So What header image

So What? Setting up A/B tests for ChatGPT

So What? Marketing Analytics and Insights Live

airs every Thursday at 1 pm EST.

You can watch on YouTube Live. Be sure to subscribe and follow so you never miss an episode!

In this week’s episode of So What? we focus on setting up A/B tests for ChatGPT. We walk through why set up is vital to your long term usage, which A/B tests to set up and show you step by step how to run a test. Catch the replay here:

So What? Setting up an A/B test for ChatGPT

In this episode you’ll learn: 

  • Why setting up A/B tests for ChatGPT is vital to your long term usage
  • What A/B tests to set up
  • How to run a test from start to finish with a live walkthrough

Upcoming Episodes:

  • TBD

Have a question or topic you’d like to see us cover? Reach out here: https://www.trustinsights.ai/resources/so-what-the-marketing-analytics-and-insights-show/

AI-Generated Transcript:

Katie Robbert 0:29
Well, hey everyone, Happy Thursday. Welcome to so what the marketing analytics and insights love show, I’m joined by Chris and John, let’s go guys. This week we are talking about setting up a B tests for chat GPT Chris and I were talking about this earlier this week, because, you know, you can’t, you know, take a left turn without hearing someone talking about chat GPT you can’t go online on a social platform, you know, in the news, without someone talking about chat GPT. And so we started talking about the effectiveness, the performance, how do you measure, chat GPT-3. So everyone, you know, everyone in their mother has signed up for some kind of account are playing with it, using it, you know, pretending that it’s going to revolutionize their company, their marketing, and in some cases, that’s true. But for most of us, we really need to understand how effective chat GPT is, what it can do for our marketing, but how, more importantly, how do we measure it. And so we wanted to do today is set up some A B testing. And so we’ll go into what all of it is how to set it up. But what we really want to understand is, are what we doing as marketers, is it better or worse than what chat GPT can do for us. And we’re going to start with some very simple examples. So before we get into it, John, are you do have you been playing with Chet GPT? Or is it something that you’ve, you know, thought, You know what, I can have this do the podcast for me, I don’t even need to show up anymore?

John Wall 2:06
No, I haven’t. I have at least you know, dug into it once. But I have not spent a ton of time on it at all. And so I’m looking forward today to kind of figure out what’s going on. And I am I really want to issue a chat GPT NFT later this week, so I’m hoping that’ll be a big moneymaker for me. That’s my,

Katie Robbert 2:22
you’re fired? That is I mean, if you’re going to talk about it on clubhouse, then we’re good.

John Wall 2:30
Even though, check out my Google Plus page, we’re here to go.

Katie Robbert 2:35
Alright, Chris, so, you know, we’ve talked a lot about what chat GPT and what chat GPT-2? Isn’t? Can you give a very quick rundown on the basics of you know, some use cases for chat GPT-2 and why? You know, setting up an AB SaaS is a good idea.

Christopher Penn 2:50
Sure. So very briefly, chat. GPC is a web interface to a large language model. The large a large language models is a piece of software has been trained on enormous amounts of text. And what it does is it generates or rewrites text based on instruction to give it called prompts. So that’s, you know, the dimestore explanation. This is what it looks like. We’re using the plus edition, which is the paid edition. Yesterday, OpenAI just announced that the API is now available for people who are wanting to do development with it. And it’s a pretty straightforward piece of software. So you give it some instructions, and it will do some things let’s do list.

Katie Robbert 3:59
Version. And so Chris, what you’re demonstrating is how we’ve seen the majority of people using chat TPT, which is to create net new content, chat GPT-2 can obviously do a lot of other things. But I would say this is probably statistically the most common use case that people are using chat GPT-3 for is to generate something to generate an outline to generate, you know, a first draft and that’s how you’re demonstrating the use of it right now.

Christopher Penn 4:30
Exactly. Right. So what we want to talk about today was for the process of rewriting content, or re mixing content, how to judge whether or not chat GPT-2 does a better job than you know the content you’ve already got. So the first place we should probably start is with the five P’s. What is the thing we’re trying to do? So the purpose for a lot of marketers have Content Creation is attracting organic search traffic, or organic social traffic, but mostly organic search traffic. So because that’s the case, then the first place we should probably look is within an organic search tool. And the one that everyone has access to for free, is Google Search Console. The place to look in here is under search results, go to pages. And you will see the number of pages on your website, the clicks they get and the impressions they get. And what I’m looking for, is I’m looking for pages that get decent impressions, which means that Google thinks that the page is relevant, but just doesn’t get the clicks. It means that the when a human being reads the search listing, and that’s not what I’m

Katie Robbert 5:55
and if you the viewer is interested in learning more about how to use Google Search Console for yourself to see if it’s set up on your website, we do have a course, go to trust insights.ai/sars Search Console, it is a free tool, you just need to make sure that it is connected to your website so that it can collect this kind of data. So Chris, what you’re showing is the Trust Insights website. And so these are the different pages, primarily, probably blog posts from our website. And you can see, we have our top pages. We have the clicks and the impressions. And so it sounds like what you want to see is the pages that get both a lot of impressions and clicks. Is that correct? Are you going to reverse order?

