July 31, 2024 • 21 mins
Anthony Karls of Rocket Clicks and Casey Shea discuss how AI, particularly ChatGPT, can boost small business productivity by 40%. Learn about the evolution of GPT, practical use cases, and how to create tailored AI tools to streamline tasks like resume screening.
00:00 Introduction to Revenue Road
00:31 Understanding AI and ChatGPT
02:42 Impact of AI on Small Businesses
04:20 Five Key Tips for Using ChatGPT
07:24 Live Demonstration: Using ChatGPT for SEO
12:30 Creating Custom GPTs for Business Tasks
19:59 Conclusion and Final Thoughts
Check out our blog here!
#DigitalMarketing #Sales #BusinessGrowth
Curious to discover your personalized roadmap to scaling a law firm, no matter where you are in the business?
Follow these steps:
1. BOOK A FREE 30-MINUTE AUDIT WITH US: https://rocketclicks.com/schedule-a-family-law-quick-audit/
2. CONNECT WITH US:
LinkedIn: https://www.linkedin.com/in/anthonykarls/
https://www.linkedin.com/company/rocket-clicks
Facebook: http://facebook.com/2311.karls.anthony
http://facebook.com/RocketClicks
Instagram: http://instagram.com/karls.anthony
https://www.instagram.com/rocketclicks/
3. TELL ME WHAT YOU WANT:
Tell me in the comments if you liked this podcast and what other kinds of topics you would like to see.
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
Anthony Karls (00:01):
All right.
Welcome, welcome.
So this is Revenue Road backwhere we talk about sales and
marketing for localentrepreneurs.
I'm Anthony Carls, president ofRocketClicks.
So today I'm here with CaseyShea.
So last time we talked withCasey, we talked about technical
SEO.
mentioned in that video thathe's also one of our.
AI champions here atRocketClicks.
(00:21):
so we're gonna be, we're gonnabe tapping him about that today.
So we're just going to introducethe topic.
We're going to talk a little bitabout it.
he's going to give us somepretty cool use cases.
You learn something.
So we're talking about AI today.
so before we jump in and kind ofdo our little show and tell.
So what is AI?
What's chat GPT?
(00:41):
Like, where did it come from?
What is this thing?
Everybody's, everybody thinksit's brand new.
Cool.
I know you have differentperspective on it.
You gave a great presentation tothe U.
S.
community that we presented to acouple months ago.
What's AI?
Tell me about it.
Casey Shea (00:55):
So basically AI it's not in the sense of sci fi
movies, Terminator, Skynet, youknow, is going to be unleashed.
Basically what it is it's alarge language model.
What it does is, and this hasbeen around for decades.
It's been used since thebeginning of the internet.
I mean, it's been around sincethe eighties, really.
They've been using Largelanguage models.
(01:17):
And what it does is it justpredicts the next word, the next
character of a sentence.
Anthony Karls (01:23):
So how does that differ from what exists today?
So this is kind of, it's beenaround forever.
So like, why is everybody soexcited about JetGPT as an
example?
That's what we're going to usetoday.
Casey Shea (01:35):
So some things changed back in 2017 when open
AI they took a large languagemodel and they just pumped it
full of a whole bunch ofinformation.
It was like over 2000 books.
And then they also took, I thinkit was around 83 million reviews
off Amazon.
And they just wanted to see whatit would do.
And then all of a sudden.
This pre trained transformer, oras we know, a generative pre
(01:58):
trained transformer, GPT, itstarted to figure things out on
its own.
And it started to figure outlike the emotion behind certain
words.
It began to think, and thenthey're like, all right, well,
what if we put more informationfrom the internet into this
thing, and it just continued togrow and get smarter and smarter
as they did this.
Anthony Karls (02:19):
Okay.
So, so basically it went from anLLM.
a more advanced LLM where it'skind of thinking kind of putting
a lot of things together andcontextualizing it based on all
of the information that itpotentially has.
It's kind of what I heard yousay.
Casey Shea (02:35):
Exactly.
It's just, it's starting tothink on its own, not quite
Skynet, but it's getting there.
Anthony Karls (02:41):
Nice.
Okay.
So on revenue roadmap, we talkabout things that are impactful
to understanding that will drivea small businesses revenue.
So like, how does this fit in?
Okay.
To, to that what is, what doesthat look like?
Like, why should I consider thisas a small business owner?
I have a small team.
We have a pretty good businessthat we're running.
(03:02):
Like, why should I look at chatGPT as something to use?
Casey Shea (03:07):
The biggest reason why is just reflecting on a
couple of studies that have beenrecently done fall of last year
with Stanford and Harvard.
They took individuals from justany small business, put them in
a room.
No experience whatsoever withchat GPT with any kind of AI.
They gave them just a quick runthrough, just like the five
basics that we're going to kindof talk over today.
(03:28):
And with that, they saw a 40percent increase in
productivity.
So just within a week of justplaying around with it and with
no prior knowledge whatsoever,40 percent increase.
I mean, I'm pretty sure anybusiness would love to see a, an
increase like that.
Anthony Karls (03:43):
Yeah, I'd agree.
Okay.
So that's, so it's impactful.
and it's only getting better.
So I know it's made a, fromthree to four was a big jump.
I don't know if five's comingout this year or not.
