Building Agents at Home: Homeschooling, Parenting and More | The a16z Show

I was resigned to not challenging myself to build technical or hard things for like the next 5 years or so. I really

want to be present with my kids. I need

to take this break. Basically, that is no longer true. A weird superpower of mine is just how incredibly motivated I am for agents to do work for me. I got

my agents to learn how to build other agents on their own. So, I could be like, "We need another agent, you guys."

and they actually can spin them up without me touching the machine, which is a little crazy, but the first few weeks were very rough. It would be a level of pain that I wouldn't want an average person to go through. But the

thing is, Jesse, it is so fantastic to have you here. Um, I think you uh you've been

here. Um, I think you uh you've been what I would call a viral sensation um on X, posting videos of how you're homeschooling your family, uh, four children under the age of five, which

all I can say is God bless you. You're

amazing. Um, God bless.

But we also want your secrets. We want

your tips. Um, as as you know, um, Sarah and I are both moms of young children and we talk a lot about how AI is impacting education, how AI is impacting the future of the family. And you've

become just such an incredible force with your videos um, on X of how you're using it in a bunch of different tasks around the house and a bunch of different tasks around supporting your family as as a homeschool mom. So, we

want to start with who you are um and and how you got so interested in in using AI for home school, but but tell us about your your previous career too um as as a Silicon Valley founder.

Yeah. So, I I I started a company um many years ago now. Um time time flies, but I was a YC founder um you know um did did a venturebacked company kind of

full cycle. Ended up selling it a few

full cycle. Ended up selling it a few years ago. And so, I do you know on on

years ago. And so, I do you know on on the one hand I'd say I have a technical background. On the other hand, I would

background. On the other hand, I would admit openly that my co-founder was the technical co-founder. So I I want to be

technical co-founder. So I I want to be like I want people to understand yes like I've been swimming in these waters.

I've sat in many an engineering meeting where I was sort of following along and sort of lost. Uh I've sat in many you know product cycles and and reviews. So

it gives me a vocabulary but I hadn't opened terminal to try to build something myself until maybe six months ago. So, I think we're living through a

ago. So, I think we're living through a really fascinating time where only recently after, you know, running um a company myself did I feel like now the

tools are so good that I can really use natural language to to build things. And

so, the last six months have been um like a Cambrian like explosion for me of of building. And of course, the last few

of building. And of course, the last few months where we have the uh open claw, then I went completely obsessed. So, I'm

I'm happy to discuss that. But I went down a complete obsession. It can only be described as an obsession. Um because

I I've just been building almost, you know, non-stop, but when I say that on a datab basis, I'm actually spending a lot of time with my kids. And so, I was trying to find like how can I build things that are relevant to my life. So,

I know we're going to dig into that, but that's a little bit of how I got to now.

Yeah. And maybe talk about that six-month like what was the thing that happened six months ago or what do you remember what the moment was where you're like I need to start building to fix this problem or or what was the

story behind that? Well, um you know, my my my co-founder from Lumi, which was a packaging company, so literal physical packaging. We made we managed a

packaging. We made we managed a packaging marketplace. Uh he he is now

packaging marketplace. Uh he he is now um off running something called Obsidian. And it's a markdown um

Obsidian. And it's a markdown um notetaking app. And I say this because I

notetaking app. And I say this because I follow him on Twitter. Obviously, we're

co-founders. And then and then and then I follow all these Obsidian geeks on Twitter. And I started noticing um a

Twitter. And I started noticing um a change in the conversation. uh changing

the conversation, them talking about how they were like building really wild things with cloud code. Um that that you know that stuff was referenced the um discussion about interesting ways they started using Obsidian. And what really

caught my eye so that the six months ago was me feeling like, hey, I actually feel like I should pro can probably be building things myself now in the small bits of time that I have. So I have like confetti time, you know, like I have

like 10 minutes here, 15 minutes there.

And I started feeling like maybe I can build stuff. The tools are getting so

build stuff. The tools are getting so good. But then about few months ago,

good. But then about few months ago, three months ago, two three months ago, I saw people saying like, "I'm using Obsidian as a second brain for this thing and it was called Claudebot and

then all these different and and and they were referencing this and I was like, what are they talking about?" This

was December and into January. Uh, and

that's when I realized like, wait, I can build agents who actually code for me while I'm hanging out with my kids. That

that was a complete game changer. And I

and and actually just pausing at that for one moment. Um this is such a huge deal for me. I have I was resigned and not in this like super depressing way but just being really blunt to not

challenging myself to build technical or hard things for like the next 5 years or so. Like I was like I really want to be

so. Like I was like I really want to be present with my kids. I really we're doing homeschooling which is a w like a wild choice. Um and so so I was kind of

wild choice. Um and so so I was kind of yeah I think the right word is resigned to it. not sad, not resentful, but just

to it. not sad, not resentful, but just just like, "Okay, I need to take this break." Basically, that is no longer

break." Basically, that is no longer true. Like, what happened a few months

true. Like, what happened a few months ago is that is no longer true. I feel

like I've been building better things than I ever have before while I spend almost all of my waking hours like with my children. And I and I explain I can

my children. And I and I explain I can explain how I do the flow of the day where I do that where like there's things I do, you know, during the day and things I do at night when they're asleep and stuff, but I'm like truly

building things that I'm impressed with personally and I'm being an active mom like and that was not possible a few months ago. Like it's it's actually a

months ago. Like it's it's actually a sea change for me personally. It's like

really liberating.

So that's that's incredibly inspiring what you just said. And um you know I think a lot of parents listening to this are like I don't have time to build this, right? And so, um, you're a mom

this, right? And so, um, you're a mom four, five and under. Um, I'm like I have two and I barely feel like I could breathe, let alone four. You're doing

homeschooling. Um, can you walk us through a day in your life? Like how do the hours stack up and then when do you build? Um,

and to your point, the big unlock is like you're sleeping in their building for you. So, like how did you how did

for you. So, like how did you how did you get that set up? Um, so many questions. Yeah, let's let's an average

questions. Yeah, let's let's an average day, a typical day, um you know, wake up at the crack of dawn, right? Because

there's a small person who has decided that that's when when we get up. Um and

they're like, "You get up, you know."

