December 24, 2024 • 24 mins
Link to this episode on YouTube: https://youtu.be/23MrFuVuMmg
In this episode, I give you an "over-the-shoulder" peek into using Google's NotebookLM to produce next week's podcast episode!
That is perhaps the most surprising feature of this amazing free tool. Besides that, it's great at summarizing documents or web pages for easy consumption and can be a great resource for you to have in your digital back pocket!
Chapters:
00:00 - Intro
07:21 - Using Google's NotebookLM
Shoutout to Marley Wagner and Bob London who did this LIVE at ChurnZero.
+++++++++++++++++
Like/Subscribe/Review:
If you are getting value from the show, please follow/subscribe so that you don't miss an episode and consider leaving us a review.
Website:
For more information about the show or to get in touch, visit DigitalCustomerSuccess.com.
Buy Alex a Cup of Coffee:
This show runs exclusively on caffeine - and lots of it. If you like what we're, consider supporting our habit by buying us a cup of coffee: https://bmc.link/dcsp
Thank you for all of your support!
The Digital Customer Success Podcast is hosted by Alex Turkovic
🎬 This content was edited by Lifetime Value Media.
Learn more at: https://www.lifetimevaluemedia.com
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
Speaker 1 (00:03):
Today I've got some over-the-shoulder AI fun for you
, so stay tuned.
Once again, welcome to theDigital Customer Experience
Podcast with me, alex Terkovich,so glad you could join us here
today and every week as weexplore how digital can help
enhance the customer andemployee experience.
My goal is to share what myguests and I have learned over
(00:23):
the years so that you can getthe insights that you need to
evolve your own digital programs.
If you'd like more info, needto get in touch or sign up for
the weekly companion newsletterthat has additional articles and
resources in it.
Go to digitalcustomersuccesscom.
For now, let's get started.
Greetings and welcome toepisode 84 of the digital cx
podcast, the show where we talkabout all things digital in CX,
(00:47):
and it's a solo episode 84,mainly because the next two
episodes are actually going tobe solo.
So 84, 85 are both going to besolo.
It is Christmas Eve today ifyou're listening live, or on day
of release, so Merry Christmasto those of you who celebrate.
Hopefully this is a time foryou to spend with family and
(01:11):
friends and loved ones and allof that, but I also recognize
that a lot of us need a littlebit of escape during this time
as well, so maybe I am part ofyour escape today, in which case
, thanks for joining me.
Today is going to be a littlebit different.
And be forewarned if you are aregular podcast listener in
(01:33):
other words you're listening tothe show, you're not watching it
on YouTube you may want to takea second to go find a screen or
go look for this episode onYouTube.
I will be putting a link in theshow notes below so you can get
to it pretty easily.
The reason for this is I'mgoing to do a little bit of
(01:54):
screen sharing today and we aregoing to have some fun with
Google's Notebook LM, which, ifyou haven't used it yet, is a
pretty cool Google product, alittle bit under the radar, uses
Google's Gemini platform toessentially do some
summarization of whatever youfeed it and also produces.
(02:17):
This feels really random to me,but it also gives you the
ability to produce a co-hostedpodcast episode with two a male
and a female voice banteringabout whatever it is you fed it
in terms of the sources, sowe're actually going to have
some fun with that today.
In this episode, we are goingto feed Notebook LM some sources
(02:42):
and do a little bit ofprompting, at which point.
We're going to ask it toproduce one of these podcast
episodes and on next week's showyou're going to hear the result
of that.
So you're going to hear theoutput of whatever it is we feed
it today.
So you're getting back-to-backsolo episodes.
Today is going to be nuts andbolts and over the shoulder and
(03:03):
next week is going to beliterally the output of whatever
it is we're working on today.
So, before we jump over into thescreen share, I thought it
would be good to spend a coupleof minutes just talking about
Notebook LM and use cases forNotebook LM, because essentially
, what it does is takes whateverinputs you give it.
It could be a website, it couldbe linked to a YouTube video,
(03:25):
it could be a document like aPDF or a text document that you
upload, it could be any numberof things that you feed it, and
it allows you to summarize thosedocuments and essentially have
a conversation with Notebook LMabout those documents, and then
you can pin those conversationsso that you can reference them
(03:46):
later.
It's really cool and it setsnotebook alum is different than,
let's say, chat gpt, forinstance, because of this
ability to summarize multipledocuments into one place and
then pinning those thingsessentially for for later.
So the obvious use case here issummarizing documents.
(04:10):
So if you have a swath ofdocuments, you can put those in
and summarize them.
So, for instance, you couldwell I suppose you could feed it
your knowledge base articles orsomething like that.
There's a limit, I think it's20 documents that you can upload
to it, but you can point it ata number of websites on the same
topic and then have aconversation with it to
(04:34):
summarize those things.
