▶️YouTube

The end of Microsoft Excel's 40-Year Dominance? (Shortcut AI is INSANE)

Greg Isenberg·youtube.com·35 min read·6h ago

Select text to create a clip

Transcript — click timestamp to jump, select text to highlight

470 segments

I spent years inside Microsoft Excel, building models, forecasting revenue, cleaning messy data.

I hated it. Every time I thought there has to be a better way. Then last week I came across

Shortcut. It's this AI app that plugs into Microsoft Excel, Google Sheets, and suddenly

the tedious stuff becomes magic. So I invited the co-founder Nico onto the podcast. We built

financial models in real time. We explored how Shortcut works under the hoods, and we

talked about how to get the most out of this product. If spreadsheets are a part of your

daily life, this episode will change how you work. Let's dive in.

So I reached out to Nico and I think the DM said something like, this is one of the

most impressive AI demos I had ever seen. Can I use the product? And you said you'd come

on to the podcast and share how people are using your startup Shortcut. It's kind of like

Microsoft Excel if it was built in the future. And I've never really been a huge Excel guy

because to be honest, it's been overwhelming to me. The macros, like I don't even know what a macro

is. So that's why I reach out to you. I just feel like there's an opportunity to, like I know how

valuable it is, but I just, I know how hard it is to use. Anyways, Nico, welcome to the pod. I want you

to show me how I could use Shortcut to make more money and be more productive. And I was hoping

you can do so. Yeah. Thanks for having me. Super excited. I'm going to just share my screen and kind

of get into it. I think I've been doing live demos for some time now and it's always just like the

most possible fun way to do this. So kind of like you said, it's like Excel if it was built in the

future. Very intentionally, it's like exactly Excel. You can do whatever you would possibly

want to do in Excel and you would do it here. And we had to recreate a lot of it to allow this.

The big difference is that it's also a superhuman agent that can do most of your work. So like the

good way to think about it is not as like a co-pilot for one or two steps. It's like it will do 90%

of your entire job and then you get to do other things as that happens. So I can give you some

examples. But again, again, it's just like Excel and it's not just for creating things

from scratch. You can just open up existing Excel files in here and directly manipulate

them. So for example, here's like a DCF file on Microsoft, which is like a pretty nasty model

to have to make. And then from here, you can do whatever you want. You can just ask it to

be updated. The best way to really use it is to send it off and probably just come back

in about 10 minutes. And one thing I want to show you, I guess this would be like a technical

demonstration of how hard it is. But like I will say, you know, here is this huge DCF,

which can take up someone like, you know, half a day or a whole day to build. Hey, take this,

please update it and use the exact template that I want to use Google. Now pull the, you know,

10 Ks from 2022 through 2024 and, you know, do forward projections through 2029. And it's going

to do it. It's kind of crazy to watch. I think it's fun to watch the first couple of times, but

again, you're going to want to just come back to when it's done. But Greg, the other thing I kind

of want to address is like your question, which is like, how can people use this to make money and

be productive? And I think the best way to do that or show you that is like to do exactly what

I'm already doing right now or like I have to do today. So for example, this, and you'll see that

I can come back to and like have multiple shortcuts running at a time. This is like dummy data. I try

to make it look just like our data without giving away sensitive information from our actual like

revenues, expenses and its sources and like its types. And what I need to do for work is like build

a PNL, like pretty classic income statement. And specifically, I need to project it out two

years as well while looking when you're back. And it's going to be like for our data room.

This, you know, I know you're not a big Excel guy, but this is one of the most like common

financial models you'll have to make on Excel from rookie.

I will say I'm not a big Excel guy as like a contributor to the Excel, but when people give

me Excels, you know, I'm loving it and I want, I want to be able to manipulate it, but I'm

scared. I'm going to break something. Yeah, that's fair. Um, there's like two actual major

use cases right now or types of users archetypes. Um, the ones that it's most sticky for are

the people who are kind of Excel experts, but it takes hours of work and makes it like

10 minutes. But there's another class of people that like I'm learning more and more about,

which is like, they're not super strong at Excel, but this thing makes them almost like

Excel gurus pretty quick. Um, so we can even do an example together based on like what you

want to do and like see how far you can take it and see how much better it makes you.

Um, so here's like what that example was for me, what I needed. Um, and right before I do

that, I actually will show you one thing. Sam Altman, the co-founder of open AI just said

that it is the era of the idea guy and he is not wrong. I think that right now is an incredible

time to be building a startup. And if you listen to this podcast, chances are you think so too.