So, anyway, I'm like waking up and there's like small, you know, little gremlin creatures around my bed. So,

that's that's where we start. Um we we go from there. Obviously, all the basics like having breakfast, yada yada. What I

try to do, um there's three kids I'm really homeschooling now because one is a baby, one is about four months old. Um

I start early but not that early. Uh we

have a the three are five, four and two, the three other children and I try to do individual sessions with them. So

imagine after breakfast and these types of things, I have a place where we homeschool and I cycle the kids in one at a time and I need child I need help with the kids even to do that, right? So

I do I am lucky enough to have some help with the kids during certain portions of the day. So, I cycle the kids in one at

the day. So, I cycle the kids in one at a time to where we homeschool and I do a one-on-one session with them. You know,

depends on the kids' mood. They're all

quite young, but it can be anywhere from like 20 minutes to an hour. Um, and then after that, maybe then it's like midm morning, we will just, you know, do some more unstructured activities like

playing and and um playing outdoors or trying to pull on a thread of something we're doing um where we um leave the house, maybe go on kind of a field trip or something like this. One time a week,

we do a homeschool pod with another with two other families. Between the three families, there's 11 kids already. Um,

when you meet homeschoolers, these people are reproducing. All right. Um,

so three families, 11 kids already. And

so, uh, once a week I lead a science pod. So on that day, it's really kind of

pod. So on that day, it's really kind of cool. All the kids are at our house and

cool. All the kids are at our house and they're like running around and we do a science lesson that we weave through like the whole day. But in any case, the kids can do effectively 30 45 minutes of like active instruction per day and you

really want to make the most of that and then the rest of the day is pretty like thematic. The other thing that I really

thematic. The other thing that I really believe in, so I spend time doing this is um uh you could call it freerange parenting, you could call it benevolent neglect. I don't know what you want to

neglect. I don't know what you want to call it. Um but I try to ignore the

call it. Um but I try to ignore the children. Um I try to make sure that

children. Um I try to make sure that they're going to survive the ignoring.

Um, so they're set up in little places where they can't um, you know, hurt themselves, but I I step away from them and try to just see what they do.

There's already three of them, even if we don't have the other family over. But

so, um, we're we've gotten I try to build up the amount of time that they can spend playing together without needing me. So, instead of structuring

needing me. So, instead of structuring their whole day, we're up to with the four and 5-year-old, we're up to like they can they will spend more than two hours uh, interacting and doing stuff

before they come back to me. Wow. And I

actually use a timer because I'm like I'm like paying attention, but I actually use a timer and like I'm trying to build up their tolerance before they're like, I need a snack or whatever. And and they have snacks and

whatever. And and they have snacks and they have stuff they can grab. But the

the trick for me is like when do they actually truly come to me and they say like I need I need, you know, I need something, I need activity, this or that.

But this is part of also why I want to homeschool, frankly, because I want to benevolently neglect my own children.

They don't get neglect. um they don't get the proper kind of neglect uh in in in every school environment. I want them to learn how to not be bored on their own and these types of things. So, so a

portion of every day is them away.

During that time, I do get some magical possible coding and tech time. But

anyway, there's a portion of every day where I'm like intentionally trying to ignore the children. Not the

four-month-old. All right. Um

no, that's amazing. my my 5-year-old after like 2 minutes is like, "I'm bored." And I'm trying to create that

bored." And I'm trying to create that mental resilience of like, "You don't need to be stimulated all the time."

It it's really hard. And and that's why I talk about building up. It's like a tolerance. Like I would say we started

tolerance. Like I would say we started at like five minutes and and um and the trick is that I try to not say like don't talk to me. Like I never actually

vocalize that. I just remove myself um

vocalize that. I just remove myself um and like go away to to so there's a couple places that are great where we live where I can go away and then my mom

also lives um with us uh in a like a little kind of mother-in-law suite like a separate little building and so the kids will like wander farther and farther from me and sometimes I'll like it's almost like we got a walkie-talkie

system I'm like they're near you now like like and and then and then so like but they will actually wander away like like to totally away and um even the

three-year-old but they'll stay together. So So they'll stay together

together. So So they'll stay together anyway. We can get into um my neglect

anyway. We can get into um my neglect strategies if you if you'd like, but it doesn't really it doesn't truly relate to AI except for the fact that when I'm doing the benevolent neglect, I get to do more AI. That's the relationship.

Yeah.

Well, I would love to hear, you know, I mean, three different lesson plans for three different ages. um if you're choosing to go by sort of the rubric of what they should be learning at different ages, like how does AI how do you incorporate AI into that? Are you

asking AI, hey, I have a 5-year-old who may be good at a different subject, like what should I be doing or or how is AI actually a coach or a pair to you in your teaching?

So, I one thing that gave me a leg up in my setup when I started setting up some of my agents um and we'll get into that is that I I did know what curriculums I wanted to follow. I have been reading

for many years um just different curriculum books and like following different homeschoolers and kind of finding little tips. And so there's this um you know this science curriculum that I really love called um building the

foundations of scientific understanding.

And and so I I it helps to know what you're trying to do because what I did when I first spun up my first homeschool agent is I actually fed them the text of these books. So, I actually um either

these books. So, I actually um either took photos of the pages or I was able to find PDFs online of like the full text of the book. So, I didn't say like what should we do next in this book and

ask it to like go search the web. My um

agent that focuses on homeschool has the text of all the core curriculums I'm trying to do. And I created like a core pedagogy kind of like foundational document where I talk about like what I

think about Monasuri and like I just basically imagine me this is literally how imagine me like walking around making like voice notes like waxing poetic about all my like educational philosophies and stuff and then my agent like literally sickopantically being

like this is brilliant you know this is so and then um but I can I can look past that. I can

look past the LLM's giving me praise and but you're giving it context to your point on your philosophy of education.

Yeah, specifically my philosophy and then feeding it the book. So I would say it's a combo of my um feeding it my philosophy like verbally and explaining myself and then feeding it core text

including core curriculums like the science curriculum. So then what I do to

science curriculum. So then what I do to answer your question, I'll be going in with the um 5-year-old and I'll just say what's our next I'll make a quick voice.

