for it. And I think it's an obvious problem, but it's a combination of, I think, the timing of when we brought this to market and where the technology was, we found out almost say that probably didn't have the kind of product market fit that would, that we were looking for. And so a few months in, we after we had raised funding and we had hired a very small team, we decided, it was a very difficult decision, but we were like, we're going to be decisive and we're going to pivot away rather than sort of like continue to kind of butt our head against this problem. And we spent a good like three months exploring this like idea base of like where we, what is our next thing? And we were very deliberate about experimenting quickly and trying to see when there is like a spark of demand. And we were on this journey with primarily like enterprise ideas of like we would see where there was a problem and we would try to build a part, have quickly, we would try to get to customers quickly and see how the response was. That's when we came, we were doing that when we kind of stumbled on Anna basically. Stumbled on a direct to consumer product instead and you mentioned enterprise of course you had experience in that, but I also happened to know that you know building enterprise products, you can get bigger valuations, you have stickier contracts, typically big juicy ones with nice logos. There's all kinds of reasons to be focused on enterprise, but there's something really cool about when you go to the consumer route and something clicks. And you can kind of, because then you're in a cool situation socially I feel as well. Not only does that work and you have networks of fact, network effects like you were saying how you can exploit the data that you're collecting from your users. So that allows you to develop a mode relative to other people who could be like, oh yeah, I'm also going to create an AI for parenting. One cool thing about a direct to consumer product is in a social situation, the old cocktail party, it's so easy to explain, which is nice too. It's really fun. It's extremely fun to work on a, because you're a product, especially because it's so, it's incredibly satisfying to understand what that person is struggling with and helping help solve their problems. And I think in the enterprise context can be quite hard because you're sometimes quite removed from what these people are doing day to day. It has consumer in AI has been very under served, I think, because all of the effort and all the companies that you see out today of the big ones are really all like enterprise or prosumer in some way. So it's an exciting time to be building in consumer AI, it is challenging because I think we're trying to figure out like 10 years ago when you're building consumer, you just try to acquire, you have to grow quickly, try to acquire as many users as possible. But that's quite costly to serve them within the AI world. So I think we're still figuring out what, how does the startup scale in consumer space? And so that's like the next challenge. Yeah, scaling a SaaS business was way easier to have like an extensive premium tier, for example, or like how Google, Facebook, these products that are still free today, because it was so inexpensive for them to, some of those users aren't providing them any value. When it comes to an incognito window, it's hard to serve ads to them that are well-targeted, but it doesn't really matter because it's so cheap and there's so many people out there that are, you know, you are able to hit target to dads or whatever. Yeah, it is a trickier thing that I think all AI businesses face today, where it is so much more expensive to serve your customers than it is for a SaaS business. I mean, it helps if you have like a mega wallet behind you to bath that, like, you know, if you're like a matter or good one, and you can kind of do this. But as especially as a startup, you really have to start thinking about your unit economics much earlier than I think previously. And I still, the funny thing is, you know, you always think like, well, the token cost is going to come down, but you're always like, you always want to be building in the frontier because you always want, like, you're still just barely getting by with what is possible with the best models today. So you're like, I always want the best model and the best model and the best model. So it's going to be so interesting to see the open source models have helped. It's going to be really interesting to see how these like, because I don't think a big freemium tier can play out without at least some limits. And so we've seen other similar companies have all sorts of interesting pricing models, but they might like cap their free tier. Or there was one that you had to negotiate the price with the agent, which was like fascinating because I think, like, poke. So no one has quite landed on this yet. And I think we're going to be doing a lot of experimentation. Regular listeners will already be aware that I'm obsessed with Anthropics Fable 5 model and it has taken over my working life. I'm writing a technical book that includes latex files, mathematical notation, Python code examples, and Fable 5 in Cloud Code handles requests I make across whole chapters with accompanying Jupyter notebooks and to end work that a few short months ago would have been dozens of separate requests with way more manual fiddling required with Fable 5. It just works essentially like magic first time. Cloud is the AI for problem solvers. It's the collaborator that understands your entire workflow and thinks with you, not for you, whether you're debugging code at midnight, building a financial model or strategizing your next business move, Cloud extends your thinking to tackle the problems that matter. For problems worth solving, get started with Cloud at Cloud.ai/superdata. That's Cloud.ai/superdata and check out Cloud Pro, which includes access to all of the features mentioned in today's episode. Cloud.ai/superdata. I love it. You have an exciting trajectory. Where do you hope to be with Anna in a few years' time? It's moving so fast. My dream is that if you're a family that in like a year or two years, you actually just have a team of agents who are just handling your admin and you