Now I think that you can look at trends, uh, to basically figure out, uh, what are the startup

ideas you should be building? So that's exactly why I built idea browser.com every single day.

You're going to get a free startup idea in your inbox, and it's all backed by high quality data

trends, how we do it. People always ask, we use AI agents to go and search. What are people looking

for? And what are they screaming for in terms of products that you should be building? And then we

hand it on a, you know, silver platter for you to go check out. Um, we do have a few paid plans

that, you know, take it to the next level, uh, give you more ideas, give you more AI agents and more

almost like a chat GBT for ideas with it, but you can start for free idea browser.com. And if you're

listening to this, I highly recommend it. This is a kind of an interesting like user paradigm.

One thing we've learned is like people specifically working on Excel, aren't like extremely good at

prompting, um, or, and they don't even expect that the AI really greatly understands its subject

matter. But when you show clarifying questions, it can make them better. And it's kind of, it's

like a first magic moment for people who use Excel a lot. So, you know, what are the growth

assumptions I should use going forward? Conservative, moderate, aggressive. Let's just say like,

you know, I want all scenarios. Let's make it hard.

That's really cool. I've never seen UI like this. You know, actually I've seen like from

time to time, a clode or chat GPT will be like, can you refine it? And I love when it

does that, but I haven't seen it built like product ties like this.

It's become one of the magic moments, which I totally did not expect. Um, but users are

really not that great at prompting. And I think GPT does something similar. If you do deep

research or if any of you guys should use deep research, I get them out, but they almost,

they, they like necessitate that, that clarification. But for us, we actually want to make it context

aware so that the clarification is even better. Um, and users have like become much better

prompting because of this. Um, so I'll do all scenarios. Um, let's keep the same exact

structure of the template and, um, update the data with the same metrics and charts. Um, again,

I think this is like the most similar to real finance work, for example, is like you have your

templates and you just want to update them. You don't want to create things from scratch.

It's definitely like, this is maybe even like the hardest kind of work. So it'll take that on.

I'm going to go back to this example. I'll say, Hey, I need to build a PNL for this last year of data

and do a two year projected out. This is for my data room for VCs and bankers make it very

professional. Uh, it's always funny to see like how it interprets that, um, see how it goes.

And what we can do also is like show you a third version of this and like something you want to try

or that you think like would be valuable to you or valuable to your audience. Uh, and we can give

that a shot as well. Cool. I'm also like, as you're going through this, I'm, I'm, I'm just

wondering like, what is the, what is the best way to prompt shortcut? Like, is it long prompt,

short prompts? Do you need, you know, you've seen thousands or more prompts? Like what do you

recommend to people? Yeah. Um, it's a really good question. Uh, in general, I've always liked

relatively vague prompts, um, cause it forces the frontier models to really get creative, um, and then

suss out clarifying questions from you. So specifically because of our clarifying questions,

I'd like less for both prompts. I'd like less specific prompts. And then that kind of encourages

a little bit more creativity out of the model and then out of your clarifying questions. Cool. Um,

so we'll, you know, we'll fill this out as well. I'll say do this over many different sheets. Cool.

And it will, uh, get going from there. And meanwhile, I'll check in on, on Microsoft. Um, so what you'll

see here is it actually looked for the Google's data and the 10 Ks exist in like an SEC database.

That's like super hard to find and extract, but it found these 10 Ks and extracted them. Uh, 10 Ks

are like a hundred pages of PDF material for, for public companies. Uh, it found all of these Google

10 Ks and it's starting to extract the data and you'll see it actually provided a task list here.

So it's, it's current plan is to read and analyze all the current models, search for and download the

10 K filings and extract these and then start to update the historical data and the drivers,

uh, and the assumptions as well. Knowing that like the PNL and the dashboard are more formula

driven and will be updated automatically if you can change the source material.

That's crazy, man. That's actually like, that's crazy.