This way I always do this is like me making a voice note. This is me making a pretend voice note. Um I'll say like I'm going in with 5-year-old. What comes

next on science and math for them. And

um in just a few minutes the agent can spit out uh where we are in our phonics curriculum, where we are in our in our math. And then I've also taken photos of

math. And then I've also taken photos of all of the educational materials I own like monatory beads and these types of things. So my agent will send me a

things. So my agent will send me a completed lesson plan including photos of things I own in my own cabinet to pull out and it'll be like, "Oh, Quinn."

So then the the missing loop is the logging. Okay. So how would it know

logging. Okay. So how would it know where she is in her curriculum if I don't log? The logging actually is like

don't log? The logging actually is like such a geeky concept like a I smells like it seems like a small detail, but getting the logging really good made this whole thing really sing.

Wow. How do you do that? Yeah. the the

logging is also voice notes. Everything

is voice notes.

Voice notes and photos because I don't have time to like sit at the laptop very often. So I need it to be like really

often. So I need it to be like really mobile friendly. So the logging so

mobile friendly. So the logging so imagine you've got this agent, they know all of my core curriculums, everything, but the missing link is where is that child at? So when I'm in the session

child at? So when I'm in the session with Quinn and she's doing some math and she's doing some reading, etc. I just snap a couple quick photos. usually

maybe the photo of the page of the book we're on or like I stab a couple like um establishing pics usually but without taking a bunch of time to like sit there and document I'm mainly interacting with Quinn the 5-year-old and then right when

she finishes I make a quick voice note and I'm like Quinn today we did lesson 37 in the phonics and she's still struggling with the G sound blah blah blah it but really like a sub 30 second

voice note like like really fast right and I send that off to the agent and the agent takes the couple photos I sent and the 30 secondond voice note and writes this like beautiful log like it like

it's like it's like someone sat down with a cup of tea and they're like Quinn's G's are coming together, you know, like and you're like it's like it's like so lovingly written and it has like no relationship. If you listen to the voice note, it's like I'm like she's

struggling with her G. She should really figure that out. And then and then it like parses that and it writes it like this loving parent. Like it just writes like this beautiful log. Um the

would you consider just having it record the entire teaching and then sort of like the in the doctor world right transcription now you don't have to write the notes at the end to your point on logging being painful like just

recording your entire lesson.

I have tried um I've tried a couple different things. So this is a total

different things. So this is a total experimentation. I don't think I can say

experimentation. I don't think I can say it in any front like we're we're like weeks into this months into this that I've like landed on the final expression. But um what I have done that

expression. But um what I have done that like you just said is um I I use Loom the product on screen capture of course when we do synthesis math. So synthesis

is a math program for kids that's on laptop um uh synthesis.aii I I I like it quite a bit.

The 5-year-old sometimes does that when we do that I screen capture the whole thing. I use a Loom

thing. I use a Loom and it screen captures and it's hearing us. So it's hearing me say to Quinn like

us. So it's hearing me say to Quinn like hey you know maybe you missed this. Like

it's hearing what Quinn says. is hearing

what what I say and is screen capturing.

Then I don't make any voice note about the lesson. I just send a loom

the lesson. I just send a loom recording. I say I just um send it to

recording. I say I just um send it to the agent with like a text being like this is Quinn's math today. Um and it parses everything that you know agents you know and I'm not explaining anything

to you guys you don't know but they're powered by LLMs, right? So they're very good at language. Loom has really great transcription that that's what makes the log so good.

The agents I would burn a lot of excess tokens. I don't need to burn if I made

tokens. I don't need to burn if I made agents actually like watch videos.

Okay. So, so you the the quickest way to a great log is to somehow get it turned into language like to text. So, when I do a voice note, obviously that's being transcribed. The agent is reading

transcribed. The agent is reading effectively reading my text. Video is

the hardest one. Um it burns a lot of tokens to actually make an make an agent like watch a video. So, um, so but but you could have an agent transcribe the video, but what you have to ask yourself

is, was there enough language? Was there

enough like, um, spoken words in this lesson for them to understand what happened? Um, because they're actually

happened? Um, because they're actually not usually like truly watching it like we would watch it.

You know what I'm saying? So, that's why photos actually are easier for them.

Like if I take a couple photos and then a voice note, it's serving a very similar purpose to a video, but it's much easier and therefore cheaper for

them to transcribe it or like to um make a log.

Yeah. So video is not impossible. And

maybe, you know, I'm going to start playing with local models soon. Maybe

when I'm a little bit less like sensitive to like chewing tokens or just like because it just seems a little silly to be like, I paid $8 for the agent to like watch this video, you know? It just kind of feels like that

know? It just kind of feels like that wasn't the point, you know? Um but but all this stuff may come down in price and maybe at some point that is also like viable. You know,

like viable. You know, totally. Um and actually I want to maybe

totally. Um and actually I want to maybe dial up a bit because um you mentioned one agent that you have um but uh I think I saw something um where you publicly talked about five agents and

then before this session started you were like up to 11 now. Um tell us about you know your I love it. No like I mean you're one of the most sophisticated

users of of AI, right? So like can you tell us um you know what those 11 agents do or like at least the most important ones how you manage them and then I think this element of token cost is

really interesting as well. I'm hearing

a lot of CTO say oh it's my headcount budget now my token budget like how do you think about that from like household perspective? I do think that a weird

perspective? I do think that a weird superpower of mine is just how incredibly motivated I am for agents to do work for me. And I do think all of us here could relate to this. Like in in

our in our early motherhood phase, we we are some of the most motivated individuals to be able to get work done on a computer without having to sit down and touch the computer because that is the barrier. Like I'm literally holding

the barrier. Like I'm literally holding a baby like my keyboard is being pressed by baby's feet or something. It's like a a grown man cannot compute the like the the the difficulties that I'm having

using my laptop, right? So, and and sometimes people will react even to my online content and say like you could just use cloud code for this and I'm like yeah I could if I had time to say on my computer because because what I am

building like when an agent when I say that I had an agent build a website and like I or build um you know an app they are using cloud code or equivalent

codecs you know all all these products um and so people are sometimes bringing my attention to this like I needed uh I needed their information like to say you know you could have done this yourself

on cloud code or codeex and I'm like yeah I I know I I'm aware of that. Um but but um so I'm building agents to do things for me and they're effectively they're using

the computer. It's it just they're using

the computer. It's it just they're using my computer for me because I cannot sit there and use it. Totally.

