This AI Tool Lets You Build Apps Faster Than Googling | Amjad Masad (Replit)

I think if you were to work in TCH I you have two radically Divergent ways to think about it if you want to be a programmer and have job security I think

you have to pick something as close to the metal as possible for example NASA will not have JavaScript generated or like GPT generated JavaScript run the

Rockets right or the Tesla cars or what have you so if you want to work on embedded systems using C you have job security for 50 years the other

direction is you want to get really good at being a product person yeah and being a jist being a designer a maker pm and that's because I think this like full

stack developer that's the thing that's most at risk right because it's the thing that's most represented on on GitHub it's the thing that AI is most good at it's the thing that's already somewhat automated like people using

repet and cursor and others you're already sort of automating a big part of it so I think the need the demand for Engineers like that I think will will go down and instead companies would look

for generalists that can go from ideation to production code by using Ai and I think they're going to be a lot more highly leveraged and again also if you're already in Industry I would run

in one of those directions don't stay in the middle I think the middle is is going to get squeezed okay well welcome everyone my guest today uh is amjad CEO of replit uh replit has 34 million users

and just made his AI agent uh free for every want to try so super exciting really excited to talk to amjad about why this is the most exciting time to learn how to code how rep is different

from other AI tools and how AI agents will transform product teams so welcome thank you it's my pleasure to be here excited to share uh more with you all right so let's talk about how to learn a

code with AI you know like a while ago like Jensen Juan said like kids shouldn't learn to code because AI will just do all the work for them but you actually have a law under your name that

says otherwise okay talk more about that yeah my my view is that programming is evolving and you know when Jensen says something like that I'm not entirely

sure whether he means that we shouldn't teach programming like we used to or the idea is that we should adapt to how programming is taught so I think the act

of programming with AI is significantly different than sort of sitting down and breaking down the problem into components and writing classes and figuring out how to wire these classes

and figuring out what packages to use and in a way programming with AI I think is a more pure form of programming because you're not dealing with especially in rup because we automate a

lot of the stuff you're not dealing with the minutia not dealing with the setup with things that are really they don't they're not about building they're kind of chores right so a lot of the chores

go away and what's left is you and your creativity and I think that's the most exciting thing about programming and so the law you're talking about is uh my observation is every six months we have

a new model and every model is getting better at coding and that's been the case since uh you know gpt3 because there was this observation that coding

is uh makes models more intelligent at everything else and then you know co-pilot became a huge business and it turned out that okay this is a product

Market fit for this technology and they started optimizing for coding and so you know GPT 4 4.5 clots on it

was this huge jump and now we have 03 mini just come out R1 these new reasoning models which they're really good at programming in in certain ways better than the others and other ways

you know different I think still getting better but you know this basically six months on the dot like you know CL had a claw 3.5 son it was like it was like you

know June maybe and so December you had by December you had like you know deep seek V3 and an o1 preview and all of

that stuff so every 6 months coding becomes easier to start with and more powerful so both the floor is becoming

more accessible and the ceiling is is being raised you can do more things with AI therefore every every bit of skill of coding or programming that that you

learn is going to take you further every six months y makes sense some skills might get outdated for sure but N I think that the just learn just

continuously learning a little bit this craft the skill is is going to turn exponentially more on your investment this episode is brought to you by vanta whether you're a startup founder

navigating your first audit or a security professional scaling your GRC program security has never been more critical or more complex that's where Van comes in businesses use Vana to

establish trust by automating compliance needs across over 35 Frameworks like sock 2 and ISO 271 Venta can help you start or scale your security program by

connecting you with Auditors to conduct your audit and set up your program fast plus with Automation and AI throughout the platform vanta gives you time back so you can focus on building your

company join over 9,000 global companies like alassian quora and Factory who use Venta to manage risk and prove Security in real time get $1,000 off at vent.com

Peter that's V n.com Peter for $1,000 off now back to the episode yeah and I love how like you know it's made it so that you can get the reward right away you can see the

fruits of your labor I mean I have to give you credit man like cuz even before AI I was using a rep ret and you know as just like a PM right soone was not super technical like it was such a pain to

actually you have to install this Library try to figure out like which library to install and do all this stuff but rep made all that easy even before Ai and now but even with that like I

tried taking your 100 days of AI course I think it was like a like 100 days of python right yes 100 days of python and like I tweeted about it and then I only got to like day seven because you know

life got in the way and like you know it it just felt like very removed from the the stuff I wanted to actually build so I guess like how would you recommend yeah I I wouldn't recommend 100 code uh