Uh, yeah, it's pretty crazy to see. Um, you know, and actually, and we can talk a little

bit into the technical details, uh, as far as you think, you know, that's interesting. Um, but

these 10 Ks are so big and confusing and like horrible that you'll see that like we're running

into context limits here. You see in the, in the, in the file on the right side and it's

actually agentically deciding, well, let me look at these like one part at a time or like

one chunk at a time. Um, so there's really no upper limit in terms of like how we can allow,

um, agents to go over material. I think historically a lot of, a lot of what we've been doing

is rag in this industry. Uh, but as agents can learn to start to search for chunks of

information selectively and then compact their context as necessary, that is, that is changing

dramatically. Um, yeah, I guess what this, what's going through my mind right now is, you

know, Excel has been around for how many years, 30 years? It's almost its 40th birthday, 40th

birthday. Like Excel is a middle-aged person. Yeah. You know, probably a middle-aged man,

gray hair, um, you know, khaki pants. Yep. And, uh, you know, when I'm looking at this is

I'm like, okay, what, what, what does this unlock from a use case perspective that, that

Excel hasn't been able to do? And, and what are some unfair advantages that people who get onto

shortcut early are going to be able to unlock? That's, what's going through my brain right now.

Yeah. Yeah. So let me tell you a little bit about Microsoft, um, and what we know about Excel,

um, and then what these unfair advantages are. So Microsoft Excel specifically is like,

I would argue, like I grew up using Excel. I started my career in finance, which is not a

coincidence for why we ended up building this. Um, in a lot of ways I would say it's like the best

design software maybe ever, like it's 40 years of staying power, 2 billion users, the business,

like the business world runs on it. Um, but what it's, what's, what's that is, what that has

accumulated is like a lot of things that you have to satisfy for a lot of different enterprises and for

a lot of people who are still built, you know, 20 years ago for their tech stacks. Um, so even

co-pilot, which is trying to do what this is doing right now is forced into helping people use Excel

better. It's not forced into like, how should Excel really work? Right. Um, so we really had

the chance to just go from the ground up and instead of doing a single step co-pilot for the

things that you only want to do in Excel, we have an end to end agent that can just do all of your

work. Um, and the kind of fun part about it is that like you can import and export Excel directly.

So no one would ever even know it's in shortcut. So in terms of what people are using it for,

they have their standard things they do at work. And honestly, like there's a thousand

companies already using this. And I actually think their bosses don't know. I think they have

their four or five hours of things they do that have turned into 10 minutes and ideally good

employees are doing more of them, but maybe a lot of them are just getting them done and enjoying

their free time. And I can tell you like what those specific things are, but that's, I think what

the pattern becomes. Um, so actually by the way here, um, one kind of really key, key thing is even if AI

becomes perfect, which it's not, and I'm not sure it ever will be, it's like an indefinite hill

climb, you will have to really, really trust its outputs in order to move forward. As in like,

if you don't know where things come from, they're almost useless. You have to review its work.

So here you'll see that it looked, it found these 10 Ks from Google and it can actually cite every

single part of the information down to like the exact figure, the exact page of the PDF it came from,

the exact year the data came from. Um, so that when things come into your Excel model,

you can trace every single bit of it. It's almost like if you use cursor, like code gen was very

cool, but until you were able to see the diff, you couldn't quite trust it. Cause like some arbitrary

line in your code would break. So the one reason we're not building this directly in Excel, um,

or not mainly focused on that is that you can't really manipulate the UI. Like right now you're

seeing that this agent is, it sees as an error in the calculations, it found it and it's directly

editing it. So we're changing the spreadsheet and the entire front end, um, like in real

time.

I'm happy you said that because it's going, it probably going through everyone's mind,

which is like, how can I trust this data? You know, the, the stakes are a lot lower with

like, Hey, write this blog post and Hey, build a financial model.

Yeah. Um, it's just that the finance world until probably right now wasn't ready for

this, but this was the same things that we had to ask ourselves in software engineering.

It was like, Oh, well I'll never use that alum code. Remember when everyone was complaining

about hallucinations in December 22. And then we found out that if you can really observe

it, if you can apply the diff, of course, humans are still responsible. And if my code doesn't

build, like I'm the one who gets in trouble, it's not clot code or cursor. Um, so what will

inevitably happen, whether it's us or someone else who cracks it is in finance, accounting,

FPNA, real estate, wherever we're like, there's these giant people who use Excel, they'll progress

to this role of supervisor where they're 10 times faster. And if they're wrong, or if there

is a bad number in there, of course it's them that's on the line, but they would take that

trade off because it's easier to supervise work much faster than it is to do the groundwork

yourself.

I mean, ultimately you're supervising work regardless, right? Like either you're supervising human

work or you're supervising, you know, agentic work. And the bottom line is you, you know,

I guess the question, it goes back to like, you know, are self-driving cars more safe than

human, human cars?