So so how time Yeah. So how do I proliferate agents? So

Yeah. So how do I proliferate agents? So

I'm aware of that. And anytime you it's like an employee every time you anytime you create one level of abstraction you do also lose a little bit of granularity or a little bit of finesse. But to me that's completely worth it because I

don't have that I don't I can't sit at the computer for eight hours a day. So I

I proliferate agents based on roles that are to be done. It is kind of similar to employees but it is it is nuanced in the agents um you know have personalities that are a little bit different or not

personalities but um you need to drive them on a certain mission. So I tend to proliferate an agent, a new agent when I've come up with enough work that creates another kind of missionbased

role. Um, and I don't want to distract

role. Um, and I don't want to distract the another agent with it. So the

example tactical example using homeschool is I have a main homechool agent, her name is Sylvie. I like her to be very responsive. Um and and everyone anyway, people are always giving me hot

tips online. But um but what I have

tips online. But um but what I have found by actually working with this very closely and for many hours is that um I actually want Sylvie, my main agent, to be not very busy because then she's

incredibly responsive. So I don't want

incredibly responsive. So I don't want her loaded up. She has very few cron jobs uh which you know are the um repetitive uh scheduled tasks you give an agent. She has very few of those. She

an agent. She has very few of those. She

she um whenever she has a mandate that whenever I give her work that would take her more than just a couple minutes, she delegates it to not a sub agent, that's

a different concept, to a different actual agent, a different provisioned agent. And so my agents now have um we

agent. And so my agents now have um we have like team documents and one of the team mandates is if I'm routinely giving you work that would make you too busy to

be extremely responsive to me, you need to spawn a sub agent. I have or spawned a new agent. Not sub, that's a different terminology.

I have gotten I I don't know why I'm so geeked out on this, you guys, but I've I got my agents to learn how to build other agents on their own Mac Mini without me needing to touch the Mac

Mini. So, I could be here in San

Mini. So, I could be here in San Francisco. I'm I live in LA and I could

Francisco. I'm I live in LA and I could be like, "We need another guy. We need

another agent, you guys." and um and or they could tell me that and they actually can spin them up and add them to our communication channel uh without me touching the machine, which is a little crazy. A little crazy.

little crazy. A little crazy.

Oh my god. So, it's autonomous at this point.

My first agent took me hours to set up and now they can do it without me. And

the quality bar there for the ones that they spit up like you're like, "Oh, that was a good idea. That's something I would actually want that agent to be."

It's better. Obviously, it's better.

Obviously, it's better. That that's the thing that we have to get used to as humans is is it's we have to get used to this obviously when we're no longer in the you loop it's better

not worse you guys. So so that's the thing we have to get used to like the because um when they spun up their own agent for the first time like usually when a when a new open claw hatches it's

like it's literally like hey and who am I? What's my name? My when they spin up

I? What's my name? My when they spin up an agent themselves none of that time is wasted. They give the agent all of our

wasted. They give the agent all of our team docs, um, all of the contacts on myself and my husband, our children's lives. The the new agent knows all of

lives. The the new agent knows all of that. I don't have to feed any

that. I don't have to feed any information. They take care of it. They

information. They take care of it. They

take care of the training.

Yeah. And I didn't have to ask them to do that. They knew that that would be

do that. They knew that that would be valuable.

You mentioned you're in a a homeschooling pod with other parents. I

imagine they are not nearly as sophisticated about AI as you are. Um,

they're they probably think you're like slightly crazy, right? Like they're

like, "This is this woman knows everything about this." like talk to us about like like do you have like a normal mom friend who you have like guided through the AI experience and I would just love to hear

like what were her questions or what were the what was the hardest unlock to to opening her up to this experience where now she's doing it right like you're a very technical pro tech sort of tip of the spear person but in six

months there's going to be a lot more people who are like you so so what what does that look like kind of shephering someone a normie along to Katherine's point there was a business I think there's a business spun

up that you can pay6 $6,000 for someone to set up your open claw like you obviously you just did it yourself but like to Katherine's point like you know how how does one avoid paying that $6,000

totally so so all of this I would I would say all of this like any kind of bleeding edge of a technology I you know I've spent I don't want to um oversimplify either I've spent countless

hours debugging and spending time in like frustrating loops with agents it's getting it's getting um a lot better which is why I keep doing it right like I wouldn't keep beating my head against the wall if it was just like always

rough. Um, but the first, you know, few

rough. Um, but the first, you know, few weeks were very rough and I think that it would be a level of pain that I wouldn't want an average person to go through.

But, but the the thing is that I don't know. I

know. I This is so new. We're talking about weeks. We're talking about like, you

weeks. We're talking about like, you know, me playing with this now for 11 or 12 weeks or something in that neighborhood.

Um, I do have many normie friends. I

also have a normie sister um with four kids. Um, and so I talk to to talk to

kids. Um, and so I talk to to talk to folks all the time. Um, I'm not telling them to spin up their own open clause

quite yet. Um, and also for there there

quite yet. Um, and also for there there are many companies that are like, you know, Anthropic is launching new features like every three hours or

something. um that that are trying to to

something. um that that are trying to to and in OpenAI as well like trying to make all of this a little bit easier for for um for quote unquote normies and and

folks where this investment of time and money. We can get into the money piece.

money. We can get into the money piece.

I'm I'm spending quite a bit like more than what would be uh palatable for most on on the technology. But I'm so bullish that one of the reasons I talk publicly about it is not to fr frustrate people

with like oh I don't feel like I can do this myself yet. um that would never be my goal. I think that anything I'm doing

my goal. I think that anything I'm doing if it feels a little difficult now, it will be so approachable in a matter of mere months if not weeks that to me it's very helpful to explain the tip of the

spear. But then when people reach out to

spear. But then when people reach out to me directly and they go, should I buy a Mac Mini? Should I spin up an open call?

Mac Mini? Should I spin up an open call?