You can also use it to transformdocuments into something more
digestible, maybe turning a bookthat you wrote into an ebook or
a short version of something.
You can use it to analyzereports.
So if you have a bunch of datahanging around, you can use it
to essentially have aconversation with your data,
(04:55):
which is super cool.
And I mentioned earlier youcould summarize knowledge bases,
but you could also use it tocreate a knowledge base.
So if you have documentationthat's pretty broad on a
specific niche topic or a groupof topics, you could then use it
to essentially create outlinesor create the startings of
(05:20):
different knowledge basearticles.
One interesting use case ummight be uh, if you're if you're
an average cook, for instance,you could feed it your recipes
and have it be a place to storethose things and then use it to
basically query those recipes ifyou need some ideas about
things that you like doing, sothat you know there's just the.
(05:42):
It's one of those tools whereit's so kind of open-ended that
really the only limitation isyour creativity in actually
using it.
One of the things that Googledoes suggest that you can use it
for is fact-checking.
I'm on the fence about that,because I don't generally trust
generative AI or AI models to dothe fact-checking.
(06:04):
In fact, quite the opposite, Itend to fact-check the outputs
of generative AI.
But hey, you know, go play withit.
I wanted to at least provideyou with a couple of examples of
how you might use Notebook LM,either for your personal use or
within a team.
It's an incredibly powerfultool, so, without further delay,
(06:26):
let's get into it.
I'll do a little bit of screensharing and we'll get into
Notebook LM.
This isn't gonna be necessarilya tutorial like a full-blown
tutorial in Notebook LM, butwe're just gonna play around and
see what we come up with.
Hey, I wanna have a brief chatwith you about this show.
Did you know that roughly 60%of listeners aren't actually
subscribed to the show, onwhatever platform they're
(06:48):
listening to it on.
As you know, algorithms love,likes, follows, subscribes,
comments, all of that kind ofstuff.
So if you get value out of thecontent, you listen regularly
and you want to help others todiscover the content as well,
please go ahead and follow theshow, leave a comment, leave a
review.
Anything that you wanna dothere really helps us to grow
(07:10):
organically as a show.
And while you're at it, go signup for the companion newsletter
that goes out every week atdigitalcustomersuccesscom.
Now back to the show.
All right, so I've gone tonotebooklmgooglecom and sign in
with your profile.
Pretty straightforward.
I've deleted the ones that I'veput in here just to show you
(07:32):
what the experience is right offthe bat, but it does prompt you
to create your first notebookand talks about uploading
documents and havingconversations with them by
having, you know, convert themto useful documentation.
What it doesn't tell you abouthere is the fact that it can
produce this miraculous likepodcast episode that a lot of
(07:53):
people are talking about.
By the way, I can't take fullcredit for this and I didn't
discover this by any means.
It's pretty well known thingnow that you can create these
podcast episodes from NotebookLM, but most notably, marley
Wagner and Bob London talkedabout this at Churn Zero and
(08:14):
actually produced an episodelive during their session, which
was super cool.
Anyway, we'll stop blabbering,I'm going to hit Create and this
will pop me into this initialmodal where I can start to feed
Notebook LM certain sources.
And you see, here I can uploadPDF, txt, markdown, audio, so
(08:38):
any number of different things.
I can upload documents from myGoogle Drive.
I can link to websites.
I can link to websites.
I can link to YouTube videos.
Now, what's interesting aboutthe YouTube thing is I was
researching this a little bitmore you can't.
It's not crawling video, um,like live.
It's actually taking thetranscripts from those videos,
(09:01):
and it actually, um won't taketranscripts from, like very
recent videos because I guessthey need some processing time
or whatnot.
But you are limited to 50different resources, which is a
ton, or you can just copy andpaste text in here, right?
So there's a lot of capabilityhere.
(09:21):
Now, in thinking about what Iwanted to do for this little
demo is, you know, there's thisconcept of wrapped or like end
of year kind of recap of whathappened throughout the year and
I thought, well, why don't Icreate that?
(09:42):
But using Notebook LM in audioformat, that, but using Notebook
LM in audio format.
And so I think what I'm goingto do is feed Notebook LM a
series of things that I've doneover the course of the year, and
we're going to start with justthe website, because it will go
crawl the website and pull stuffin there as well, stuff in
(10:12):
there as well.
So I'm going to give itdigitalcustomersuccesscom to
start with and there we go.
So you'll see, on the left itis looking at
digitalcustomersuccesscom andright off the bat in the chat
window, so you see, the sourcesare over here on the left, I can
add sources here In the chatwindow.
It has started to basically sayhey, look, here's kind of a
brief summary of the topic,right?
(10:34):
So in this case it thinks thatI'm essentially talking about
the podcast, or want to talkabout the podcast specifically
for this, which it's not wrong.