Yeah. It's an interesting thing to bring up. Um, the reason that self-driving cars, well,

I mean, even within certain cities where their accuracy is really good, hasn't, haven't been

adopted is a little bit of, because of this accountability issue where like, it seems like

humans are actually willing to have more death and chaos, as long as they can clearly point

to whose fault that is. Um, what I really believe to be true though, is there's a certain accuracy

threshold where if met, we will change that. Um, a certain benefit where if we really can,

can experience this benefit, we're willing to think in a new way. Um, but it's not just enough

that it's better. It has to be better. It has to be faster. It has to be more observable

and traceable because you're right. Humans are already managing humans. And like, that's

actually not that easy as I'm sure, you know, right.

And, you know, shortcuts specifically, like how on a scale from like 2005 self-driving car

to 2025 self-driving car, like, where are we?

Yeah. Great question. Um, think of it in two dimensions. One is, or two almost, let's, let's

do two kinds of use cases. There's a use case of like build something from scratch. And let

me show you, for example, um, this one, right? Bam. So this was the one I asked it to build

something from scratch or more or less. I said, here is, um, you know, data build me, build

me summaries dashboards. Right. And in this use case, like it just did this in eight minutes,

Greg, like that's like, that would have taken me, you know, an hour or two and I'm good

at Excel. Um, for use cases like this, we're already past this self-driving moment. We're

past the, the way amount moment now. And I'll continue to answer your question, but I'll

show you why it looks like this, which is super cool. Um, this is the observability we're

talking about. You can see exactly what figures are hard coded, which are formula driven and

why so that you can really review this better. Um, but the real use case, like I was pointing

to earlier is you're going to update not at things from scratch, but you're going to

update existing models. Now for this use case, which I think is 90% of real Excel work where

like the billions of dollars are, I'd say we are at like the Tesla self-driving right

now, as in like, if you're in the know, if you're willing to adopt frontier tech, it's

very exciting and actually useful in your workflow. But humans are still by and large doing the

manual driving themselves. I, I like to think of it as we're probably heading for like an August

2024 moment, which is when Karpathy tweeted about cursor and it went like 20 X. I think

the question is, is, are we like, is it August now or is it may, but, but there's a very clear

line that we can future predict towards that looks like we know what to solve and that it

is solvable. So it's, it is, as you can imagine, super exciting for us.

And it's also very clear that use, you know, a product like this should exist, right? Like

using plain English to, you know, we've had vibe coding, we've had vibe marketing, we haven't

had vibe Excel yet. Um, but I think, you know, that this idea around, um, you know, taking your

thoughts and, and build and building, you know, in this case, it's not code, but in, you know,

it's kinda, it's kinda quasi code in some ways, right?

Yeah, no, of course. Um, I wish I can show you the logs cause it's of course code.

Um, everything's code, right?

Right. And everything will be code. Um, and I think all code will be generated like dynamically.

Um, but the reason, the thing you're kind of getting to is what I've always thought was,

you know, maybe one of my smarter ideas, but you know, it's not mine exclusively is the best

ideas are not definitionally contrarian as in like, I didn't have to think of something

that you didn't believe and then make it true. I just think the best ideas are really obvious

in hindsight. And I think the best predictor of what that is, is if you can release something

to people say, I can't believe this didn't exist already. Right. Um, so when people see

this, I think that's the reason that the initial reception has been so strong. It's just, why

hasn't this existed? Like there has to be some explanation and I'll tell you what it is.

We're a research lab with 20 people that are all, you know, from MIT, Stanford, great

researchers. But if it wasn't for my background in finance, we wouldn't have done this. And

I just don't think that there are co-founders at, you know, the 10 or so frontier research

companies in the world that care at all about finance. No, no researchers really spending

material time in Excel at all. Um, they are building coding agents because that's what

they love. Right. So it, it, it took someone of a little bit of a different background to

make it happen. Um, and now I think the world knows how important it is because of the,

because of the initial reception and I'm sure everyone's sprinting towards it.

Yeah. I mean, that's why, that's why I reached out. Cause I, I had this in my brain that I

wanted this. Um, and so it's, it's cool to see it working where, so what's happening?

What am I seeing on screen right now? Yeah. So this is actually a great one. This is the

big hard task, right? Which is update the Microsoft, um, you know, DCF model using Google's new

data, just use the same exact template. Don't change anything except for the data. And what

you found is the agent has actually extracted all of this data, has updated the historical

data, the drivers and the assumptions is looking at the tax rate. And it's actually kind

of finding errors as it goes. And it's like, that actually doesn't really quite check out.