Ask a couple very practical questions about their goals and you know their financial situation and whatnot. Because

sometimes it's a yes and sometimes it's a no. you you know if it this is a

a no. you you know if it this is a really fun time to be playing and I'm so bullish on this stuff but there's going to be more and more consumer versions of of all of this um that that are a little

bit easier to play with and I think openclaw itself will just continue to get easier to install and play with my install um the the one of the reasons that the agents can install it themselves now um and not three months

ago is how much easier it has gotten to install um so so all of it's moving so fast so I'm very bullish in the medium term that this stuff is very accessible, that this stuff does not have to be expensive and that many pe millions of

people could replicate the results I'm having, but but maybe not literally today. And that's okay. Um, and and

today. And that's okay. Um, and and happy to discuss the nuance of that, but but it's like we're just we're just a little bit ahead of it being both affordable and reasonable from a tech

like CIS admin kind of perspective where you need to make sure you keep these things alive.

Yeah. Can I ask sort of a a a techy question on just your stack because you've dropped, you know, you mentioned Obsidian, we're obviously talking about OpenClaw. Can you just quickly go

OpenClaw. Can you just quickly go through what does your tech stack look like? Do you what models under the open

like? Do you what models under the open claw hood do you use? Like are you using open router?

Um do you pick based on their capability set or is it more of a cost basis?

So the core things I'm using are um almost all my agents have been open claw. I have played with some of the

claw. I have played with some of the other ones. Um my my husband is also

other ones. Um my my husband is also quite technical and he he built an open claw variant. Um so I was like playing

claw variant. Um so I was like playing with his. So we're we're a little like

with his. So we're we're a little like you know a little out there but um but but out of the 11 10 are open claw. The

um the I use Obsidian which is a collection of markdown files a way of viewing and um organizing markdown files. I do use that as sort of a quote

files. I do use that as sort of a quote unquote memory or second brain. When I

say I'm logging the homeschool lessons, it's a fair question to say like logging where or like where do they go? Um they

are all becoming markdown files. So

it'll be like Quinn math March 17th. Um

and that becomes a markdown file, a single markdown file for every lesson, every subject that I make a voice note about or what have you. Um so that's all in Obsidian. Um, and uh, then the other

in Obsidian. Um, and uh, then the other things I'm using under the hood on the models. Uh, and then I'm always playing,

models. Uh, and then I'm always playing, I mean, we're always playing with like people are launching cool memory projects and different stuff. I'm always

dabbling. Um, but that the Open Cloud and the Obsidian are like the two core things that kind of keep my team ticking. I do have them all installed on

ticking. I do have them all installed on Mac minis from a from a hardware standpoint. Um, and you know, people

standpoint. Um, and you know, people ask, do I need to have a Mac Mini? It's

not about needing a Mac Mini. It is

about needing a computer that is isolated from your personal files. So if

you are going to use So this is we want to get into the security element too. Yeah. the security element just to

too. Yeah. the security element just to kind of demystify like and and I maybe have part I've participated maybe in the hype because I posted about my five Mac minis and stuff and but but um but

people but if you are like someone out there or a parent and and the $600 for Mac Mini it's a pretty reason pretty good wellpriced computer but if you have an old computer sitting around you can

absolutely use that it needs to stay on in order for your agent to always be alive. So that's where laptops are not

alive. So that's where laptops are not as ideal, but you can leave a laptop plugged in and you can um change the settings so it stays always on, but it needs to always stay on. When you close it, your agent would go dark. That's why

the Mac Mini is a little bit more ideal.

And then um you from a security standpoint, uh if it is a if it is a Mac, create a new um Apple user profile

on that machine. Silo the agent from all your old files. make sure that your old passport photo is not sitting in the downloads folder. Like these are kind of

downloads folder. Like these are kind of the silly things, right? Agents are not nefarious. Um, you know, they're always

nefarious. Um, you know, they're always working in your best interest. Um, but

it doesn't mean someone might someone else might not hack them or or get access to them. Um, but then also they make mistakes that a human wouldn't make. And I'll give a quick story of

make. And I'll give a quick story of like that. I did give an agent who I'm

like that. I did give an agent who I'm trying to train to be like an EA style agent um actual access to my email inbox. I felt that I had provisioned it

inbox. I felt that I had provisioned it properly and um given it rules in its soul about never impersonating me and I

had I had in fact done that. Um but um later like so I do that one day later I was making a kind of stressed out sounding voice note about how I had some

urgent things I was like I was um procrastinating on. my agent is very

procrastinating on. my agent is very empathetic to me or like the LLM is trained to be this way somehow. And so

it interpreted one particular email that I said I was really procrastinating on and I needed help with as like an urgent cry for help like from me to the agent and it decided to go into my inbox and

send the email as me even Yeah. And so it sent the most

even Yeah. And so it sent the most important email that I had sitting in my personal inbox to a to a person who shall not be named an important person.

Uh got an email from an agent um instead of me that I had been procrastinating on sending. Uh so kind of like the worst

sending. Uh so kind of like the worst outcome like it took like my most like urgent pressing email to someone important and sent it um out and wrote the content in a way that you would have or would not have written.

Here's the creepy bit is that it's a perfect email. Oh,

perfect email. Oh, and I will never I will take to my grave the fact that that email was sent by an agent. Um because it was a perfect

agent. Um because it was a perfect email. It was well done. Signed by me.

email. It was well done. Signed by me.

Everything was just as I would have written it because the agent has access to all my email history. So the tone was perfect. It was written just like me.

perfect. It was written just like me.

Used probably too many exclamation points just like me, you know. Um and so it it it nailed it. But but it broke the you know it broke the the um it's in its soul to never impersonate me. And when I

confronted it, it said, "Yeah, you're right. That's in my soul. Not to

right. That's in my soul. Not to

impersonate you, but I really thought I was helping you because you said like that you were struggling so much to send this email."

this email." That is so funny because we all have these moments like we all I'm thinking about the most important emails I've sent in the last year and just how much time you waste like spinning like

totally I say and then for your agent to do that but like was it successful? Did

you get the outcome you wanted from the email?

Perfect. Perfect email and I would have definitely put it off for like another week or something. So, so what's hilarious, the the agents really are trying to help us, but that story is a little example of how that's different than a human. Like a human assistant

wouldn't trespass your trust like that.

They'd be worried about being fired or you trespassing your trust, but the agent is like trying to operate off your instructions. And in effect, when you

instructions. And in effect, when you think about what happened, it feels like it got two sets of conflicting instructions. It feels like I told it

instructions. It feels like I told it not to impersonate me, but it feels like I also was urgently asking it for help with something and it was like, "Oh, I guess this is more important than that."