It is interesting the titlethat it gave this chat, which is
generative AI for customersuccess managers.
It probably did that because Ihave my AI tutorial for CSMs
(10:56):
embedded on the homepage of thewebsite.
Now that begs the questionshould I maybe feed it some sub
pages?
So let's go look atdigitalcustomersuccesscom and
what I might do is point it tothe four pillars of digital
customer success, which is anarticle that's on there.
(11:18):
I'll go ahead and add that as asource as well, just to see how
reactive this thing is.
I'm still kind of in play modehere, if you couldn't tell, but
we're playing live together,super fun, all right.
So I fed it that.
Now, in thinking about whatother content I wanted to feed
(11:40):
this chat you know, to give itsome sense, for you know the,
the show and kind of what we'vebeen through on this show
journey together I thought itwas good to feed it a few
episodes, and so what I will donext is essentially give it some
links to some of my soloepisodes that I've done, and so
(12:05):
I will start adding those assources here.
Now I'm not going to drag youalong while I add, like I don't
know, 10 different episodes here, but, as you see, here I've
added a YouTube video and youcan check and uncheck these as
you go along, right.
So what I'm going to do realquick is just take a second and
(12:29):
go add probably half a dozen orso solo episodes.
The other thing that I thoughtI would do is add a list of
guests that I've had over theyears Sorry, not over the years,
over this past year and see ifthat helps the cause as well.
So give me a second.
I'm going to do a bunch of workand then I'll see you here
(12:52):
shortly.
All right, so I've added abunch of YouTube episodes.
As you can see, I've done acouple of other things that I'm
going to add here.
First of all, I am going toupload a list of guests that
I've had.
I just put that into GoogleDrive guests in 2024.
(13:14):
I'm going to insert that.
So I think that gives me ageneral yeah, it gives me a
general kind of overview of theshow of this year.
It's got quite a few episodes,it's got the web page, it's got
my guest list for the year, andso now I can start to interact
(13:35):
with these documents and thesevideos and start typing and have
a conversation with it.
Now, before I do that, I didwant to show you real quick.
The output element of this ison the right-hand side here, and
so you know you can producevarious things.
For instance, I could producean FAQ if I wanted to, which is
(13:57):
super powerful, you know abriefing document, if I wanted
to present an executive overview, for instance, of the podcast
to somebody, or a study guide,if I was going to offer a
certification on all the topicsthat have been discussed over
the last 84 episodes, which Idon't even know if I could pass.
But that's beside the point.
(14:18):
Anyway, there's a bunch ofoutputs here.
One of them is this deepconversation so two hosts,
english only, and that isessentially what we're going to
output for next week's show.
I'll play a clip of it herewhen we're done.
But the first thing we're goingto do is just have a
(14:39):
conversation with Notebook LM sothat we can start to direct
what we want that podcastepisode to talk about.
And so it does give you acouple of suggestions down here.
How does generative AI impactcustomer success?
How can community buildingenhance digital customer success
, all that kind of stuff.
This is all digital customersuccess related, which is great,
(15:00):
because that's the subjectmatter.
However, right now, what I wantto do is basically ask it for
an overview of what the DigitalCX podcast is, and so we're
going to ask it.
Can you give me a summary whatthe Digital CX podcast is and
(15:27):
the major themes covered on theshow.
I'm going to see what thatcomes back with.
All right, now, what's coolhere is it has come back with a
pretty lengthy list here, but itdoes tell me about the podcast
itself, and you'll notice thatit does cite sources, which is
incredibly cool.
(15:47):
Think of this as basically likea steady guide.
So if you fed this a bunch ofsource documentation and asked
it to summarize it, it would dothe same thing that it's doing
here, which is it'll give youthe sources from where those
things came.
(16:07):
So very, very cool.
And then, yeah, as per myprompt, it does then tell me you
know what are some of the majorthemes that the show talks
about.
And now what I'm going to askyou to do is to give me a recap
of 2024.
Is to give me a recap of 2024.
(16:31):
And this is where I'm going tomanually actually feed it.
My Spotify wrapped details, sowe're going to pepper in a
little bit of manual informationhere as well.
You can see, the show grewphenomenally, by the way, which
is awesome 316% follower growth,which is awesome, awesome.
(16:52):
My average five star rating isfive stars, so thank you to
those of you who've left a fivestar review.
Um, all right, so I've skippedahead a little bit, because it
does take it a second to reallycome up with this stuff, but
(17:14):
you'll see that it says we'veexperienced significant growth,
which is all accurate Increasein the show's relevancy and
impact and digital customersuccess community, as well as a
commitment to providing valuableinsights to its audience.
Awesome recap of the journey,name change and scope of
(17:35):
expansion uh, yeah, this isgreat.