100 despite no not right now yeah yeah so so like how would you recommend like let's say like a total beginner like try to learn how to code like how should someone get started now I would start

with something like repet agent so you put in your idea you in describe in natural language actually I can start sharing now I think is a good time to

kind of go through once you log into ret the first uh thing you'll see is like what do you want to build today and and

here you can put a prompt as you know small and direct as you want it to be or you can get really creative and you know product managers really like to write

these PR you sophisticated prds so Peter you know you know you should give me an idea just so we can the audience you know doesn't think we're sort of cooking

this and this is the real deal why don't we do some sort of a okay so for example I have problems tracking my nutrition like like I I want to eat more protein

every day and like using my f pal sucks CU like so many ads and stuff in there can we do something like a basic nutrition tracker I want a basic

nutrition we can do improve prompt and see see what it comes up with a web based nutrition tracker monitor daily food intake food entry system MC

nutrient daily nutrition summary progress okay great let's go all right that that that was the PM part you just skipped that part yes yeah exactly and so now we get go

into this sort of Lobby experience where the agent is you know takes our prompt is constructing a plan behind the scenes

and any second kind of it's going to give you a plan so it says it it picked a stack for you it says I'm going to use streamlet for this uh because I think it

sort of inferred that it is a you know get data and visualization heavy uh application you can change that so I can just say no I want it in in react and

I'll propose a new plan but let's go with this and see let's go with a recommended solution and see what it comes up with yeah that's cool that it gives you the plan first to approve before it just starts cing because we

have um multiple and you know I think we'll get to that when we're talking about other tools but we have a lot of different stacks and we're going to be adding more we're going to be adding like a mobile stack because we want

people to do whatever they want and sometimes like one sack will not be able to do everything for you so you know you know back to the question of like how could you learn how do you learn to code

today I would really start by making things and the reason why you should start this way is because now you understand what coding is for whereas the way coding typically is taught is

like you teach the programming teach the f- statement whatever but you wouldn't know what to do with it and so here inverting it where we're going to actually sort of show you what you can

do with it and then the way you learn is basically you'll run into a problem invariably and you're going to have to figure out what kind of tools you need

to recover from this problem and that'll you know expose you to code the AI might get totally blocked and you have to go and like find other tools go to sack

overflow go read the code go explain the code so now it's taking a screenshot of the app it built the app and now it presented to us like so it it looked at it it wrote the code looked at it make

sure it's working and then it presented to us so here it's going to you know we're going to put our you know weight and height and age and let's say

moderate activity and let's say want to lose weight search for food item I wonder where get the data from

just ASM data or I I think that it maybe try to get or maybe it expects me to add a meal here so add to meal plan

Apple okay good so now we have today's calories H there's zero protein see progress so you can see the calories you

can see the carbs the macronutrients and so it's it's pretty complete so far add a feature if you like or we can deploy it

too uh how where is it getting the the data from like is already just added a bunch of data about the fruits I think we I think so created it created a sort

of a some default data and I think I think we'll be able to create let's see Chen breast so yeah we can ask it

now where can we create like more should just add a bunch more data like probably has data in LM

yeah okay yeah so you know notice here it's asking you to test it and once you're done testing it you're going to say yes it works

well but I want you to add a lot more uh foods to the database okay and is set up a proper

database for this or is it like saving stuff on the client or something um so we can actually see it doesn't look like it set up a database but so we can ask

it sometimes if you made it explicit in the prompt it will set it up but because it's paid sometimes it'll like just give you the ability to do it down the line

got it so you could just say like hey set up a database for me and make it persistant and will go do that yeah okay so it's adding Foods now nice yeah here

we go there's more now it's all Health it's all healthy it's like should we ask for McDonald's I'm I like [Laughter]