I've.
Recently heard owner CEO of openAI talk about kind of when he
thinks five is going to come outand that's coming out soon ish.
So we'll see, but that oneshould be better than four.
(04:06):
So we'll continue, but allright.
So let's talk about, you see,you mentioned there's five
things.
So there's five things that,they gave these small business
owners in this study that madethem 40 percent more effective.
So what were those?
What did they.
Like, how do I use this thing?
How do I start thinking aboutit?
Casey Shea (04:20):
Basically what they did is they just ran through the
five most important ways tospeak to an LLM or a GPT.
Those five things are going tobe.
First and foremost, how are yougoing to engage with this?
You have to give it some kind ofrole.
What is it doing?
What do you want it to be?
You want it to be an expert inmarketing, advertisement, SEO,
(04:41):
whatever it is.
It could be a recruiter.
It just needs some kind of rolethat it can really start to.
Refine its knowledge into,because you got to keep in mind,
this has the entire collectiveinternet in its knowledge base
from, I think it was April of2023.
So it's a lot to figure out.
So it needs a specific role.
Anthony Karls (05:01):
It identifies role.
Okay.
What's next?
Casey Shea (05:04):
Second one depending on this one is kind of, it's
optional.
I always say, so this is whatkind of tone do you want it to
speak in?
So if you're breaking down somelike technical jargon or
something like that, that youhave no understanding of, you
got to say, Hey, speak to melike I'm 10 years old and I know
nothing about tech.
So give it some kind of tone.
(05:24):
And then also if it's writing anemail for you or a report or
something like that, you want itto have more of a professional
tone, or sometimes you want itmore conversational if it's a
friend or a coworker.
Anthony Karls (05:36):
So who am I?
What's my role?
Okay.
And how should I speak back toyou?
What's my, what's the tone youwant this back in?
So what else?
Casey Shea (05:45):
Ask, it'd be very specific.
It needs to know what it'sdoing.
It doesn't need, Hey, can youplease do this?
And I'd really like it if youdid that.
Nope, this is your littlerobotic slave.
You just tell it what it needsto be done in as few words as
possible, but also as specificas possible,
Anthony Karls (06:03):
So who am I?
What's the tone you want toreceive it in?
And what's the task?
What's number four?
Casey Shea (06:08):
ask questions, I can guarantee you that the first
result is not going to beexactly what you want if it
does, Hey, like you're doingbetter than me most days.
But.
Ask it questions just like it'ssomeone that you're training,
someone that's new on the job.
Someone who's not very familiarwith the project that you're
working on.
Talk to it conversationally,like it is a person.
(06:28):
Once again, though, you don'tneed to have all the manners and
the fillers and things likethat.
Just get right to the point,
Anthony Karls (06:35):
Okay.
And then what's number five?
So ask the questions is numberfour.
What's number five.
Casey Shea (06:39):
Reworking your prompt.
So sometimes it's just, you canhave a conversation.
You can keep talking to it.
You can keep asking questionsabout what it's giving you.
But sometimes you just need tostart from the beginning and
rewrite the directions that youinitially gave it.
The other one that kind ofblends in with five is also
understanding.
GPT and AI has a really shortmemory right now.
(07:00):
So if you have a big, longconversation, maybe you're going
through 50 different resumes,you know, that's a lot for it to
handle and remember through afull conversation.
So there's certain points whereyou want to start over with the
conversation because it has alimited memory.
So you want to make sure thatyou start over and you don't go
out too long.
Anthony Karls (07:19):
Okay.
Got it.
Okay.
So that's the useful.
So how do you use it?
So give us an example, show ushow you're actually doing this.
So pull us up on, on the screen.
Let's do a little show and tell.
Let's do a little mad scienceexperiment with Casey.
So we can show you off a littlebit.
Casey Shea (07:37):
So this is something that I actually just used
earlier this week.
So what I did, I gave it a role.
It's an expert in SEO.
And then what I wanted it to do,I wanted it to read and analyze.
This page right here, it's goingto go on the internet.
It's going to look at it.
And then what do I want out ofit?
I want specific contentopportunities.
(07:59):
I want to know what is donepoorly and what needs to be
optimized.
This is just surface level.
What's that?
Anthony Karls (08:07):
you enter, what is what is SEO Sage?
Casey Shea (08:10):
So,
Anthony Karls (08:10):
chat GPT, so what is this?
Casey Shea (08:12):
so Sage is going to be something this really shows
the capabilities of what youhave at your fingertips with a
little bit of work, a little bitof prompting and just a little
bit of hands on.
So with.
GPT, you are able to go in andcreate your own GPT that gives
you step by step, and you cancontinue to just fill it with
knowledge, instructions.
(08:33):
With my SEO Sage, I've got anumber of different documents
in, in the back end of it thathave everything from Google's
guidelines, To what it wants outof the search results, which is
163 pages that I'm not going toread, but my AI will do it for
me as it's going throughcontent.
And it will reflect on thedocumentation when it's giving
(08:53):
me answers.
So this is my sage for SEO.
Anthony Karls (08:57):
Got it.
So this is basically a, this ison open AI, right?
Or chat GPT and you've createdyour own version of it to do
more specific work.
probably need a shirt.