So this picked up from episode50 that I fed it because that's
when we changed the name fromdigital CS podcast to CX podcast
, so it's great.
Uh, focus on the four pillars.
We did a lot of stuff on thefour pillars this last year
emphasis on measuring, roi,exploration of automation,
(17:58):
generative AI integration whichis cool community building okay,
so I mean a decent summary.
Now, what isn't apparent here isthat you know this this isn't
(18:28):
going and crawling the web fornew sources, right, it is
specifically looking at thesources that I am feeding it.
So could it perhaps produce abetter result if I fed it some
additional things?
Absolutely, did I think aboutthe possibility of feeding it
every single transcript fromthis year's episodes?
Single transcript from thisyear's episodes?
(18:49):
Absolutely, and we probablycould have done some of that.
But also, you know, using toolslike this, the whole goal is to
create some efficiency in yourlife.
If I were to go and downloadevery single show transcript, if
I were to go and download everysingle show transcript format
(19:09):
it put it in here you couldargue that I could really just
as easily in that time record arecap episode of myself.
So you know, there's a point ofdiminishing returns here.
But the point is that you canfeed it a lot of information and
have it distill thatinformation down into digestible
chunks and really good outlineformat.
(19:29):
Now, one of the features ofNotebook LM here is that it
allows you to save notes, and soI'm going to click save note
and what that does, because asyou have a conversation with the
chatbot, you know things getkind of lost in the mix, and a
lot of times with ChatGPT youhave to go back and reference
things that you did.
(19:50):
And one thing that makes thisreally a notebook is that you
can save these notes over herefor reference later.
So super, super handy.
So I'm going to leave it atthat for now.
I could.
I could go on and refine things, and it's it's best practice
(20:10):
that you do that with any uh,you know, with any ai, but I
feel relatively good about wherewe stand with our results thus
far.
So what I'm most interested inhere today is this audio
overview deep dive conversationto hosts english only I would
imagine they're going toprobably going to probably going
to expand that at some point.
But what I'm really interestedin is having this thing create
(20:31):
next week's episode for me sothat I don't have to.
So we're going to have twohosts talk about the Digital CX
podcast a year in review, and soI'm going to hit the customize
button because then so I'm goingto hit the customize button
(20:56):
because then this will give methe ability to basically prompt
what I want these two hosts totalk about in this episode.
And so here we go.
Be a recap, let's say, of theyear 2024 as it pertains to the
(21:16):
Digital CX podcast.
The episode should highlightsome of the major milestones and
accomplishments achievedthroughout the year, as well as
highlight the concepts.
I can't spell conceptsdiscussed throughout the year
(21:49):
High level, but we're going togive that a try.
I'm going to hit generate andit's going to chug on that for a
little bit.
So while it's doing that, Ihope you see how cool this tool
is.
I really want to use it a lotover this coming year as a
notebook and helping mesummarize certain things.
When you exit out of a specificone that you're working in,
(22:10):
you'll see that it has aplaceholder for this particular
conversation that you're havingwith Notebook LM and then you
can add to those right.
So it's not this stream ofconsciousness, there's this
concept of just separateconversations that you're having
within Notebook LM, but I thinkyou're going to be pretty
impressed with what it pumps outas its podcast episode.
(22:35):
I found this to be fascinatingfor a couple of reasons.
First off, it just seems random, you know, to have it pump out
a podcast episode of all things.
You know the study guide makessense, the briefing doc makes
sense, faqs that makes perfectsense.
But then you know it's apodcast episode.
So somebody at Google, I think,was having fun with this.
On the surface it's anincredibly cool thing and for
(22:59):
the most part the output isrelatively engaging, though when
you really listen to it it canbe a bit of snooze fest.
To be honest with you, thehosts are engaging and they
sound like podcast hosts and itsounds really well produced and
those kinds of things, but thebanter is a little bit contrived
(23:20):
.
You'll get what I mean when youhear the results.
So I really hope you've enjoyedthis brief, over-the-shoulder
experience of Notebook LM.
Maybe you can start to utilizeit yourself as well, and what
we're going to do is actuallyoutro this episode with a sneak
(23:41):
peek of what it is generating aswe speak.
But, that said, I want to wisheverybody a very Merry Christmas
.
If you celebrate, if you don't,hope you get some good time off
with the family and all thatgood stuff and make sure that
you tune in next week on Tuesday.
I guess that would be NewYear's Eve.
(24:01):
Yes, it would be on New Year'sEve, because we're going to be
playing the output of NotebookLM in its entirety.
So hope you enjoy that.
Thanks for listening today andwe'll talk to you again in the
next episode.
This show was busy in 2024.
We're giving you the VIPbackstage pass to their year.