just have like 10 more hours in your week that you're not doing like horrible admin work. That's kind of the dream, like you just have more free time. And I think under the hood that means there's like a team of agents who are constantly just figuring out what needs to be done to make your household run, but potentially even like talking to the agents that belong to other families and coordinating for you and figuring out, oh, like who's doing the soccer pickup this weekend and kind of figuring all that out? Like agent to agent, interaction in family to family is like where I see this going and it's all going to be voice and SMS or voice and WhatsApp and that kind of human interface rather than someone tapping buttons. I think so. Definitely. All right, I have alluded to the fact that you have a very interesting background and we've kind of done a cursory glance over it, but I'd like to double click on a few things from your past just to give people. I think we've covered Anna pretty comprehensively now, but it would be interesting to learn a bit about you, Delani, and your journey to now being the CEO and co-founder of Anna. So you did a PhD at a little-known university called Harvard in physics, and then you jumped to McKinsey. And I think that one I can understand because I also thought about, you know, Bane, BCG, McKinsey, when I was getting to the end of my PhD because it gives you the opportunity to showcase to the world that you've now developed, you know, not only do you have this great technical background, but you can be commercially savvy as well. And you get amazing experience at one of those big consulting firms. So that one, I feel like I can understand the transition, but maybe you can add a bit of color or tell me what I got wrong. I had always thought it was going to be a physicist, like a academic, and I was doing like very theoretical, I was like particle physics. So like really large head drawn collider, thinking about like dark matter, bunch of that stuff, very, very fun. I get thinking about dark matter all the time, some dark stuff. Yeah, especially like, hey, I these days, I'm like, oh man. But I was in Cambridge and you know, you're surrounded by like MIT and Harvard, and there's this like, it's not quite Silicon Valley, but like, I got there. I was like, there's all this like, people trying to do start. What are our startups? What is like, what is this? And I came from a show, which at the time didn't have like a huge texting. And I was like, oh my god, this stuff moves like so fast. And like people do really exciting things in a very short period of time, where like, takes like a year and a half to write a paper and like get it published best case. And I towards the end of my PhD was like, I think that's what I want to do. Like it's just so much more exciting. You can see all these like startup competitions and crazy stuff that comes out. So I actually knew that I wanted to do tech, and potentially even like be a founder. But I couldn't easily make that jump from like a physics pasty. Like my options at the time were like, being an academic will go join like a quant hedge fund. Those were like the two things that people kind of do. And I was like, well, I want to be do, do like, being a tech company and build. I didn't even know how to articulate that. And so I was like, hey, I think the way to do that is to get a little bit more commercially savvy. Like you said, which was like a McKinsey jump. And as I was doing that, I kind of figured out, okay, product management is this interesting space where you still get to work with technical people and you can leverage a little bit of your technical background. But you're still thinking about the business. And it was, it was a very exciting world of time and not even very well defined. And I happened to have like my manager at exy kind of took a chance on me, even though I had no product management experience. And I was like, yeah, this is it. And it's he's like the most fun company in the world. So it was in New York at the time. And that's that's kind of how that transition happened in Brooklyn. Yes. It was like the most fun I've ever had, honestly. Wow. That's cool. I didn't know it was that fun. It was like, you know, it was a pre IPO when I joined. And it's it's such an interesting unique work culture. And then Facebook, Atlassian, I mean, I think those are kind of understandable transitions. I don't know if you have anything to add onto that. And you definitely can't. But my question that I already kind of said I was going to ask is then what prompted you to go from being this very senior role at Atlassian head of product management for the shared experiences platform, you know, leading a team, leading an organization of 150 people across North America and Asia Pacific region, like sounds like an amazing opportunity. But you left almost two years ago now to co-found Anna. Well, I guess it was called parade at the time. Yeah. I mean, like I said, when I left my PhD, I was like, I want to found something. And I had like actually dabbled with a few things while I was doing my PhD. And there were a bunch of various, like I was on an F1 like a student visa. I didn't have any money to do this. So that was not the right time. And then kind of like when I joined the tech companies, things were growing quickly. So it was always like hectic. So but I in the back of my head, I was like, I always wanted to found something. And then like 2020 to 23 came around. And I could see pretty clearly that AI was going to change things. Like, yeah, there was like GPT three at the time and people were like writing things with it. But you can see that this was going to be like very different from every other sort of like tech revolution we've had. And I was like, well, I think this is the time. Like if you don't do it now. And like I at the time was had just had my third kid. So I was like not saving very much. And like struck like struggling to manage like three kids and work and everything. But I was like, this is the time. If you don't catch this way, like this is the way we don't want to miss. And I think that's what kind of prompted the okay. It's time to it's time to make the call and it's too exciting. Yeah, I agree. I say a lot in my when I do those