I think CapEx is too high, right? Or here's an example. There seems to be an income calculation

error. Let me correct the issue. I see the issue is that in the data sheet, it has the

wrong references and it's always finding its own mistakes and just chugging along. So

you're seeing it actually do the kind of work that a human would have to do. And it's about

like, you see, I see the issue. There's a dependency and it's causing a circular reference. One of the

hardest problems in Excel, you have like these things that are codependent on each other.

Um, and it found that the circular reference and the exact formula that it was referencing.

Uh, which isn't a hard formula. Like, I don't know if you ever use like sums in Excel, but

it found it and it found it and it fixed the error. So that error is gone. And now it found

that there's a couple of ref errors, um, in this SGNA and it's correcting those two. Yep.

And now it's, that's correct. And there's still some remaining ones. Um, and then Greg, what

I'd also like to do is like, if there's anything you want to try, like go push it, go, let's go

break this thing. Yeah. I mean, I'll tell you one thing that's been on my mind recently.

Mm hmm. So, um, we, we've got an agency and a design agency for, for AI companies called

LCA. And one of the things that, um, you know, if you write a, if you run a tight agency,

you, you need to have utilization rates that are, you need to have people basically

on, on, uh, files. Like they need to be utilized in order. And cause the big mistake, you know,

the big problem that a lot of agencies have is at the end of the year, they're making 5%

EBITDA, 3% EBITDA, 7% EBITDA. Like they're very hard businesses to run because, you know,

people aren't utilized. So I wonder if there's a way to create some sort of like profitability

analysis around, um, you know, agency utilization rates based on like different teams and stuff

like that. Like ultimately my dream, Nico is to look at a spreadsheet where it says like,

this is how, uh, utilize this team is. This is how utilize that team is. This is how much revenue

they're bringing in. This is how profitable they are. Just like a bird's eye view of, um,

utilization and profitability. You can tell, uh, my spelling has deteriorated ever since using

AI. Um, so let's go ask, let's ask shortcut for that. Um, yeah, it'll ask clarifying questions

and then we will see what we can do about it. Okay, cool. I mean, I would, if this works,

like, this is a good test. This is a good test. Um, I had done something similar where I asked it

like, Hey, we're going to do like some kind of launch soon. I'm looking for like a bunch of the

most in distribution, best launch partners that I can like meet with, talk to. And I had to find

that across every single platform and then it get like their posting schedule, why it's a good fit,

how much they expect it to cost. Even I got the people's emails. So it's kind of a similar kind

of task like that. Um, so you tell me this is your dream task, right? Do you, do you want this

multiple sheets, custom, uh, single sheet, single sheet? Yeah. What time period should

the utilization and analysts cover monthly? Let's do monthly. Key metrics. Yeah. Utilization

percentage revenue. That's great. Cool. All of them. Do you want a dashboard to visualize

the data? Yeah. Why not? Yeah. Make it hard. Yeah. Just make it hard. There's now like what

kind of data I'm, it's going to assume to make dummy data. I suppose you want me to like

get weird data from the web. Like what do you want to do? Is there a way to benchmark

our utilization rates versus, you know, standard design agency, uh, utilization rates? Like

I want to know if we're ahead of the pack or behind. Maybe I'm making this way too complicated

for us. No, no, no. Let's do it, man. Um, can you benchmark existing and standard agencies?

These are which ones specifically design? Design agencies. Yeah. Right. Um, design agencies.

And then for our data, do you want me to like say like, use Greg Eisenberg's company? Like

see what you can find? Yeah. I mean, you can, you can go late checkout. The website's late

checkout dot agency.

Go to late checkout dot agency. That's my company. Sure. Um, yeah. So I mean, it's pretty vague.

Let's see if we can, let's see if we can start marching towards your dream.

That's all I ask because I, I'm, I feel like I bug the finance people and like on my team

and they, they don't want to hear from me, like add this column here and do this there.

And I also think that a lot of people listening are like solopreneurs are small teams, startups

who don't have finance teams. Right, right, right. Right. So is this your finance team

in a box type thing? Yeah. I mean, that's why I use that first prompt here, which was

like, I have my expenses. Let me walk you through the actual answer here. Yeah. Um, I don't have

a finance team, right? I'm one person of 20 and I'm the only business oriented person

and I still spend most of my time coding. Uh, so I had the expenses here. I actually need

to build a PNL. Um, so pull this up and in fact, actually there's some errors here, which

I'm not used to seeing, but let's go into why, uh, historical PNL projections. Oh, interesting.