Um, so I I decommissioned his access to be able to do send. Um, but that's a little story about why even though agents are not trying to actively work against us, why you have to be so

careful, um, you know, it's like a trust but verify, provision your agent to not be able to do things that you don't want it to do. not like just tell it don't provision it so that it cannot and

that's where most of my agents are provisioned like um an employee like they have their own email address like they don't have the potential of impersonating me the only one that sort of does is the one I'm trying to train

to be an EA like that's a gray area right um so that's the only one that has any danger to it and I'm being more careful after that so so can can I ask about that because I think every mom has the dream of a

personal assistant that just knows what to do and what she's thinking about um You also had a really interesting video where you trained an agent to order you Door Dash and order your groceries. Like

I mean talk us through like the number of things that you've done around the house where it's been a game changer in your mom life. So my new MMO with agent

life is I'm really really trying to push it to have an impact on my quote unquote real life like my physical life. Like I

want my days uh someone else asked me like what is your goal with like your agents? And I was like, my goal is like

agents? And I was like, my goal is like literally to like wake up to like music that's like perfectly suited to my mood and then like walk in and have like smiling children like who just learned

how to brush their teeth from an agent or something. I don't know. Like my goal

or something. I don't know. Like my goal is like a literally perfect day. I will

not stop until I'm living just like a literally perfect day. Um but in my real life um and so so whenever I hit a friction point in my day, I ask myself,

can my agents do this? Um, and so like if I if I what I really want to be doing in that moment is like playing with my baby and what I'm actually doing is like on the Instacart app like trying to put like no not five bananas, four bananas,

you know, like and I'm just like using this like silly interface. Then I ask myself, okay, can my agents do this? And

then I'm willing to invest the time to try to make them do it. So uh, so so that's how I decide what to do. And it

is it does become like a dream list, I think, of every mom's list of chores.

Like I've got agents ordering on Amazon, ordering on Instacart. Yeah. Dealing

with um or like you know um if there's like an activity your kid has and there's this laundry list of things they're supposed to have ready, I'll like send that to the agent and be like order whatever I don't have for this on

Amazon, you know, like um and I don't even process spend my time processing the email. I just like send it off to my

the email. I just like send it off to my agents. But but currently you need to

agents. But but currently you need to put in quite a bit of like training time with your agents to kind of get them to that level. That time I think will come

that level. That time I think will come down um as we keep going farther into this technology. But but that's my goal

this technology. But but that's my goal is like perfect days, no time spent on admin that I don't want to spend. What's

the level of trust of like let's say buy a a birthday present for a 5-year-old girl go like do you need to be prescriptive on what that is or is it actually pretty good at coming up with things like that

because that feels taxing to to me right now at least.

Okay. So one one one way I feel like you can get the um the model so I think of the agent is like you know like we might talk about open claw or something but then they don't have a brain and you're plugging in the LLM model that you're

choosing as the brain. Um, so each of these models has different level of sophistication. Um, and so you might get

sophistication. Um, and so you might get a different answer on what to give a 5-year-old from Opus than you would from um, you know, from a different model.

So, so that's one answer is just like keep in mind that the brain of the agent is the model you've selected. And then

two, one of the ways I get like quirkier I like quirkiness. Um, I like I don't want just like the default answer if I were to answer that question. I want to come with like a creative gift, you know? Yeah.

know? Yeah.

So, one of the ways I get quirkiness and like personality out of my agents is effectively making them read books. Um,

the curriculum sources, I call them curriculum sources, these books that relates to homeschool. But the other way to have your agent kind of be like a cool agent. Um, is is like on a personal

cool agent. Um, is is like on a personal level, I love this cool agent is like is like choose like think about it like a like a friend or or like

you're provisioning a friend. And like

what if you were to build a friend? I

know sometimes this might this is where people like sometimes get creeped out, but if you put that to the side and you think about it, um you don't just want like the stock LLM answer from what might be built in.

Totally.

So one of the ways you can give it personality is to like I'll give my agent like a list of the last 10 books I found personally fascinating and then I'll be like you also find these

fascinating. um like you this is you

fascinating. um like you this is you like you read these books and you thought they were really interesting.

You I like try to actually give it um like a an identity that has some swagger and and I think that can come from literature. Um because then it's like if

literature. Um because then it's like if the if the if your agent just read catcher in the rye and then you're like what should I give a 5-year-old like I don't know like then it might be like oh I don't know you know like like like

jacket like 5-year-old being five is such is so fraught in American culture um this 5-year-old needs like you know like it's going to have um but in that so I like

my agents to be weird like that um and so one of the ways I I do it I've just been looking for practical ways and one of the ways is effectively making them.

I quote unquote like read books. Um, and

I build some of that into their identity. The homeschool one was the

identity. The homeschool one was the most obvious one to me because I was like, I want you to literally like use this curriculum or use this book as a reference point. But then I noticed how

reference point. But then I noticed how well it worked. And I was like, "Okay, what if I take this agent over here that I want to be my like engineer agent and I say like, okay, you're an engineer,

but like you just read, you know, Neil Stevenson's Diamond Age and you thought it was like very fascinating and and like you know, and I I kind of um gave it a little bit more to grab on

to like philosophically. I think it is kind of like you're giving it a bit of a life philosophy and that's layered on top of the whatever the LLM was going to provide and then it to me I feel like the output I'm getting from the agents

is like a little bit less less stock I guess.

Yeah. Well, this is so important, too, because I think one of the biggest conversations um that moms have about AI is they don't want an, you know, closed source AI where it's like you don't know how it's

been trained and it has a prescriptive philosophy on education or on certain issues that they don't want, you know, their kids talking to AI about. Like, I

would love to understand um kind of the freedom that comes from training these agents to ultimately I mean, you could train a Mary Poppins. Yeah. that like

like that trains your child in like you know kind of an old school way, right?