Yeah, the podcast itself reallyevolved this year.
(24:23):
It went from just digitalcustomer success to a bigger
picture of digital customerexperience.
Thank you for joining me forthis episode of the Digital CX
Podcast.
If you like what we're doing,consider leaving us a review on
your podcast platform of choice.
If you're watching on YouTube,leave a comment down below.
It really helps us to grow andprovide value to a broader
audience and get moreinformation about the show and
(24:45):
some of the other things thatwe're doing at
digitalcustomersuccesscom.
I'm Alex Tergovich.
Thanks so much for listening.
We'll talk to you next week.
Today I've got some over-the-shoulder AI fun for you
, so stay tuned.
Once again, welcome to theDigital Customer Experience
Podcast with me, alex Terkovich,so glad you could join us here
today and every week as weexplore how digital can help
enhance the customer andemployee experience.
My goal is to share what myguests and I have learned over
(00:23):
the years so that you can getthe insights that you need to
evolve your own digital programs.
If you'd like more info, needto get in touch or sign up for
the weekly companion newsletterthat has additional articles and
resources in it.
Go to digitalcustomersuccesscom.
For now, let's get started.
Greetings and welcome toepisode 84 of the digital cx
podcast, the show where we talkabout all things digital in CX,
(00:47):
and it's a solo episode 84,mainly because the next two
episodes are actually going tobe solo.
So 84, 85 are both going to besolo.
It is Christmas Eve today ifyou're listening live, or on day
of release, so Merry Christmasto those of you who celebrate.
Hopefully this is a time foryou to spend with family and
(01:11):
friends and loved ones and allof that, but I also recognize
that a lot of us need a littlebit of escape during this time
as well, so maybe I am part ofyour escape today, in which case
, thanks for joining me.
Today is going to be a littlebit different.
And be forewarned if you are aregular podcast listener in
(01:33):
other words you're listening tothe show, you're not watching it
on YouTube you may want to takea second to go find a screen or
go look for this episode onYouTube.
I will be putting a link in theshow notes below so you can get
to it pretty easily.
The reason for this is I'mgoing to do a little bit of
(01:54):
screen sharing today and we aregoing to have some fun with
Google's Notebook LM, which, ifyou haven't used it yet, is a
pretty cool Google product, alittle bit under the radar, uses
Google's Gemini platform toessentially do some
summarization of whatever youfeed it and also produces.
(02:17):
This feels really random to me,but it also gives you the
ability to produce a co-hostedpodcast episode with two a male
and a female voice banteringabout whatever it is you fed it
in terms of the sources, sowe're actually going to have
some fun with that today.
In this episode, we are goingto feed Notebook LM some sources
(02:42):
and do a little bit ofprompting, at which point.
We're going to ask it toproduce one of these podcast
episodes and on next week's showyou're going to hear the result
of that.
So you're going to hear theoutput of whatever it is we feed
it today.
So you're getting back-to-backsolo episodes.
Today is going to be nuts andbolts and over the shoulder and
(03:03):
next week is going to beliterally the output of whatever
it is we're working on today.
So, before we jump over into thescreen share, I thought it
would be good to spend a coupleof minutes just talking about
Notebook LM and use cases forNotebook LM, because essentially
, what it does is takes whateverinputs you give it.
It could be a website, it couldbe linked to a YouTube video,
(03:25):
it could be a document like aPDF or a text document that you
upload, it could be any numberof things that you feed it, and
it allows you to summarize thosedocuments and essentially have
a conversation with Notebook LMabout those documents, and then
you can pin those conversationsso that you can reference them
(03:46):
later.
It's really cool and it setsnotebook alum is different than,
let's say, chat gpt, forinstance, because of this
ability to summarize multipledocuments into one place and
then pinning those thingsessentially for for later.
So the obvious use case here issummarizing documents.
(04:10):
So if you have a swath ofdocuments, you can put those in
and summarize them.
So, for instance, you couldwell I suppose you could feed it
your knowledge base articles orsomething like that.
There's a limit, I think it's20 documents that you can upload
to it, but you can point it ata number of websites on the same
topic and then have aconversation with it to
(04:34):
summarize those things.
You can also use it to transformdocuments into something more
digestible, maybe turning a bookthat you wrote into an ebook or
a short version of something.
You can use it to analyzereports.
So if you have a bunch of datahanging around, you can use it
to essentially have aconversation with your data,
(04:55):
which is super cool.
And I mentioned earlier youcould summarize knowledge bases,
but you could also use it tocreate a knowledge base.
So if you have documentationthat's pretty broad on a
specific niche topic or a groupof topics, you could then use it
to essentially create outlinesor create the startings of
(05:20):
different knowledge basearticles.