So in this example, you probablydon't need as long of a prop
cause it's got a big reservoirof information cause it
Casey Shea (09:15):
Yeah.
Anthony Karls (09:16):
it is and it's supposed to do.
Casey Shea (09:18):
So with this one, it's a very it's built to be
just a general expert.
And SEO.
So therefore my prompts for thisare very short.
Otherwise with something likethis, I would have to say,
you're an expert in SEO.
Here's the project that we'reworking on, you know, giving it
some more context behind likeexactly what it is so it can
refine what its task and whathis job is.
(09:40):
But with that, I've got italready done in the backend.
So this simplifies it.
And then in the future, I canjust go into my left menu and I
can just click it for whatevertasks that I want in the future
and not have to redo the promptevery time.
Anthony Karls (09:53):
So what is.
So that's super cool.
I got a question about thatafter.
So what did it do?
What are we trying to do here?
What question did you ask it?
You gave it what?
Casey Shea (10:01):
So I wanted to know what content opportunities there
were on this specific page, soon this website with this
specific page, which is theircommercial page and then it also
included a link just in case Iwanted to click it myself.
Okay.
And then it gave me just somehigh level specific content
opportunities, certain areas ofoptimizations, and keeping in
(10:23):
mind that this is reflectingstrictly on exactly what Google
asks us for.
So if you've heard of EAT, ifyou've heard of the guidelines
that Google continues to putout, this is reading that.
And then it's reading the pageand then it's putting them
together.
And then as far as, you know,other business owners, this
might be a bunch of technicaljargon, you know, maybe you want
(10:45):
to run this on your own website,but you don't understand SEO,
jargon, nerd talk, anything likethat.
So, explain it to me.
I know.
Explain to me I have no ideawhat digital marketing is
Anthony Karls (11:04):
Okay.
Casey Shea (11:05):
and it's going to start getting a little bit of
goofy.
So you can continue to simplifyit, refine it in a way that you
can understand it.
So this is really useful,especially if you have really
long documents, say it's acontract or something like that.
You can load this contract intoGPT, give it the specific role,
the specific instructions andwhat you want to, what you want
(11:28):
out of it.
And it's going to produce that,and it can continue to refine it
more and more as you're askingquestions and getting exactly
the result that you want out ofit.
Anthony Karls (11:37):
Okay.
So this is, this example, thisis great for you and kind of,
you've been able to downloadyour years of information and
like you're thinking about SEOinto this, and then it can can
be your admin assistant fordoing some initial research,
which is awesome.
How would I use this as abusiness owner?
(12:00):
How would I use chat GPT as abusiness owner?
What's a, like a use case wouldbe like it's really hard for me
to like screen resumes.
When I post a job, I gethundreds of resumes.
I got to look through all ofthem.
It's a pain in the butt.
I don't have time to lookthrough all of them.
I'm probably missing stuff thatI should be catching.
I gave you that as a potentialassignment.
So what did, like, how did youthink about that on the
(12:20):
documentation we have that wehave our own admins run?
So like, how can we make thatsimpler and use chat GPT to you
to do it?
Casey Shea (12:30):
So, first and foremost, let's start over, and
let's go out of my Sage, andlet's just go with regular GPT
4.
One thing you may be asking, GPT3.
5, What's the difference?
3.
5.
I use that for like maybeorganizing some numbers,
calculating some things, verysimple things.
(12:51):
Think of it like a middle schooleducation where in chat GPT
four, that's more of a, itactually, it ranks in the top 10
percentile for collegegraduates.
So it passes the bar exam.
It passes the medical exam.
I like to go with four, butthere is a limit as far as how
many times you can use it withina time span, just because it
uses a lot of computing power.
Anthony Karls (13:13):
Got it.
Casey Shea (13:14):
Something that we worked on at RocketClicks for
screening resumes is creatingpretty much like a checklist
that it gives it once again,very specific instructions for
when it's scanning throughresumes, and this is something
that a recruiter, you know,could do, I'm pretty sure that
nobody Enjoy scanning throughresumes, trying to give it a
(13:36):
point system for each one.
This is a lot to go through andit's a really long document.
So one way you can do this, ifyou don't create your own is
just copying this, bringing itright up.
Yeah,
Anthony Karls (13:52):
admin would from their HR person or maybe you're
a smaller business.
You don't have an HR personMaybe that's you but you're
responsible for recruiting.
So like maybe it's yourparalegal.
Maybe it's your admin.
Here's the things We're lookingfor Go look at all these
resumes, which is that's a, thatsucks for a job, right?
Casey Shea (14:08):
not be happy with that job.
That's for sure.
But luckily enough, we can takeall this stuff right here.
And just, I mean, that's a lotto go through.
So what it's going to do is it'sgoing to run it back through
just to make sure that it has acomplete understanding of what
you're asking for.
(14:29):
So it's breaking everything downas we can see.
And then what we want to do isput in just a little dummy
resume that I just pulled off ofGoogle as just a sample resume.
(14:51):
And all I did is drop it inthere.
It already has the prompt.
It already knows what to do.
I dropped it in there and it'sgoing to break it down according
to exactly what our originalprompt had.
So the way that it's scoring it,the way that it's looking at
different PPC strategistcriteria and really assessing
how they fit into this role.
(15:14):
And then at the end.