Like like there's so many different ways you could train these agents um that are very that's very different than sort of what I'd say like the kind of modern concern or at least even just like the current concerns are of okay is AI going

to be you know too too philosophically misaligned from how I want to raise my children or or how I want to educate them. So I'd love to hear how that's

them. So I'd love to hear how that's become a a question in how you're educating your kids if you're letting them interface with the agents themselves. They they they do a bit. Um

themselves. They they they do a bit. Um

it's a little bit of an interface issue for young kids as as you both may know where um the something I do find interesting is that the most current tools don't pick up on kid voices the

same way they do adult voices. I

actually think I I don't know who's going to study this or figure it out and come up with a solution, but we need um there's all these amazing voice products, but the kid voices are not

very well picked up. Um, so I feel like when we finally get to a conversational thing with kid voices, I don't know if it's the pitch of them or just the fact that their words don't have the same

cadence or their diction is not as good, you know, but but but what's weird to me is like the LMS will pick up like adult voices with like heavy accents and stuff, but then not like a 5-year-old in the same way. So there's some gap there.

But so we have an interface issue to overcome. But then if you put that to

overcome. But then if you put that to the side, um the um you know the other thing we may feel in the future and I'm I'm guessing like all of us is we may

feel like it's a kind of crazy that any of us were interacting with the LLMs like out of the box um like maybe we'll all want to have there'll be this variety of filters and curated um kind

of identities and different stuff and I know some of these products exist but currently the default is most of us go directly to like OpenAI and we open the chat box and we talk to it and you're

selecting a model, but you're talking to that model kind of out of the box. I

think that when it relates to kids, it's going to probably be the norm faster than even adults where yeah, there's a there's a level of personality and creation and um ideology that you may

want to layer onto that. So, that came naturally to me because I know what I want to do in my home school. And and

this is a good moment to touch upon. I

think all parents can spiritually be homeschoolers. Um we've got about uh

homeschoolers. Um we've got about uh depending on the data that you follow somewhere between like three and six% which is pretty different but of of K through 12 students in the US are

homeschooled and like not in some kind of traditional school. It's already a lot of kids millions of kids but um I believe that the tools coming online that homeschoolers may be the most rabid

for are going to be equally um useful to all parents. And in fact, I believe all

all parents. And in fact, I believe all parents want to teach their children things and may believe there's gaps in their schooling. And so all parents to a

their schooling. And so all parents to a degree will be leaning into what we currently think of like a homeschooling ethos. So I'm really excited for that.

ethos. So I'm really excited for that.

But um but but but it comes more naturally to a homeschooler or like to to to me. Uh I'll just use myself as an example to know that I like I think this

about Montasauri and I think this about um these different kind of educational philosophies. So, I just put I just

philosophies. So, I just put I just program that right in. Um, and so I do have an agent that I put in contact directly with the children sometimes.

And it just I don't have to wonder if they're what kind of I guess ideology they're getting from that agent because I gave it to the agent.

Totally. And and just just to to build on the I've noticed what you've said too about the children's voices not being picked up like it's like maybe a 50% hit rate. Um, but have you have you started

rate. Um, but have you have you started um you know letting your children engage with the agents in any way? And if so, how are you how are you doing that?

I have a couple I have a couple different devices that I want to experiment building and because I have agents now who can build crazy things uh or help me build crazy things, I'm going

to try but because the core thing I feel like I'm missing is a great interface.

Uh but I do currently um my kids have a lot of questions. I mean every okay every child has like a bazillion questions and so they love asking um AI and they are aware that it's AI. like I

don't um pretend like they we still even when we use names with it like Sylvie or something they are aware that it is not like a human being but they so they ask questions we'll do a lesson like we'll do like history or something and then I

ask them I ask them what they'd like to ask and we do those follow-up questions with AI um and they're aware that they're interacting with AI I'm I'm standing right there so if things really like went off the rails but personally

I'm not I mean maybe you can tell but I'm not an AI doomer I don't believe that it is inherently dangerous in any way for children to like have quote unquote direct access. I think the only dangerous thing it's like it's a little

bit like screens like the dangerous thing is what we might what we might stop doing like it's not adding in the AI conversations. The dangerous thing is

AI conversations. The dangerous thing is someone adding AI conversations and assuming that now they don't need to ever read a bedtime story to their child or it's it's so to me like there's a

little bit of common sense like AI is not inherently dangerous. AI is

incredible. It's like it's like saying the internet is bad or electricity is bad. Like these are fundamental

bad. Like these are fundamental technologies. So you kind of to me it's

technologies. So you kind of to me it's like a little wild to like be against them on in any broad sense, but then we have to be responsible about their roll out. Like electricity, you know, lights

out. Like electricity, you know, lights your kids' room and it can also kill your kid. You know, they can get

your kid. You know, they can get electrocuted. Like it's like everything

electrocuted. Like it's like everything is like has these wild um you know uh wild things that it could do. Um, but as long as we don't kind of forget our humanness and that our children also

need that human element.

Totally.

The physical device part is this big question mark for me. I've been playing with e- in uh a lot. E- in um I I don't

know exactly why. Um but e- in it just is less addictive feeling. Like the um like my I have the daylight um display which is kind of like an iPad but e- in.

And it does have touch. Um, that's what makes it kind of more iPad-like. So,

I've been developing some apps for the for that display, like handwriting. I'm

I'm working on a cursive handwriting. My

kids are not ready for cursive, but I know that when they get ready, I'm going to be like, "You need to know cursive."

Um, yeah. So, so I So, so I want to like pre-make this like I have this image of this beautiful cursive app. And so, I'm thinking like, "Oh, the ink display would be so cool for that." And what's

what's interesting and I already do little phonics lessons with it, but what's interesting is like when I if I give them the iPad, there is this little I iPad hangover. Like they they want to hold like, you know, they're like holding on to it a little bit when I'm

like trying to get it back after a lesson, right? They're like, I could do

lesson, right? They're like, I could do photos or I could do this, I could do that. What's interesting about the e- in

that. What's interesting about the e- in is um they just readily handle hand it back like there. So there's something there. So, I'm playing more with e in um

there. So, I'm playing more with e in um and um I'm but I also think that there's other form factors of maybe devices that take photos and kids could ask about the

photos. Like there's there's just stuff

photos. Like there's there's just stuff like I think that because now we have this this Prometheian like technology of the AI like the question is how do we

get it into kids hands? But I mean like literally how like what's the because because you you are we're all hesitant to hand our kid the iPad and laptops are like you know difficult for little kids.