One interesting use case ummight be uh, if you're if you're
an average cook, for instance,you could feed it your recipes
and have it be a place to storethose things and then use it to
basically query those recipes ifyou need some ideas about
things that you like doing, sothat you know there's just the.
(05:42):
It's one of those tools whereit's so kind of open-ended that
really the only limitation isyour creativity in actually
using it.
One of the things that Googledoes suggest that you can use it
for is fact-checking.
I'm on the fence about that,because I don't generally trust
generative AI or AI models to dothe fact-checking.
(06:04):
In fact, quite the opposite, Itend to fact-check the outputs
of generative AI.
But hey, you know, go play withit.
I wanted to at least provideyou with a couple of examples of
how you might use Notebook LM,either for your personal use or
within a team.
It's an incredibly powerfultool, so, without further delay,
(06:26):
let's get into it.
I'll do a little bit of screensharing and we'll get into
Notebook LM.
This isn't gonna be necessarilya tutorial like a full-blown
tutorial in Notebook LM, butwe're just gonna play around and
see what we come up with.
Hey, I wanna have a brief chatwith you about this show.
Did you know that roughly 60%of listeners aren't actually
subscribed to the show, onwhatever platform they're
(06:48):
listening to it on.
As you know, algorithms love,likes, follows, subscribes,
comments, all of that kind ofstuff.
So if you get value out of thecontent, you listen regularly
and you want to help others todiscover the content as well,
please go ahead and follow theshow, leave a comment, leave a
review.
Anything that you wanna dothere really helps us to grow
(07:10):
organically as a show.
And while you're at it, go signup for the companion newsletter
that goes out every week atdigitalcustomersuccesscom.
Now back to the show.
All right, so I've gone tonotebooklmgooglecom and sign in
with your profile.
Pretty straightforward.
I've deleted the ones that I'veput in here just to show you
(07:32):
what the experience is right offthe bat, but it does prompt you
to create your first notebookand talks about uploading
documents and havingconversations with them by
having, you know, convert themto useful documentation.
What it doesn't tell you abouthere is the fact that it can
produce this miraculous likepodcast episode that a lot of
(07:53):
people are talking about.
By the way, I can't take fullcredit for this and I didn't
discover this by any means.
It's pretty well known thingnow that you can create these
podcast episodes from NotebookLM, but most notably, marley
Wagner and Bob London talkedabout this at Churn Zero and
(08:14):
actually produced an episodelive during their session, which
was super cool.
Anyway, we'll stop blabbering,I'm going to hit Create and this
will pop me into this initialmodal where I can start to feed
Notebook LM certain sources.
And you see, here I can uploadPDF, txt, markdown, audio, so
(08:38):
any number of different things.
I can upload documents from myGoogle Drive.
I can link to websites.
I can link to websites.
I can link to YouTube videos.
Now, what's interesting aboutthe YouTube thing is I was
researching this a little bitmore you can't.
It's not crawling video, um,like live.
It's actually taking thetranscripts from those videos,
(09:01):
and it actually, um won't taketranscripts from, like very
recent videos because I guessthey need some processing time
or whatnot.
But you are limited to 50different resources, which is a
ton, or you can just copy andpaste text in here, right?
So there's a lot of capabilityhere.
(09:21):
Now, in thinking about what Iwanted to do for this little
demo is, you know, there's thisconcept of wrapped or like end
of year kind of recap of whathappened throughout the year and
I thought, well, why don't Icreate that?
(09:42):
But using Notebook LM in audioformat, that, but using Notebook
LM in audio format.
And so I think what I'm goingto do is feed Notebook LM a
series of things that I've doneover the course of the year, and
we're going to start with justthe website, because it will go
crawl the website and pull stuffin there as well, stuff in
(10:12):
there as well.
So I'm going to give itdigitalcustomersuccesscom to
start with and there we go.
So you'll see, on the left itis looking at
digitalcustomersuccesscom andright off the bat in the chat
window, so you see, the sourcesare over here on the left, I can
add sources here In the chatwindow.
It has started to basically sayhey, look, here's kind of a
brief summary of the topic,right?
(10:34):
So in this case it thinks thatI'm essentially talking about
the podcast, or want to talkabout the podcast specifically
for this, which it's not wrong.
It is interesting the titlethat it gave this chat, which is
generative AI for customersuccess managers.
It probably did that because Ihave my AI tutorial for CSMs
(10:56):
embedded on the homepage of thewebsite.
Now that begs the questionshould I maybe feed it some sub
pages?
So let's go look atdigitalcustomersuccesscom and
what I might do is point it tothe four pillars of digital
customer success, which is anarticle that's on there.
(11:18):
I'll go ahead and add that as asource as well, just to see how
reactive this thing is.
I'm still kind of in play modehere, if you couldn't tell, but
we're playing live together,super fun, all right.
So I fed it that.