McDonald's so let me tell her to make a database it works well let's migrate to portress and that is pretty unique for

rep right I don't think these other tools have database yes yeah um and at the same time as it's doing that so it just says I created a database for you

right here um let me show you the deployment so you can just click deploy and this is other thing that's kind of unique as well is that we have like a you know full deployment environment you

could you know you could run seam liet you could run virtual machines you can run autosale machines it has you know versioning Secrets logs analytics so

it's a pretty complete deployment platform in addition to a development platform so yeah I mean it's it's great that you build the stuff before the AI stuff came in cuz it all works together

yes exactly we have this 8 years Head Start so let's see

apple add meal plan just put an apple here okay so let me ask you two questions one is like like guess if

there's like a bug and I get stuck right and like you know with these other tools I've tried you can get into a state where you know it's like hey go fix this bug and it fixes a bug and then there's like a new bug and then you don't

actually understand I don't actually understand how the C- work so it's like just like hey so how how do you avoid this like Loop that people get St yeah so so I want to show you a few things

one is as as the AI is coding is explaining what it's doing oh that's awesome yeah it's as it's writing database up Pi it's saying what it's

doing here so at the top of every action it is it is explaining what it's doing and then the other thing I like to do is and I encourage people to do is go into

the files so you know database. Pi for

example and I want to dig into this and actually like try to understand it you know step by step so you know for example I want to see what this does so

I'm going to click explain with assistant and should go to assistant here I'm not sure why it did not

work oh here it it apped inline sure okay so it goes yeah it goes through uh the code line by line uh and tells you

exactly what happens and then you can go to the chat here and have a like a longer session so explain to me like five okay yeah this is awesome because

normally I would just copy it into like cloud or something and try to get explain it you can do it right yeah exactly yeah so so you know it can dumb it down

um for you you can also let's start in your chat and like ask it higher level question explain how this project is structured so this project is a

nutrition tracking application built with python streamlet SQL Alchemy the main component is app.py models.py I can click on it and go to the file that's

awesome directory structure and so on so forth so I would say like talking to the AI and sometimes yeah going to Claud is also helpful so you can get like a fresh

contact or going to CHD or whatever your your AI tool of choice and you know asking questions about the codebase once you if you run into a bug you could take

that error you know ask about an assistant and then ask it okay take me to the file and like show me what I do to fix it if the AI is stuck and can't

truly fix it I would go Google you know AI is amazing but by the way before AI Engineers were like of their time on

Google so Google still has like a lot of amazing content for you to explore and learn and my experience teaching people to program and seeing people using repli

agent is that you're leveling up naturally almost by sort of almost by osmosis because you're you know you're flexing that muscle of debugging of

systems thinking and slowly you learn how to code at some point you become so interested in the craft that maybe you'll go take a programming course but

it's after you understood what is programming for yeah it's almost like the reverse right like you actually build something and then you try to break it down like you try I I I think the key step that most people don't do

is actually like asking questions like this like explain this to me how does this work that's what feeling to do you ask the qu questions yeah yeah I I think knowing what to ask is actually quite an

important skill and the other important skill is like what's typically called systems thinking uh is being able to like break down problems think through

them one by one that also enables you to do the right prompting because you know a lot of people that I think fail with agent and similar tools is that they

continuously give it like large scope and if you're telling it every time to like do something really large then you're increasing the chance of failure as opposed to like chunking the requests

down so if you were to give like a couple top tips it would be like you know do it once one feature at a time or one scope at a time or some tips to use repay agent yeah I I would say it would

start with like a chat session do everything set up the database get the first prototype and now I want to iterate on it so I will create a new

chat and start a new session a new plan with the agent and do that one feature for example I want to add way to look up food from the internet maybe there's an

API and so I'll I'll start a new session and do that now if I failed and it didn't work well we have this feature called roll back so you can click roll back and like you know start from the

start because that happens sometimes and you don't want it to break your application and then another tip is you know as like as a project gets bigger you want to give it increasingly more

pointed instructions and tell it what not to do because sometimes it gets too creative ative and start doing things it's not supposed to do and we're trying to fix this problem but somewhat of an

inherent problem with these models being a little creative and yeah I I would say those are kind of two two big tips don't afraid of be afraid of roll back start

new chats often and be extremely precise with the prompts and don't make it so that you're asking it three different things just ask one thing at a time in

each prompt and then and of like ask some questions to figure out what he's doing just like for learning purposes yeah I especially recommend going to the assistant so you could think of the

assistant is like the cousin of the agent so agent is doing things on your behalf it's going to take a lot it's it has a lot of agency it's going to make a

lot of decisions without consulting you assistant is more like a co-pilot kind of tool where it's not going to make any changes until you ask it to it is really

much better at chatting you can brainstorm with it and so it's important to know when to use the tools awesome this thanks for giving me that demo so let's kind of switch gears a little bit