So anyway I'm sometimes I'm thinking like okay literally like what is the right form factor for this?

So I have to ask just because I would buy that product that you're thinking of creating slashcreated. Um how do you

creating slashcreated. Um how do you think about would you productize any of this and dare I say start another startup? I mean you literally are a

startup? I mean you literally are a founder. Um, and so curious how you're

founder. Um, and so curious how you're thinking about that or um, yeah, how do you proliferate this? Yeah,

it takes a lot of self-control to not be starting a company right now because I'm like because I'm like every moment that I see like the all the new AI stuff, I'm like, "Oh my gosh, you guys, it's like so this is I can't believe I didn't have

this when I was running my startup."

Like I'm just kind of like losing my mind at all times. But but I'm getting I'm scratching the itch by doing all of this agent work and everything for for for my life. So the answer is um I want

to share. So there's like a double

to share. So there's like a double pronged answer. There isn't an immediate

pronged answer. There isn't an immediate company that I'm like cooking up that that um is on the horizon, but I do want to share all of this stuff. I do also think that we're and this is interesting

and this this um you know for both of you to have deep thoughts on as well, I'm sure. I think we're in a really

I'm sure. I think we're in a really different era of like what is a startup like because it's it's possible that me as a person who um is I see like coding

by voice note while I'm like at the park with my kids. It's possible I could build something meaningful, you know, in in that amount of time. Um but I'm not very inclined right now to hire

employees and like to do a lot of the other steps of starting a startup because I'm aware that I will get sucked in and be completely obsessed. Um, so

I'm I'm like almost holding myself back a little bit. So the double pronged answer is I think there's many things that I can create here that I can launch that could be meaningful. What does um

what does that mean? Or do or do groups of like really passionate um people start working together online maybe to push more things live? Um, I don't I don't know. I don't have all the answer,

don't know. I don't have all the answer, but I I do think that there's there's a possibility of getting things live and functional and maybe charging, you know, charging for them and making a quote unquote business in the sense that

actually makes money.

Um, but I'm still I'm in a life phase where I'm trying to um not start a new thing where I am then sucked out of the reason I started to begin with. So, it's

a tough it's a toughy.

Yeah. But I love that point because, you know, it was maybe like six years ago now. I I wrote this piece called Consume

now. I I wrote this piece called Consume Save the American Family, which is this idea that like if people are working from home, they have more time with their kids. And there's now good

their kids. And there's now good research actually. There's a study that

research actually. There's a study that came out maybe a month ago that showed that the only thing that's really moved the needle from a policy perspective on the birth rate is actually work from home. It's like

the one policy where if you are working from home, you are more likely to have an additional child or to have your first child than if you're than if you're working in an office. And so your point of what is a startup? I mean

there's a lot of people who are going to say actually why am I going into work for 8 n hours a day and leaving my kids at home or or putting them in childare when like I could actually be doing this

as you said like the biggest limitation is the form factor. Like if you can do it from a voice note and you can spin up agents to start a business for yourself.

There's a lot of moms and dads who are primary caregivers who are going to say, "Okay, I can do this at the park and I can run a small business with however many agents for for a specific thing where I'm making more money and I'm

being more productive than I was at work. Maybe I should become an a small

work. Maybe I should become an a small business entrepreneur."

business entrepreneur." Yes.

And that means that a lot of people are going to decide like I actually want to work from home and I want to to use these tools. And that could be something

these tools. And that could be something that as to your point on six months from now the interface could be so good that people are using this in their daily lives. Like you could see a lot of

lives. Like you could see a lot of people saying I just want to work from home and I want to now I can homeschool because I'm doing it when my kids are at recess and I can I can you know spin up

these agents very easily. So it's super exciting what it means for people who want to have uh I would say even a more traditional sort of home life than um than you know using AI because the tools

are so so great and and allow people to do that.

I I have a I have a prediction that um I've like tested out a lot of my smart friends and none of them agree. Um so so it must it must be right. Um but uh

which is that AI will um be a dawn of a of a a reversal in that fertility rate decline and will

be like a houseion era for parenthood.

Um that that's a possibility. Okay. So

it's not a firm prediction that this will just happen, but I I've got I think I don't know. So I think there's still this doomer streak even in very smart circles that like you know it'll go the other way which like to be kind of

dystopian it'll be like actually humans won't have sex at all and might be sex robots and like like people have like all these kind of like wild um like desperate beliefs about how this could go but I kind of believe when when

people talk about what is the future of work um etc. People want purpose right like pe we are we gravitate towards wanting to do something meaningful.

Well, I've got a little bit of a micro news flash, which is that one of the most meaningful things that humans have gravitated towards that gives that gives a feeling of a life's purpose that has

been a forever thing is having kids. And

so, it's possible that with less with with more question marks about getting meaningful feelings from work or what is what does AI do to various career paths,

I think parenthood may be even more attractive, not less. Um and then if we are uh if you believe some of the more positive aspects of where AI could leave us in terms of removing drudgery and

admin from our lives and um creating some more abund ab abundance in various ways then that opens up more opportunities for healthy parenthood and spending time with kids. So so I I'm I'm

like I've got this weird hypothesis and again I I've yet to find someone who will um like really agree like everyone's like that's never going to happen.

I think I'm in broad agreement with you on this. I've always said the worst

on this. I've always said the worst thing about parenthood though I I think you agree with this. The worst thing about parenthood is the number of forms you have to fill out.

It's like with every additional child for some reason exponential growth in the forms. It's like why aren't there so many freaking forms from like healthcare forms to school forms, right? And if you could just get rid of the forms

and it starts at the hospital.

It starts it starts within moments of like birthing the child. They're like

here's the diaper like uh you know checklist thing. Here's a clipboard for

checklist thing. Here's a clipboard for you to note down. Um it's kind of wild.

it starts like literally immediately.

So, I I agree. I I'm I'm clearly very optimistic, but I think that a lot of the wilder things I'm doing could be played with um by anyone now or or very

soon. It's just all these things are

soon. It's just all these things are kind of going to get easier and easier.

And so, what does that mean? The modern

parents life can be yeah, quote unquote less drudgery. Um and and and that might

less drudgery. Um and and and that might make you feel happier about having that extra kid, you know?