So it projected the revenue out for the fiscal years. Um, you know, according to where these

sources of revenue were in the expenses and it made a dashboard here. So some bizarre formatting

choices, quite honestly. Um, but you'll see it's looking like it has revenue. It has, and

these are all formula driven. So you can see exactly like where they come from.

Um, some of the ones are going to be more assumptions. Um, you see total revenue, gross

profit, operating margin, and so on, uh, even charts it. And it took, you know, my data

and built me, you know, a forward looking PNL. Right. Crazy. Um, I think we're probably,

you know, for these net news, it's like having your own mini finance team because you, you

don't want to do this from scratch, but you probably would want to just do your last

tweaks at the end. Yeah, exactly. Um, so here actually we're gone. You ready?

Yeah. Uh, let's see. She won't exist. It's going to create a profitability analysis for

late, late checkout agency. Well, interesting. By the way, Greg, I've never seen, uh, utilization

like sheet like this. So tell me, tell me what you, tell me your thoughts as you're seeing

in it. So, I mean, you know, going left to right. So I love, obviously I love the, you

know, breakdown of employee and level like that. We level people and, you know, higher

levels obviously get paid more and stuff like that. So I love that. Um, available hours

by month. It's interesting to see it like that, but that's not exactly how I envisioned it.

Like to me, I'm kind of like a percentage guy. Like, do you have, does Jane have 10% next

month? Okay. Let's go, you know, maybe let's not put her on a project cause we don't want

to be at a hundred percent. You know, we want people to like, right. That's too much. Right.

Um, but if someone has, if Jane has 70% availability, then she's kind of just sitting, sitting

around, sitting around. Yeah. Well, let's see. I think my, my guess is it will do some

percentages as well. Um, in fact, let's go through the task list cause it's going to be

pretty thorough. It has 13 tasks. It wants to get done as a part of this. Yeah. It's going

to create an analysis sheet to calculate. Yeah. Look, to calculate utilization percentages

by employee and team. Okay. Um, and revenue and cost as well. So let's, let's see how this

does for you. Meanwhile, let's check on Microsoft. Boom. So this is the Microsoft file that it

updated and changed to Google. Yeah. Um, you can see which files, I mean, which form, which

are hard coded, which are formulas. Let's just go bit by bit. Right. So it made these new

charts. This is for Google. It changed the name from alpha, from Microsoft to Google and it has

new results. Right. Um, this is like a kind of a standard PNL. I'll change the view. So

it doesn't look like it's in the review state, but PNL. So this formula didn't actually check

out. We'll, we can actually just ask it to fix it, but I'll go back. Assumptions. These

are like the growth rates for these are the, actually, this is cool. This, these are the

growth rates for, um, the assumptions for Google alphabet, which are like kind of hard to

guess. Why would you assume that YouTube is going to grow at this rate? Cloud's going to

grow at this rate. Right. Um, so if you turn this on, you can see that these are hard coded and

where they come from. Like these, these assumptions are actually coming from the 10 K. And if you

actually click into it, like, why is this value this? Right. This is something you can't do in

Excel. You can open this up and say, Hey, here's what the R and D is costing. And here's the part of

the PDF that's telling you where this fricking thing came from. It's not just completely made out of

the blue. Right. So any, anything hard coded, you can find that for, and then we'll go back.

Let's go drivers. So a couple of formula errors, which is why I'm saying, I think editing existing

templates is kind of like, sometimes your Tesla makes a turn and you're a little suspicious

about it. You know, um, that's where we're trying to cross that, that, that, that line, um, right

now. Um, so yeah, typically what I would do is highlight this. You can select the range that

you want to make specific edits to be like, Hey, fix these formula errors, please.

That's it. Like you don't, you don't give any more context to that. You just say like,

fix this. Um, yeah, let's see. Um, so that's like a cool, I don't know, like again, command

K would be like this, this feature in cursor in which you would like highly arrange and

like, you know, make a specific targeted edit. What it will do is it will strict the edit

space. So it only changes those, but it's pretty bright about like, let me look everywhere

for the necessary context to update this. Okay, cool. And then let's go back to your

task. All right. So, you know, I have to admit, I did not realize that building utilization

matrix is as complicated as a, as an LBO model. So let's see. Uh, yeah, it's starting to add,

um, information to the sheet. Let's see. Boom. Okay. Okay. Yes. This is exactly the type

of vibe I had in my mind. Really? Yeah. Like with the utilization rate, how many

available hours? Cause yeah, no, this is, this is, this is what I wanted. Something

like that. Awesome. Yeah. And then what you would probably do like as a user is you

would be like, this was good, but I actually want it a little different. Let's go like

change it, you know? And you might do it cause you're, I mean, you're not as like a

hardcore Excel user. You can do it yourself to some extent if you think that's faster.