I want to talk a little about how repet builds products and when we start with like kind of your vision for the company like is everyone going to become a programmer or what was the yeah yeah so

so if you think about it the ultimate let's call it the ultimate function of a computer is to do things on your behalf

is to automate your work just do things for you right it is not just a tool like a pencil it is it is a tool that can you

know do a lot more things behind the scenes you give it an instruction so in an Excel spreadsheet you change a number it will Reflow do all these calculations so computers were always meant to be

like that now the problem is very few people know how to code and so the most programable environment that most people have is only Excel you know that there are other

sort of modern tools but they really you know they stop at the sort of the power of excel so if you were to wave your hands and get everyone to become a programmer

uh I think a lot more people would get a lot more of the of computers and I think productivity would sore I think people will be happier because they're not

doing menial tasks so it's sort of it's similar to this vision of AGI but you don't really need need full AGI as long as you have a machine that is good at

writing programs you're going to have a very powerful tool so so our view is that not everyone needs to be a programmer but everyone

can benefit from making software so we have examples from a community where a a dad you know makes a makes kind of

software for Education like make make it interactive sort of solar system you know application and you can scroll through and like look at the planets and

their information and things like that another thing is like you know Dad made this app called Chore hero it's for their for it like a leaderboard for the kids to see who's M who's doing the most

chores who's collecting the most scores and and things like that that's nice so obviously people you know we just made an app for for workout but people use it for work a lot as well so like this dual

nature of it that makes it very interesting and this is why I feel strongly that we're going to reach a billion people eventually because I

really think that if you can use a computer you should be able to make software yeah I love how like as let is kind of more personal software like like I made an app that just help me resizes

images for my blog and like I I never sell it for money but it's like it's a useful tool for me personally it's like very addresses one person's problem yeah and especially all these

tools on the internet they're full of ads and spam and whatever so making your own tools is just like way better I said this before we launched the agent but I

said the ultimate test for like a code generation system is that you can make an app faster than you can Google for it I love that yeah in some cases that's

true today yeah cuz Google you have to like browse the links and like you know look at all the ads how do you think about replate like how do you differentiate rep against all the other

coding agents out there like you know B Co cursor V yeah so I think you know I think you know there there are these apps that are focused on code generation

which I I put kind of Bolt and cursor in similar category it's you're not using them to make the end user software maybe in some cases because you

have to take it somewhere else most of the time you know sometimes you make it with bolt or v0 take it to cursor improve it in cursor and then

take it to versal and deploy it there with repid the entire software development life cycle is in one place if you're using cursor you still need to figure out what database to use how to

do off and you need to learn all that stuff you need to learn how to start a you know development environment and with repet just you come to repet you

put in the natural language prompt we create a database for you we'll figure out what kind of deployment you need obviously will'll make the app for you

you can do set of database migrations you can handle different Integrations like we could have asked repet to make a

you know summarize my Daily Progress of my nutrition tracker using open a and they'll say okay you know what is your open eye secret then it'll save that and

it'll use that to to summarize it another thing is repet supports a lot of different Stacks we have people doing a lot of data analysis and dashboards uh

using uh streamlet we have a lot of people making sort of personal apps either with like flask and and and

JavaScript or or react um and JavaScript there are people making apis so I'm just going to make an API you know with fast API or flat

to go grab something from the internet and return Json because I want to plug it into zap or some of my own or I'm going to give it to a front-end engineer and they're going to use it so it's a

lot more Dynamic tool with a a a wider sort of apperture and scale of usages yeah I mean I mean you know going back to you guys have been building this for eight or nine years right so it's much

more FY featured how do you get to be like cuz for a lot of consumers they just care about like the user experience so I'm just curious like how do you get the agent to build good UI like how do

you is that a hard problem yeah uh we've gotten a lot better at it over the past three or four months a lot of it's just prompts just figuring out the right prompts a lot of it is just like yelling

at it to like make beautiful websites make modern production ready websites or something like that okay and you know I'm not kidding you know that's a big part of it the other part is using the

light right libraries so you know shaten is a sort of JavaScript reactjs library that ships with components that from the

start are actually pretty nice you know I'm sure you've seen it vzer I think uses it by default as well and using like an existing design system like that makes the app you know by default was

like oh I'm just going to ship this to production and then there's like responsiveness and there's like making sure you have the right HTML tags and a lot of it is just like kind of you know

iterating and fixing all these small things just to make sure the user experien is a lot better yeah you have to be like very detail oriented during use AI products what do you think about let's talk about I think he worked at