Now, in thinking about whatother content I wanted to feed
(11:40):
this chat you know, to give itsome sense, for you know the,
the show and kind of what we'vebeen through on this show
journey together I thought itwas good to feed it a few
episodes, and so what I will donext is essentially give it some
links to some of my soloepisodes that I've done, and so
(12:05):
I will start adding those assources here.
Now I'm not going to drag youalong while I add, like I don't
know, 10 different episodes here, but, as you see, here I've
added a YouTube video and youcan check and uncheck these as
you go along, right.
So what I'm going to do realquick is just take a second and
(12:29):
go add probably half a dozen orso solo episodes.
The other thing that I thoughtI would do is add a list of
guests that I've had over theyears Sorry, not over the years,
over this past year and see ifthat helps the cause as well.
So give me a second.
I'm going to do a bunch of workand then I'll see you here
(12:52):
shortly.
All right, so I've added abunch of YouTube episodes.
As you can see, I've done acouple of other things that I'm
going to add here.
First of all, I am going toupload a list of guests that
I've had.
I just put that into GoogleDrive guests in 2024.
(13:14):
I'm going to insert that.
So I think that gives me ageneral yeah, it gives me a
general kind of overview of theshow of this year.
It's got quite a few episodes,it's got the web page, it's got
my guest list for the year, andso now I can start to interact
(13:35):
with these documents and thesevideos and start typing and have
a conversation with it.
Now, before I do that, I didwant to show you real quick.
The output element of this ison the right-hand side here, and
so you know you can producevarious things.
For instance, I could producean FAQ if I wanted to, which is
(13:57):
super powerful, you know abriefing document, if I wanted
to present an executive overview, for instance, of the podcast
to somebody, or a study guide,if I was going to offer a
certification on all the topicsthat have been discussed over
the last 84 episodes, which Idon't even know if I could pass.
But that's beside the point.
(14:18):
Anyway, there's a bunch ofoutputs here.
One of them is this deepconversation so two hosts,
english only, and that isessentially what we're going to
output for next week's show.
I'll play a clip of it herewhen we're done.
But the first thing we're goingto do is just have a
(14:39):
conversation with Notebook LM sothat we can start to direct
what we want that podcastepisode to talk about.
And so it does give you acouple of suggestions down here.
How does generative AI impactcustomer success?
How can community buildingenhance digital customer success
, all that kind of stuff.
This is all digital customersuccess related, which is great,
(15:00):
because that's the subjectmatter.
However, right now, what I wantto do is basically ask it for
an overview of what the DigitalCX podcast is, and so we're
going to ask it.
Can you give me a summary whatthe Digital CX podcast is and
(15:27):
the major themes covered on theshow.
I'm going to see what thatcomes back with.
All right, now, what's coolhere is it has come back with a
pretty lengthy list here, but itdoes tell me about the podcast
itself, and you'll notice thatit does cite sources, which is
incredibly cool.
(15:47):
Think of this as basically likea steady guide.
So if you fed this a bunch ofsource documentation and asked
it to summarize it, it would dothe same thing that it's doing
here, which is it'll give youthe sources from where those
things came.
(16:07):
So very, very cool.
And then, yeah, as per myprompt, it does then tell me you
know what are some of the majorthemes that the show talks
about.
And now what I'm going to askyou to do is to give me a recap
of 2024.
Is to give me a recap of 2024.
(16:31):
And this is where I'm going tomanually actually feed it.
My Spotify wrapped details, sowe're going to pepper in a
little bit of manual informationhere as well.
You can see, the show grewphenomenally, by the way, which
is awesome 316% follower growth,which is awesome, awesome.
(16:52):
My average five star rating isfive stars, so thank you to
those of you who've left a fivestar review.
Um, all right, so I've skippedahead a little bit, because it
does take it a second to reallycome up with this stuff, but
(17:14):
you'll see that it says we'veexperienced significant growth,
which is all accurate Increasein the show's relevancy and
impact and digital customersuccess community, as well as a
commitment to providing valuableinsights to its audience.
Awesome recap of the journey,name change and scope of
(17:35):
expansion uh, yeah, this isgreat.
So this picked up from episode50 that I fed it because that's
when we changed the name fromdigital CS podcast to CX podcast
, so it's great.
Uh, focus on the four pillars.
We did a lot of stuff on thefour pillars this last year
emphasis on measuring, roi,exploration of automation,
(17:58):
generative AI integration whichis cool community building okay,
so I mean a decent summary.
Now, what isn't apparent here isthat you know this this isn't
(18:28):
going and crawling the web fornew sources, right, it is
specifically looking at thesources that I am feeding it.
So could it perhaps produce abetter result if I fed it some
additional things?
Absolutely, did I think aboutthe possibility of feeding it
every single transcript fromthis year's episodes?