Friday episodes where it's me just deep diving into a topic, my final sentences in that episode will often be about this is an unprecedented time for you to be building things, whether it's in an organization or as an entrepreneur, as a hobby, you know, there's never been a time like it. And I don't know if there ever will be again. We'll see. Hopefully it unleashes even more waves of creativity and possibility. But fantastic. Thank you so much for taking this time out of your schedule. I mean, I guess you're lucky and it's taken so much off your plate that now you could do a podcast episode with me. Exactly. Exactly. It's like I have like so many hours of like free time that I don't have control through my email. Yeah, exactly. I'm sure. And so before I let you go, something that I was supposed to tell you before we started recording is that I ask all of my guests for book recommendation. I don't suppose you have one for us. It doesn't need to be a technical book. It can be like a favorite novel or whatever. Sapiens by. Oh, yeah. Sure. You will know her. Are you? Yes. That's that's one of my favorite books of all time for sure. I feel like it's drawn so much controversy, but it was such a fascinating read. And I think about it because I actually recently saw a documentary about like human evolution. It was like this BBC series and then it took me back and this book was I don't read a lot of nonfiction. But this was this was one that stands out for me. It's a it's a pretty easy read for nonfiction like you. He you will know her. He has a pretty unusual gift for for making it like for making the narrative compelling even though he gets it to some pretty thorny stuff. It's a pastry right? Yeah, it's a pastry. I didn't know he was controversial even. What I've heard is that it oversimplifies maybe like evolution in some sense, but like that's kind of what I need because I'm not like an expert. Like I need the I need the story, the juicy story. For sure. I mean, that's like it's such an easy way to critique something. You know, it's like, oh, the well, obviously if you make something that's one of the most popular books in the world, it's probably going to have to skim over some of the detail to make that work for everyone. It's a funny trade off. Yeah, it gives a lesser selling authors something to feel good about. Um, nice. And my final question that I always ask my guests is how we should follow you after the show or your business, whatever you want. You can give us tell our listeners how people should be following you for your brilliant thoughts or Anna the business for its brilliant advances. Of course, we already know that we can go to high anna.ai to sign up for a free two-week trial of Anna. So get to it, parents. Get we more podcasts listening time in your life. I'm always on LinkedIn and I post on X and I post about both like how the product is going, but also how we're building. Um, so that's what you can find me. We can just shoot me an email to lani.ai.ai.ai anytime. Nice. Thank you so much, Delani, for taking the time to share your brilliance with the audience and something else that is crazy. You might not even be aware how unusual this is. We did this episode without any breaks or retakes. And usually there's at least a few. Sometimes there's a lot. And this was just one continuous flow of conversation, which our editors have got a lot of. That's got to be the dream for a media editor. It's just like, that's great. I'm well, there you go. Yeah, really easy chatting with you. Maybe we can have you on again in a few years when Anna is a household name. I'd love to. Thank you for having me. It's been really interesting conversations. What a great episode, in a Delani Kahawala deal. detailed how Anna watches everything flowing into a parent's life, email, school apps, WhatsApp calendars, and proactively services what matters. She described that the hardest three problems in building Anna are creating a magical experience with no app UI to lean on, teaching everyday consumers to just ask, to have this just ask mental model of working with an agent and hitting a reliability bar far above what coding agents get away with. She talked about how Anna differs from turn-based tools like Cloud Code by being a long-running agent that works every minute behind the scenes, why the Evalon Improvement Loop is the heart of her product, and the brutal economics of consumer AI were a flat, $20 a month subscription has to cover always on token spend, pushing the team toward a mix of fast models, strong thinking models, and increasingly, open-source models like DeepSeek, Kimmy, and Minimax that have closed most of the gap with the frontier. As always, you can get all the show notes, including the transcript for this episode, the video recording, any materials mentioned on the show, the URLs for Delani's social media profiles, as well as my own social media profiles at superdata-science.com/1027. For, of course, episode number 1027. Thanks to everyone on the Super Data Science podcast team, our podcast managers on your Bravich, Media Editor Mario Pombo, Partnerships Manager Natalie Jaiski, Researcher Serge Massice, and our founder, Kirill Aramenko, thanks to all of them for producing another super episode for us today. For enabling, that's super team to create this free podcast for you. We are deeply grateful to our sponsors. You can support the show by checking out our sponsors' links, which are in the show notes. And if you'd ever like to sponsor an episode yourself, you can find out how to do that by navigating to johncron.com/podcast. Otherwise, please help us out by sharing this episode with other folks that are struggling with parenting or trying to build a AI product in this day and age. Review the show on your favorite podcasting app or on YouTube. If you write a review on Apple podcasts about the show, I will read that on air in a future episode. Subscribe to the show if you're not already subscriber, but most importantly, just keep on tuning in. I'm so grateful to have you listening, and I hope I can continue to make episodes you love. For years and years to come, until next time, keep on rockin' it out there, and I'm looking forward to enjoying another round of the Super Data Science podcast with you very soon.