But if you're like, actually I need these values in red, I like actually want to use

my real data. So use this. Um, you'll just like go for that second version, you know?

I mean, I shouldn't say it's like perfect. Like I, now I'm looking at, I'm like, okay,

I would change this, but, um, well, what would you change in specific? Yeah.

Well, I think like for me, you know, I would want, if someone's average utilization

rate, let's say is above 70%, like make it red. Like that's scary. Right.

Yeah. Burn, burnout mode. If, if someone's utilization rate is under 60%, make it, um,

green maybe. You're such a, you're such a nice manager. You don't want your people

working so hard. Well, I've owned agencies long enough to know that you, that's not

the way to build a sustainable business. Yeah. Um, well let's actually look at the, um,

at the tasks here. Usually say this is what you're talking about, Greg in Excel. There's

a thing called conditional formatting, which would be like based on this condition, make

certain thing look like this. Now, while we weren't, we didn't say this in the prompt,

so it's, I'm not sure exactly what it will choose to do. Um, but my guess is it will decide

like, you know, certain numbers, if they're too high, will be in red or too low. They will

be in red. Okay. What about automation? Like how does, how do you, how can you automate?

Like, I don't want to go into this and I'm not saying we're doing this today, but, um,

like, I don't want to go in this every day and update how many hours, like, is there a

world where there's like, you can, you can program this to automate similar to how like

the gum loops and the Lindy and AIs and the world of automated marketing? Yeah. Yeah. Uh,

it's a great question. Um, we don't have at this point, like a super strong integrations

pipeline. Um, but what you're asking for is kind of like the essential thing we're getting

into now, which is you will want to automate automatically extractions from QuickBooks.

If you're in law, it's like, they want to updates from Carta. If they're in like every industry

has their thing, which is part of the challenge. If you're going to do Excel, like for a research

lab, that's like very niche and specific. Yeah. But is product, it's actually almost

too broad. Right. Um, it's like, you mean 2 billion people, right? Um, so yeah, currently

what you will have to do is actually get your export and attach it and then it will do that,

but it won't auto sync for you. So you're, you're, you're kind of in charge of at least

supplying the data for now. Currently now we, we have this dashboard. It has utilization

by departments, revenue and profit by department. It's actually looking for, so this is kind

of cool. There's like a near deep research level quality of web, of web search here.

So you see, looking, you know, based on the web research, there's utilization for certain

benchmarks here, principles average this project managers, this, this looks to be, this could

be a little out of distribution. This is for certain kinds of companies. Let's see. And

it has all of these sites that it's referencing. And now so adding industry benchmarks and strategic

recommendations based on the analysis compared to your data. Yeah. So what you'll get at most,

which actually makes Excel wonderful, is that you have formulas at least. So like you can

see that like this, like, you know, I'm good at Excel, but this would take me a while to write.

Um, you can at least see that it's taking an average of this stuff, right? So like there's

some degree of like traceability, but it's not like cited, right? Like it's not that

the job of observing in Excel is, is unfortunately today pretty brutal for that reason.

Totally. Also like to you, there's a little bit of context to Excel. Like when you see a formula,

but to like a simpleton like me who doesn't know Excel that well, I'm kind of like, what is happening

here? Yeah. So I don't think like, look at this formula. I, this is above my Excel mastery now too,

right? This is a, an average if certain conditions are met divided by an average,

like other conditions. Um, part of the really cool thing is you no longer will have to ever

know this again. Like you will just be able to, as an Excel neophyte, just say like, listen,

I just need this thing. Use Excel formulas cause my boss is going to look at it eventually or whoever,

but you will no longer have to speak in this language. Just like I code in like

Rust sometimes. And I really don't know Rust, but like I know enough of the patterns and

I trust AI selectively enough to, to do it. Yeah. Um, and then I'll go over one more.