Gave it a total score of six.
You can continue to askquestions.
So why only a six?
And that's also why you got todouble check too, because it
missed one.
It looks like
Anthony Karls (15:30):
Nice.
So it's basically taking theinstructions and then it's
taking the instructions andcomparing it with the resume.
And it's basically giving you ascore.
Casey Shea (15:37):
exactly.
And then something that you cando similar to what I did.
Anthony Karls (15:41):
all you did was log it into, all you did was
load it into, load the PDF hereand that for you.
Casey Shea (15:48):
Yep.
I just dropped the PDF.
First I dropped in the promptand then it ran back what the
instructions were.
I threw in the PDF of the fileand this can, it can take, you
know, PDF, TXT, a number ofdifferent files, word files.
It'll tell you if it can't readit and then you can format it
accordingly.
Anthony Karls (16:07):
Okay.
So what if, how do I, so how doI create, How do I create the
expert stage or whatever youwould like to call it so I don't
have to reprompt it and I cancontinue to feed it better and
better information and keeptraining it on screening these.
What does that process looklike?
Casey Shea (16:22):
you'll see right here.
Explore GPTs.
There's a number of GPTs thatpeople have already made.
So for all I know, there'sprobably one already made.
You can search for it, but Iwant it specific to this exact
way that our company does it.
So with that in this top corner,we're going to create it.
And this is where it walks youthrough everything.
(16:43):
So now that I already have thisprompt document, so I'm going to
go right into configure rightaway.
And I'm going to drop that inthere.
So I'm going to take this, I'mgoing to download it.
So I'm going to download it intoa TXT file, just because I don't
need to worry about any kind offormatting or something like
that.
(17:04):
And TXT is really small file forit.
And then we're going to upload,just going to hit prompts, and
then it'll load up in there.
And then that's where you goover to the create.
Usually what I'll just do istake this first prompt just so
(17:25):
it has that recognition rightaway.
And then you're going to put itin here.
Anthony Karls (17:31):
So this is kind of the 5 steps that we talked
about earlier.
Casey Shea (17:34):
Exactly.
So act as a human resourcerecruiting specialist and then
breaking down all of the steps.
And then you'll see it'supdating the GPT.
And once it's done updating, youcan continue to refine it.
You can continue to come back tothis.
You can save it.
You can share it with yourcoworkers.
You can share it with whoever.
(17:56):
But it walks you through everystep of the way.
And then just to test it outtoo, while it's asking me all
these questions that.
Oh, it's going to make me do it.
Yes.
Anthony Karls (18:07):
so what did it make you do?
Casey Shea (18:09):
Let me give it a name.
Gives it a name.
Gives it a picture.
It's going to say, is thispicture great?
I'll say yes.
It's great.
Anthony Karls (18:19):
so it suggested a name and then now it's going to
suggest a picture.
Casey Shea (18:23):
Yeah.
Anthony Karls (18:23):
It's going to create your, the same thing that
we hit, we saw earlier with yourSEO sage.
Casey Shea (18:27):
Yep.
So this just has some computermonitor.
I have a similar one, but it'ssome old lady that's in some
dark room because that's what Iimagined when I think of someone
just scanning.
And then this is where it'lljust continue breaking things
down further and further as yougo.
Here's where you can test it outon the right hand side, just to
(18:48):
make sure that it's operatingthe way that you want it to, if
it doesn't.
You go on the left hand side andrefine it further.
Tell it exactly what it didwrong.
That's something that I find alot of people don't do as
they're like, ah, it's wrongagain.
I want blah, blah, blah.
And they'll just repeat theprompt in a different way where
it's you have to just like achild, you have to point out
(19:08):
exactly what happened, what itdid wrong and what you were
expecting out of it.
So you have to walk it throughjust like you're training an
individual.
And then as we can see.
All I did is drop in the PDF.
I gave it no promptingwhatsoever, and it's breaking it
all down for me.
And then this way I don't everhave to put in a prompt ever
again.
I can just open this GPT, dropin a resume.
(19:31):
I can drop in several resumes ata time and it'll go through each
one of them.
Anthony Karls (19:36):
Nice.
So it's going to just, it'sgoing to come up and score it.
Now this is basically a new app,a new GPT app that you could
use.
Casey Shea (19:44):
Yep.
Just created it.
So this all works.
And then right here, you canshare it.
You can have only me link.
You can even throw it in thestore if you feel like it.
I'm just going to say anyonewith a link and then it's saved
forever.
Anthony Karls (19:58):
Cool.
Well, this was awesome.
This was awesome.
Casey.
Really appreciate you walking usthrough this.
It seems like there's hugeopportunities here.
You just kind of have to sitdown and think about it a little
bit and.
I think I think when I wastrained on this the instructor
said, you got to do a lot ofFAFO.
want to know what that means?
Go Google it.
You'll find some funny videos.
I think that's honestly what youwere talking about and you just
(20:19):
got to keep playing with it andimproving it and you'll see some
pretty cool results.
So appreciate your time andguidance here.
Any other last suggestions onthinking about using AI or chat
GPT for our audience here?
Casey Shea (20:32):
The biggest thing is use it for everything.
Just even if you don't thinkthat you need to getting used to
it, because this is going to beintegrated into everything that
we touch.