Single transcript from thisyear's episodes?
(18:49):
Absolutely, and we probablycould have done some of that.
But also, you know, using toolslike this, the whole goal is to
create some efficiency in yourlife.
If I were to go and downloadevery single show transcript, if
I were to go and download everysingle show transcript format
(19:09):
it put it in here you couldargue that I could really just
as easily in that time record arecap episode of myself.
So you know, there's a point ofdiminishing returns here.
But the point is that you canfeed it a lot of information and
have it distill thatinformation down into digestible
chunks and really good outlineformat.
(19:29):
Now, one of the features ofNotebook LM here is that it
allows you to save notes, and soI'm going to click save note
and what that does, because asyou have a conversation with the
chatbot, you know things getkind of lost in the mix, and a
lot of times with ChatGPT youhave to go back and reference
things that you did.
(19:50):
And one thing that makes thisreally a notebook is that you
can save these notes over herefor reference later.
So super, super handy.
So I'm going to leave it atthat for now.
I could.
I could go on and refine things, and it's it's best practice
(20:10):
that you do that with any uh,you know, with any ai, but I
feel relatively good about wherewe stand with our results thus
far.
So what I'm most interested inhere today is this audio
overview deep dive conversationto hosts english only I would
imagine they're going toprobably going to probably going
to expand that at some point.
But what I'm really interestedin is having this thing create
(20:31):
next week's episode for me sothat I don't have to.
So we're going to have twohosts talk about the Digital CX
podcast a year in review, and soI'm going to hit the customize
button because then so I'm goingto hit the customize button
(20:56):
because then this will give methe ability to basically prompt
what I want these two hosts totalk about in this episode.
And so here we go.
Be a recap, let's say, of theyear 2024 as it pertains to the
(21:16):
Digital CX podcast.
The episode should highlightsome of the major milestones and
accomplishments achievedthroughout the year, as well as
highlight the concepts.
I can't spell conceptsdiscussed throughout the year
(21:49):
High level, but we're going togive that a try.
I'm going to hit generate andit's going to chug on that for a
little bit.
So while it's doing that, Ihope you see how cool this tool
is.
I really want to use it a lotover this coming year as a
notebook and helping mesummarize certain things.
When you exit out of a specificone that you're working in,
(22:10):
you'll see that it has aplaceholder for this particular
conversation that you're havingwith Notebook LM and then you
can add to those right.
So it's not this stream ofconsciousness, there's this
concept of just separateconversations that you're having
within Notebook LM, but I thinkyou're going to be pretty
impressed with what it pumps outas its podcast episode.
(22:35):
I found this to be fascinatingfor a couple of reasons.
First off, it just seems random, you know, to have it pump out
a podcast episode of all things.
You know the study guide makessense, the briefing doc makes
sense, faqs that makes perfectsense.
But then you know it's apodcast episode.
So somebody at Google, I think,was having fun with this.
On the surface it's anincredibly cool thing and for
(22:59):
the most part the output isrelatively engaging, though when
you really listen to it it canbe a bit of snooze fest.
To be honest with you, thehosts are engaging and they
sound like podcast hosts and itsounds really well produced and
those kinds of things, but thebanter is a little bit contrived
(23:20):
.
You'll get what I mean when youhear the results.
So I really hope you've enjoyedthis brief, over-the-shoulder
experience of Notebook LM.
Maybe you can start to utilizeit yourself as well, and what
we're going to do is actuallyoutro this episode with a sneak
(23:41):
peek of what it is generating aswe speak.
But, that said, I want to wisheverybody a very Merry Christmas
.
If you celebrate, if you don't,hope you get some good time off
with the family and all thatgood stuff and make sure that
you tune in next week on Tuesday.
I guess that would be NewYear's Eve.
(24:01):
Yes, it would be on New Year'sEve, because we're going to be
playing the output of NotebookLM in its entirety.
So hope you enjoy that.
Thanks for listening today andwe'll talk to you again in the
next episode.
This show was busy in 2024.
We're giving you the VIPbackstage pass to their year.
Yeah, the podcast itself reallyevolved this year.
(24:23):
It went from just digitalcustomer success to a bigger
picture of digital customerexperience.
Thank you for joining me forthis episode of the Digital CX
Podcast.
If you like what we're doing,consider leaving us a review on
your podcast platform of choice.
If you're watching on YouTube,leave a comment down below.
It really helps us to grow andprovide value to a broader
audience and get moreinformation about the show and
(24:45):
some of the other things thatwe're doing at
digitalcustomersuccesscom.
I'm Alex Tergovich.
Thanks so much for listening.
We'll talk to you next week.
Popular Podcasts
Stuff You Should Know
If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks, then look no further. Josh and Chuck have you covered.
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.