So I just, it wrapped up. I'm curious, this is your dream, right? Um, my dream, it's a high bar,

but what do we think? I'm going to, I'll, I won't show the review changes now. Yeah. But we have,

you know, you guide me, what do you want to look at? I mean, I'm looking from top to bottom. So,

um, I love that. I mean, the, I love how like at the top there's like the KPIs cause like as a

founder, I just want to know like, okay, what is happening here? Are we on target? Are we, you know,

behind? I probably in the future would want to actually have like a, I can, I guess it's called

conditional or conditional or whatever. Like, okay, we're behind schedule here. We're behind target.

Like, um, and then eventually if you had an integration, I would be like, you know,

if behind target, then post to Slack, right. Saying, you know, to our, uh, finance, to our sales

team that like, we need more leads to come in. Right. Yeah. Uh, yeah. I mean, totally. Um,

and we'll flip it through. I go into the analysis. All right. So we have conditional formatting on your,

um, on your hypothetical employees here. Um, it looks like it shows, you know, 70s in orange.

So it, it's more, it's more brutal of a manager than you are. It basically assumed if you are high,

if you're high utilization, that's green, that's the best case. Um, below 78 painted as red here.

Um, did department summaries. And then again, here was the original data. Um, and sort of like the

initial drivers. I mean, dude, this is insane. I know you're probably numb to this, but this is

insane. Yeah, I'm numb to it. Actually, to be honest, I'm like a little bothered that the earlier

live demo that was, is like weaker than it usually is. This is crazy. Like we took an idea that has been

in my head for a while and we created that in a few minutes and it looks great and it's color coded

and it, it's simple and it's clean. Yeah. I appreciate it. Um, what we can do for you also

is like check it. So you can just like create a file and I'll call it Greg's dream, create a share link.

Um, and now you can actually take this and you can not just see the file, but you can see like the

entire history. You can just edit it from there on. Um, and then the other thing you can do is like

export it. So, you know, Greg, and now it's in my documents and like, you would never know again

that it was in shortcut. Um, before we wrap up, I want to ask,

you know, why, why should someone try shortcut? Should, you know, should they wait or should they

try now? Like, you know, why, why should any founder or, you know, be, be, be using this product

right now? Yeah. Um, shortcut is for the billions of people who use Excel. Um, among them, there's

like two types, the people who are really good at Excel and use it a lot. They should use it because

it takes hours of work and makes it truly like I showed here, you know, 10, 15 minutes. Then there's

the people who are more like yourself who have to use Excel, but you're not Excel experts.

It makes you an instant Excel expert, right? You could now create this, um, and you will speak to

it in just plain English. And not only is it faster, but it's now also better than you at Excel.

Hmm. And is it, is it live? Like, I mean, by the time this comes out, is it, will it be live?

By the time this is out, it will be live. Yes. Okay. Cool. Okay. And is it from a pricing

perspective? Like what does it cost? Yeah. Right now we're charging $40 a month for the pro plan and

200 for the max plan, uh, max plan actually, which I haven't shared contains the analyst beta.

So the analyst beta, you can actually just directly email it and say, Hey, I need 10 different things

at once. And it's 10 X parallel. So now it's not just 10 times faster than your analyst,

but you can have 10 of them at a time. Um, which I think for enterprises has been like the big feedback

is they just want to hire this thing already. Um, so that's, so that's, that's where that,

that's where the pricing is, is a little different there. Cool. Yeah. I think that's,

it's probably where a lot, I mean, that's, that's where a lot of AI startups are going.

Like they have like kind of a more entry level and then they have like a few hundred dollars

a month analyst type of a product. Yeah. Um, it's a fun time to be building an AI,

but you have to be, you know, the, the ground truth changes a lot and that will change the pricing.

Of course that like, this is very token hungry. You watched how many times it had to correct itself.

Yeah. Um, but as these costs fall, so does our pricing strategy.

And, and just to summarize, like if people want to get the most out of shortcut, they want to be an

instant Excel, super Excel person. Like, what do you recommend to them to, to get the most out of the

product? Um, immediately just go to try shortcut.ai. There's no other pages. It just loads it up and

try a prompt for free. Find out how it would be valuable to you. Um, and again, um, do the

hardest thing and prove to yourself that like, it can take just about anything if you're specific

enough in your prompt. Cool. Nico, thanks for showing it, showing it off. I appreciate you.

Yeah, I know. My pleasure, Greg. Later. See ya. Bye.

Clips

No clips yet

Select text above to create your first clip

Loading connections...

Reflect

How does this connect to something you already know?

Press Cmd+Enter to submit