So it's going to be.
Everywhere.
So getting used to how to use iton a day to day basis, but then
also keep it simple.
The biggest thing that I alwayssee people doing wrong is they
(20:52):
over complicate the prompt, justshort and as simple as possible.
And you're going to get the bestresults.
Anthony Karls (20:59):
Well, thank you, Casey.
Appreciate it.
Casey Shea (21:01):
Yeah.
Thank you.
All right.
Welcome, welcome.
So this is Revenue Road backwhere we talk about sales and
marketing for localentrepreneurs.
I'm Anthony Carls, president ofRocketClicks.
So today I'm here with CaseyShea.
So last time we talked withCasey, we talked about technical
SEO.
mentioned in that video thathe's also one of our.
AI champions here atRocketClicks.
(00:21):
so we're gonna be, we're gonnabe tapping him about that today.
So we're just going to introducethe topic.
We're going to talk a little bitabout it.
he's going to give us somepretty cool use cases.
You learn something.
So we're talking about AI today.
so before we jump in and kind ofdo our little show and tell.
So what is AI?
What's chat GPT?
(00:41):
Like, where did it come from?
What is this thing?
Everybody's, everybody thinksit's brand new.
Cool.
I know you have differentperspective on it.
You gave a great presentation tothe U.
S.
community that we presented to acouple months ago.
What's AI?
Tell me about it.
Casey Shea (00:55):
So basically AI it's not in the sense of sci fi
movies, Terminator, Skynet, youknow, is going to be unleashed.
Basically what it is it's alarge language model.
What it does is, and this hasbeen around for decades.
It's been used since thebeginning of the internet.
I mean, it's been around sincethe eighties, really.
They've been using Largelanguage models.
(01:17):
And what it does is it justpredicts the next word, the next
character of a sentence.
Anthony Karls (01:23):
So how does that differ from what exists today?
So this is kind of, it's beenaround forever.
So like, why is everybody soexcited about JetGPT as an
example?
That's what we're going to usetoday.
Casey Shea (01:35):
So some things changed back in 2017 when open
AI they took a large languagemodel and they just pumped it
full of a whole bunch ofinformation.
It was like over 2000 books.
And then they also took, I thinkit was around 83 million reviews
off Amazon.
And they just wanted to see whatit would do.
And then all of a sudden.
This pre trained transformer, oras we know, a generative pre
(01:58):
trained transformer, GPT, itstarted to figure things out on
its own.
And it started to figure outlike the emotion behind certain
words.
It began to think, and thenthey're like, all right, well,
what if we put more informationfrom the internet into this
thing, and it just continued togrow and get smarter and smarter
as they did this.
Anthony Karls (02:19):
Okay.
So, so basically it went from anLLM.
a more advanced LLM where it'skind of thinking kind of putting
a lot of things together andcontextualizing it based on all
of the information that itpotentially has.
It's kind of what I heard yousay.
Casey Shea (02:35):
Exactly.
It's just, it's starting tothink on its own, not quite
Skynet, but it's getting there.
Anthony Karls (02:41):
Nice.
Okay.
So on revenue roadmap, we talkabout things that are impactful
to understanding that will drivea small businesses revenue.
So like, how does this fit in?
Okay.
To, to that what is, what doesthat look like?
Like, why should I consider thisas a small business owner?
I have a small team.
We have a pretty good businessthat we're running.
(03:02):
Like, why should I look at chatGPT as something to use?
Casey Shea (03:07):
The biggest reason why is just reflecting on a
couple of studies that have beenrecently done fall of last year
with Stanford and Harvard.
They took individuals from justany small business, put them in
a room.
No experience whatsoever withchat GPT with any kind of AI.
They gave them just a quick runthrough, just like the five
basics that we're going to kindof talk over today.
(03:28):
And with that, they saw a 40percent increase in
productivity.
So just within a week of justplaying around with it and with
no prior knowledge whatsoever,40 percent increase.
I mean, I'm pretty sure anybusiness would love to see a, an
increase like that.
Anthony Karls (03:43):
Yeah, I'd agree.
Okay.
So that's, so it's impactful.
and it's only getting better.
So I know it's made a, fromthree to four was a big jump.
I don't know if five's comingout this year or not.
I've.
Recently heard owner CEO of openAI talk about kind of when he
thinks five is going to come outand that's coming out soon ish.
So we'll see, but that oneshould be better than four.
(04:06):
So we'll continue, but allright.
So let's talk about, you see,you mentioned there's five
things.
So there's five things that,they gave these small business
owners in this study that madethem 40 percent more effective.
So what were those?
What did they.
Like, how do I use this thing?
How do I start thinking aboutit?
Casey Shea (04:20):
Basically what they did is they just ran through the
five most important ways tospeak to an LLM or a GPT.
Those five things are going tobe.
First and foremost, how are yougoing to engage with this?
You have to give it some kind ofrole.
What is it doing?
What do you want it to be?
You want it to be an expert inmarketing, advertisement, SEO,
(04:41):
whatever it is.
It could be a recruiter.
It just needs some kind of rolethat it can really start to.
Refine its knowledge into,because you got to keep in mind,
this has the entire collectiveinternet in its knowledge base
from, I think it was April of2023.
So it's a lot to figure out.