Facebook for like two or three years right like a long time ago and you know like a lot of these companies have like these annual planning processes with like a lot of PMS in a room and then and

then they have like a three-year road map or like a vision and then I don't know I I just feel like it's kind of like you know not very useful if you spend M doing that kind of stuff so so

like how do you guys do planning or like what do you think about all this planning stuff frankly frankly we don't that's great and you know honestly I think road maps are

dead like you know U you want to be able to react to new technology which happens every two weeks now so you know we

dropped everything and like played with R1 uh we decided it's actually it's very interesting academically but it doesn't come close to Sonet for for coding for

example so you want to be able react to that but like if it turned out to be great we're just going to pour more resources into it and and build build it into our system so in this environment where the you know the ground is

Shifting underneath your feet you want to be able to kind of shift resources really quickly and road maps make people rigid because they're going to be single-minded about one thing the way we

do things is I generally have a sort of direction or some you know a higher level goal for example Le this quarter

or this month we're focusing on growth and then I say like okay come up with ideas for growth and everyone goes and like have has ideas and then we put them together we pick the best ideas we split the teams and like we go work on it and

then let's say well we want to work on inter liability it's like here are the issues like you know agent reliability we have all these metrics we want to move this metrics and then you know everyone contributes to that and so we

try to do like one or two or three things per you know whatever quarter or whatever interval with thinking about and we don't really plan for the next quarter like as we're doing this like

more information presents itself and the application change and the user Behavior change and and the technology change and so then we come up with a priority for

the next quarter and again it's like single word you know growth reliability retention something like that uh sometimes it's like yeah we're want to build a new product right sometimes it's

like you know by the time people are watching this we would have launched our new mobile app that is Agent AI first and allows you to build apps on your phone and encourage everyone to go try

it out and so that came out from the feeling that you know mobile is a really great could be a really great experience and we could reach people that otherwise we wouldn't be able to reach because

there are a lot of people that spend about zero time on their you know on their computer and they spend it more on their iPhones and iPads and and things like that

so this is how we sort of make decisions and how we align the team and and I think especially small startups should consider doing it something like that

yeah and and how do you think like how do you guys use rep internally or like how does the prodct teams build this like how do you guys build a mobile app

is like you know we the way we see repet is it is for making these Standalone applications and you know being

relatively simple being able to you can deploy them being able to scale them you can build a business on it but you know if you're a you know professional engineer working at repet sometimes you

just need an IDE so we have that but the way we use repet is two or three ways one is our designers use it to prototype increasingly we're skipping the figma

step we go straight to prototypes our Engineers use it to look at the feasibility of doing something our Engineers use it all the time for for

you know building debuging tools building proof of Concepts things like that and every once in a while we use it to build a production system and

typically that's like a microservice or API or something like that we also use it a lot for data analysis but you know if we're building like the rust

infrastructure that runs the cloud for repid uh we're not going to use repid for that what do that PMS you you still have PMS in the company the

PMS we we have one PM that was designer originally we we just added a also you know young and and very um energetic and

exciting PM but you know we you know PM or organization repa is not you know fully developed yet and RPMs are kind of creators right like so they spend a lot

of time making things either in figma or in ret they bring you know experience around how to design experiments they

talk to users a lot they do uh research and user testing they do quite a bit of project management and make sure different teams are talking together and aligning but we're at a point and you

know maybe someone in the audience would would want to join we're at a point we're hiring for product management okay yeah my my theory is that you can't be like a straight shot PM anymore these days you got to like have some other

skill like you got at least talk to the users man you can just like freaking do all the internal alignment stuff yeah yeah exactly yeah yeah I mean I think PM is one of those very dynamically