So it needs a specific role.
Anthony Karls (05:01):
It identifies role.
Okay.
What's next?
Casey Shea (05:04):
Second one depending on this one is kind of, it's
optional.
I always say, so this is whatkind of tone do you want it to
speak in?
So if you're breaking down somelike technical jargon or
something like that, that youhave no understanding of, you
got to say, Hey, speak to melike I'm 10 years old and I know
nothing about tech.
So give it some kind of tone.
(05:24):
And then also if it's writing anemail for you or a report or
something like that, you want itto have more of a professional
tone, or sometimes you want itmore conversational if it's a
friend or a coworker.
Anthony Karls (05:36):
So who am I?
What's my role?
Okay.
And how should I speak back toyou?
What's my, what's the tone youwant this back in?
So what else?
Casey Shea (05:45):
Ask, it'd be very specific.
It needs to know what it'sdoing.
It doesn't need, Hey, can youplease do this?
And I'd really like it if youdid that.
Nope, this is your littlerobotic slave.
You just tell it what it needsto be done in as few words as
possible, but also as specificas possible,
Anthony Karls (06:03):
So who am I?
What's the tone you want toreceive it in?
And what's the task?
What's number four?
Casey Shea (06:08):
ask questions, I can guarantee you that the first
result is not going to beexactly what you want if it
does, Hey, like you're doingbetter than me most days.
But.
Ask it questions just like it'ssomeone that you're training,
someone that's new on the job.
Someone who's not very familiarwith the project that you're
working on.
Talk to it conversationally,like it is a person.
(06:28):
Once again, though, you don'tneed to have all the manners and
the fillers and things likethat.
Just get right to the point,
Anthony Karls (06:35):
Okay.
And then what's number five?
So ask the questions is numberfour.
What's number five.
Casey Shea (06:39):
Reworking your prompt.
So sometimes it's just, you canhave a conversation.
You can keep talking to it.
You can keep asking questionsabout what it's giving you.
But sometimes you just need tostart from the beginning and
rewrite the directions that youinitially gave it.
The other one that kind ofblends in with five is also
understanding.
GPT and AI has a really shortmemory right now.
(07:00):
So if you have a big, longconversation, maybe you're going
through 50 different resumes,you know, that's a lot for it to
handle and remember through afull conversation.
So there's certain points whereyou want to start over with the
conversation because it has alimited memory.
So you want to make sure thatyou start over and you don't go
out too long.
Anthony Karls (07:19):
Okay.
Got it.
Okay.
So that's the useful.
So how do you use it?
So give us an example, show ushow you're actually doing this.
So pull us up on, on the screen.
Let's do a little show and tell.
Let's do a little mad scienceexperiment with Casey.
So we can show you off a littlebit.
Casey Shea (07:37):
So this is something that I actually just used
earlier this week.
So what I did, I gave it a role.
It's an expert in SEO.
And then what I wanted it to do,I wanted it to read and analyze.
This page right here, it's goingto go on the internet.
It's going to look at it.
And then what do I want out ofit?
I want specific contentopportunities.
(07:59):
I want to know what is donepoorly and what needs to be
optimized.
This is just surface level.
What's that?
Anthony Karls (08:07):
you enter, what is what is SEO Sage?
Casey Shea (08:10):
So,
Anthony Karls (08:10):
chat GPT, so what is this?
Casey Shea (08:12):
so Sage is going to be something this really shows
the capabilities of what youhave at your fingertips with a
little bit of work, a little bitof prompting and just a little
bit of hands on.
So with.
GPT, you are able to go in andcreate your own GPT that gives
you step by step, and you cancontinue to just fill it with
knowledge, instructions.
(08:33):
With my SEO Sage, I've got anumber of different documents
in, in the back end of it thathave everything from Google's
guidelines, To what it wants outof the search results, which is
163 pages that I'm not going toread, but my AI will do it for
me as it's going throughcontent.
And it will reflect on thedocumentation when it's giving
(08:53):
me answers.
So this is my sage for SEO.
Anthony Karls (08:57):
Got it.
So this is basically a, this ison open AI, right?
Or chat GPT and you've createdyour own version of it to do
more specific work.
probably need a shirt.
So in this example, you probablydon't need as long of a prop
cause it's got a big reservoirof information cause it
Casey Shea (09:15):
Yeah.
Anthony Karls (09:16):
it is and it's supposed to do.
Casey Shea (09:18):
So with this one, it's a very it's built to be
just a general expert.
And SEO.
So therefore my prompts for thisare very short.
Otherwise with something likethis, I would have to say,
you're an expert in SEO.
Here's the project that we'reworking on, you know, giving it
some more context behind likeexactly what it is so it can
refine what its task and whathis job is.
(09:40):
But with that, I've got italready done in the backend.
So this simplifies it.
And then in the future, I canjust go into my left menu and I
can just click it for whatevertasks that I want in the future
and not have to redo the promptevery time.
Anthony Karls (09:53):
So what is.
So that's super cool.
I got a question about thatafter.
So what did it do?
What are we trying to do here?
What question did you ask it?
You gave it what?
Casey Shea (10:01):
So I wanted to know what content opportunities there
were on this specific page, soon this website with this
specific page, which is theircommercial page and then it also
included a link just in case Iwanted to click it myself.
Okay.
And then it gave me just somehigh level specific content
opportunities, certain areas ofoptimizations, and keeping in
(10:23):
mind that this is reflectingstrictly on exactly what Google
asks us for.
So if you've heard of EAT, ifyou've heard of the guidelines
that Google continues to putout, this is reading that.
And then it's reading the pageand then it's putting them
together.
And then as far as, you know,other business owners, this
might be a bunch of technicaljargon, you know, maybe you want
(10:45):
to run this on your own website,but you don't understand SEO,
jargon, nerd talk, anything likethat.
So, explain it to me.
I know.
Explain to me I have no ideawhat digital marketing is
Anthony Karls (11:04):
Okay.
Casey Shea (11:05):
and it's going to start getting a little bit of
goofy.
So you can continue to simplifyit, refine it in a way that you
can understand it.
So this is really useful,especially if you have really
long documents, say it's acontract or something like that.
You can load this contract intoGPT, give it the specific role,
the specific instructions andwhat you want to, what you want
(11:28):
out of it.
And it's going to produce that,and it can continue to refine it
more and more as you're askingquestions and getting exactly
the result that you want out ofit.
Anthony Karls (11:37):
Okay.
So this is, this example, thisis great for you and kind of,
you've been able to downloadyour years of information and
like you're thinking about SEOinto this, and then it can can
be your admin assistant fordoing some initial research,
which is awesome.
How would I use this as abusiness owner?
(12:00):
How would I use chat GPT as abusiness owner?
What's a, like a use case wouldbe like it's really hard for me
to like screen resumes.
When I post a job, I gethundreds of resumes.
I got to look through all ofthem.
It's a pain in the butt.
I don't have time to lookthrough all of them.
I'm probably missing stuff thatI should be catching.
I gave you that as a potentialassignment.
So what did, like, how did youthink about that on the
(12:20):
documentation we have that wehave our own admins run?
So like, how can we make thatsimpler and use chat GPT to you
to do it?
Casey Shea (12:30):
So, first and foremost, let's start over, and
let's go out of my Sage, andlet's just go with regular GPT
4.
One thing you may be asking, GPT3.
5, What's the difference?
3.
5.
I use that for like maybeorganizing some numbers,
calculating some things, verysimple things.
(12:51):
Think of it like a middle schooleducation where in chat GPT
four, that's more of a, itactually, it ranks in the top 10
percentile for collegegraduates.
So it passes the bar exam.
It passes the medical exam.
I like to go with four, butthere is a limit as far as how
many times you can use it withina time span, just because it
uses a lot of computing power.
Anthony Karls (13:13):
Got it.
Casey Shea (13:14):
Something that we worked on at RocketClicks for
screening resumes is creatingpretty much like a checklist
that it gives it once again,very specific instructions for
when it's scanning throughresumes, and this is something
that a recruiter, you know,could do, I'm pretty sure that
nobody Enjoy scanning throughresumes, trying to give it a
(13:36):
point system for each one.
This is a lot to go through andit's a really long document.
So one way you can do this, ifyou don't create your own is
just copying this, bringing itright up.
Yeah,
Anthony Karls (13:52):
admin would from their HR person or maybe you're
a smaller business.
You don't have an HR personMaybe that's you but you're
responsible for recruiting.
So like maybe it's yourparalegal.
Maybe it's your admin.
Here's the things We're lookingfor Go look at all these
resumes, which is that's a, thatsucks for a job, right?
Casey Shea (14:08):
not be happy with that job.
That's for sure.
But luckily enough, we can takeall this stuff right here.
And just, I mean, that's a lotto go through.
So what it's going to do is it'sgoing to run it back through
just to make sure that it has acomplete understanding of what
you're asking for.
(14:29):
So it's breaking everything downas we can see.
And then what we want to do isput in just a little dummy
resume that I just pulled off ofGoogle as just a sample resume.
(14:51):
And all I did is drop it inthere.
It already has the prompt.
It already knows what to do.
I dropped it in there and it'sgoing to break it down according
to exactly what our originalprompt had.
So the way that it's scoring it,the way that it's looking at
different PPC strategistcriteria and really assessing
how they fit into this role.
(15:14):
And then at the end.
Gave it a total score of six.
You can continue to askquestions.
So why only a six?
And that's also why you got todouble check too, because it
missed one.
It looks like
Anthony Karls (15:30):
Nice.
So it's basically taking theinstructions and then it's
taking the instructions andcomparing it with the resume.
And it's basically giving you ascore.
Casey Shea (15:37):
exactly.
And then something that you cando similar to what I did.
Anthony Karls (15:41):
all you did was log it into, all you did was
load it into, load the PDF hereand that for you.
Casey Shea (15:48):
Yep.
I just dropped the PDF.
First I dropped in the promptand then it ran back what the
instructions were.
I threw in the PDF of the fileand this can, it can take, you
know, PDF, TXT, a number ofdifferent files, word files.
It'll tell you if it can't readit and then you can format it
accordingly.
Anthony Karls (16:07):
Okay.
So what if, how do I, so how doI create, How do I create the
expert stage or whatever youwould like to call it so I don't
have to reprompt it and I cancontinue to feed it better and
better information and keeptraining it on screening these.