shifting sort of role but actually like PMS actually can help you AI PR now because like the prompt is so important and some of this stuff is just very like manual and iterative so like yesterday I spent the whole day like trying to

update a promp for my product it's actually kind of annoying work man it's like going back and forth what is your background we're building this I can't talk too much about is I prod internal Roblox and we're trying to make the

output like consistent like you know not have it hallucinate and you know uptain the prompt is like one part of it right up a promp run the evals up a promp again it's like that that that Loop

you're a product manager at and but you're sounds like you're in the trenches building I mean yeah I'm like the anti I Prim myself on being the anti PM so like I want to build I don't want

to write documents I yes amen amen well okay well let's wrap up by talking about let's talk a bit about your big launch like what are

some of the big things are changing about repet so the big thing is we're making repet agent free to try so we'll give people like a generous allotment of

credits to try repet agent you can go all the way from a prompt to an app that's working and uh you'll be able to share it with your friends and I think

that's like one of the most just sort of cherished experience when you able to make software and share with someone we like I mentioned the mobile app a couple

times but the I I think that is quite it's a first ofit kind we took a lot of Novel approach for the design to figure out what is like a making experience

look on such a tiny screen and I think we have some really exciting sort of design concept that I hope people will try and and then we were coming out with

like a social experience where one once you make an app on repet you can choose to share it to let other people remix it and you know talking about the educational experience that we talked

about earlier being able to remix other people's apps I found like as a kid that's how I learned I would download Visual Basic code from the internet and

like Tinker with it until it works and we're we're coming up with a like a a new onboarding experience that teaches you how to use upload because for a long time we just threw you on this homepage

and you have to figure it out so this new onboarding experience will like for new users will like guide you through building your first application perhaps sharing it as well yeah I no that the UI

has it fall from like it's it's kind of more Focus over time all the way to now it's just like a input box so that that's great yeah I I think over time we're gonna we're going to

keep simplifying and you know that's the thing about our culture is that you know there no sick cows like I think you you want to be tied to a certain time and and place and you want to be able to

meet the future where it is or actually run towards the future before the future ales so you can so you can be ahead of the game maybe a little bit and do you have any closing Awards of advice like we're at an interesting moment in Tech

right where like maybe it's the year of the AI agents maybe instead of like you know doing a co-pilot thing you can just like tell asan to do something and then come back an hour later and it'll be done and at the same time you have all

these comp companies like big tech companies like you know trying to be more efficient going through layoffs like how does someone get you know someone Tech think about all this I

think if you're sort of going through school you have two and you want to work in t i you have two radically Divergent ways to to think about it if you want to

be a programmer and have job security I think you have to pick uh something as close to the mental as possible for example

NASA will not have JavaScript generated or like GPT generated JavaScript run the Rockets right or the Tesla cars or what have you so if you want to work on

embedded systems using C you have job security for 5050 years maybe similarly if you work on cloud platform writing rust or go or things like that I found that the AI is typically not very good

at that because it is not very well represented in the um training data the other direction is you want to get you want to get

really good at being a product person yeah and being a jist being a designer a maker a PM and that's because I think

this like full stack developer that's the thing that's most at risk right because it's the thing that's most represented on on GitHub it's a thing that AI is most good at and it's a thing

that's already somewhat automated like people using graet and curs and others you're already sort of automating a big part of it um so I think the need the

demand for engineers like that I think will go down and instead companies will look for generalists that can go from ideation to to a production code by

using Ai and I think they're going to be a lot more highly leveraged and again also if you're already an industry I would run in one of those directions don't stay in the middle I think the

middle is is going to get squeezed I totally agree I to I think the generous direction is more fun because you can try different things every day and maybe you can just like start your own one person company and like you know

sell like a nich thing and then it'll work out for you yeah yeah I I know a bunch of people who did that with the sort of Advent of generative AI awesome

well I'm where can people well I guess I go to rep.com right go to rep.com sign up try agent if you like it give us some money and we'll we'll make sure that

you're going to have a blast I was just going to say like aad am as a d most on the web like a Twitter is is the channel I I spend most of my time on and you

know I want to thank you on behalf of all the PMS out there for democratizing programming for all of us so we have hope yeah my pleasure yeah thank you

thanks for having [Music] me oh