What does that process looklike?
Casey Shea (16:22):
you'll see right here.
Explore GPTs.
There's a number of GPTs thatpeople have already made.
So for all I know, there'sprobably one already made.
You can search for it, but Iwant it specific to this exact
way that our company does it.
So with that in this top corner,we're going to create it.
And this is where it walks youthrough everything.
(16:43):
So now that I already have thisprompt document, so I'm going to
go right into configure rightaway.
And I'm going to drop that inthere.
So I'm going to take this, I'mgoing to download it.
So I'm going to download it intoa TXT file, just because I don't
need to worry about any kind offormatting or something like
that.
(17:04):
And TXT is really small file forit.
And then we're going to upload,just going to hit prompts, and
then it'll load up in there.
And then that's where you goover to the create.
Usually what I'll just do istake this first prompt just so
(17:25):
it has that recognition rightaway.
And then you're going to put itin here.
Anthony Karls (17:31):
So this is kind of the 5 steps that we talked
about earlier.
Casey Shea (17:34):
Exactly.
So act as a human resourcerecruiting specialist and then
breaking down all of the steps.
And then you'll see it'supdating the GPT.
And once it's done updating, youcan continue to refine it.
You can continue to come back tothis.
You can save it.
You can share it with yourcoworkers.
You can share it with whoever.
(17:56):
But it walks you through everystep of the way.
And then just to test it outtoo, while it's asking me all
these questions that.
Oh, it's going to make me do it.
Yes.
Anthony Karls (18:07):
so what did it make you do?
Casey Shea (18:09):
Let me give it a name.
Gives it a name.
Gives it a picture.
It's going to say, is thispicture great?
I'll say yes.
It's great.
Anthony Karls (18:19):
so it suggested a name and then now it's going to
suggest a picture.
Casey Shea (18:23):
Yeah.
Anthony Karls (18:23):
It's going to create your, the same thing that
we hit, we saw earlier with yourSEO sage.
Casey Shea (18:27):
Yep.
So this just has some computermonitor.
I have a similar one, but it'ssome old lady that's in some
dark room because that's what Iimagined when I think of someone
just scanning.
And then this is where it'lljust continue breaking things
down further and further as yougo.
Here's where you can test it outon the right hand side, just to
(18:48):
make sure that it's operatingthe way that you want it to, if
it doesn't.
You go on the left hand side andrefine it further.
Tell it exactly what it didwrong.
That's something that I find alot of people don't do as
they're like, ah, it's wrongagain.
I want blah, blah, blah.
And they'll just repeat theprompt in a different way where
it's you have to just like achild, you have to point out
(19:08):
exactly what happened, what itdid wrong and what you were
expecting out of it.
So you have to walk it throughjust like you're training an
individual.
And then as we can see.
All I did is drop in the PDF.
I gave it no promptingwhatsoever, and it's breaking it
all down for me.
And then this way I don't everhave to put in a prompt ever
again.
I can just open this GPT, dropin a resume.
(19:31):
I can drop in several resumes ata time and it'll go through each
one of them.
Anthony Karls (19:36):
Nice.
So it's going to just, it'sgoing to come up and score it.
Now this is basically a new app,a new GPT app that you could
use.
Casey Shea (19:44):
Yep.
Just created it.
So this all works.
And then right here, you canshare it.
You can have only me link.
You can even throw it in thestore if you feel like it.
I'm just going to say anyonewith a link and then it's saved
forever.
Anthony Karls (19:58):
Cool.
Well, this was awesome.
This was awesome.
Casey.
Really appreciate you walking usthrough this.
It seems like there's hugeopportunities here.
You just kind of have to sitdown and think about it a little
bit and.
I think I think when I wastrained on this the instructor
said, you got to do a lot ofFAFO.
want to know what that means?
Go Google it.
You'll find some funny videos.
I think that's honestly what youwere talking about and you just
(20:19):
got to keep playing with it andimproving it and you'll see some
pretty cool results.
So appreciate your time andguidance here.
Any other last suggestions onthinking about using AI or chat
GPT for our audience here?
Casey Shea (20:32):
The biggest thing is use it for everything.
Just even if you don't thinkthat you need to getting used to
it, because this is going to beintegrated into everything that
we touch.
So it's going to be.
Everywhere.
So getting used to how to use iton a day to day basis, but then
also keep it simple.
The biggest thing that I alwayssee people doing wrong is they
(20:52):
over complicate the prompt, justshort and as simple as possible.
And you're going to get the bestresults.
Anthony Karls (20:59):
Well, thank you, Casey.
Appreciate it.
Casey Shea (21:01):
Yeah.
Thank you.
Popular Podcasts
Dateline NBC
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations. Follow now to get the latest episodes of Dateline NBC completely free, or subscribe to Dateline Premium for ad-free listening and exclusive bonus content: DatelinePremium.com
24/7 News: The Latest
The latest news in 4 minutes updated every hour, every day.
Therapy Gecko
An unlicensed lizard psychologist travels the universe talking to strangers about absolutely nothing. TO CALL THE GECKO: follow me on https://www.twitch.tv/lyleforever to get a notification for when I am taking calls. I am usually live Mondays, Wednesdays, and Fridays but lately a lot of other times too. I am a gecko.