Christopher Penn 6:40
I’m not well, I’m looking for pages that get good impressions, because that means Google thinks the page it often doesn’t get it doesn’t get the clicks. So there’s something wrong with that page that people look at the summary of the synopsis and go. That’s that’s not what I was looking for. So here’s one, this is a blog post from four years ago now called AI SEO in the post BERT. Marketers need to know. Now, this is actually fairly long page. Let’s take a good chunk of this year.

And now let’s take this and toss it over to chat GPT-2 greater conversation and say, write the following.

syntax

Unknown Speaker 7:42
right.

Katie Robbert 7:51
And so what you’re seeing Chris doing is what we talked about on other shows. It’s called prompt engineering. And so Chris is writing it as specifically as possible, and you can check out that episode over on trust insights.ai/youtube. The reason Chris is getting so specific is because he doesn’t want to have to go through this process multiple times, there may be some refinement needs to be done. But as the more specific you can get in giving chat GPT-2 instructions, the better the results are going to be. And so you know, the example that we were giving earlier this week was Chris, if I said to you bake me a cake, I haven’t told you what kind of cake what shaped cake, what flavor that needs to be gluten free, dairy free, or any of that stuff. So you’re gonna say, Okay, let me bake a cake. And so you’re gonna hand me a cake and then I’m gonna get frustrated because it wasn’t a gluten free, dairy free vegan, you know, only beet sugar, you know, chocolate with a unicorn on top. But had I told you those things, you would have done your best to deliver that. And so using prompts in chat GPT-2 is very similar to, you know, asking someone to do something, get as specific as you can, and then you’re likely to get the result

Unknown Speaker 9:04
that you’re after. Exactly. I

Katie Robbert 9:05
will never bake you that cake. I don’t actually want that cake. That sounds awful. It really does. That’s

Christopher Penn 9:11
just a block of sugar. So what you see here is what you see here is the revised content. Now, what when we’re talking about AB testing, we want to do things as apples to apples as possible. Let me show you a couple of examples. This is an original blog post of mine from 2016. Way out of date, and I had chat GPT-2 Rewrite it I dated at the exact same date and from a promotional perspective, I would promote each post. Similarly same for this one change improvement changes improvement. Again, follow the exact process we just did. I’ve created these posts in parallel and So what I’d be looking to do then is give each page appropriate amounts of promotion, and see which page performs better. Does the does the text that’s machine written, perform better than the text that is purely human written or not? And that’s, that’s what we’d want to ascertain.

Katie Robbert 10:18
And so, you know, is this something? Remind me is Google sunset and Google Optimize?

Christopher Penn 10:27
Yes. Okay. No, it’s Google. Well, Google Surveys. No, actually they, yeah, they have they are sunsetting, Google Optimize, optimize has

John Wall 10:35
gone away. Yeah.

Katie Robbert 10:37
So this is a way to do an A B test without relying on a tool such as Google optimized, which a lot of us have been using for years. But Google has decided that it’s no longer going to be a standalone piece, I think what’s actually happening and we can double check on this is they are rolling it into Google Analytics 4, so that you have to use it through that system. So it’s no longer something you use a standalone. So the reason I bring that up is because I think when, you know, we as marketers think about a B tests, we immediately think we have to be using a tool, such as Google optimized, but Chris, what you’re demonstrating is that you don’t, you can do this without having a third party tool running the test for you.

Christopher Penn 11:23
Exactly right. And that I mean, this is as simple as it gets, you just create additional pages, and you promote each of the pages. And one of the things I would suggest you do is, as part of the experiment, you put together a very simple spreadsheet, right? You know, here’s the URLs, and then do your promotion. And then after 30 days of promoting both pages, super simple. Compare the pageviews and say, well, we’ve promoted both equally, assuming he did, which page performed better, and you can look at, there’s a whole bunch of different metrics you can use to judge this pages, and certainly be the simplest.

Katie Robbert 12:04
Well, and I think that that goes back to your original point, Chris, about the five P’s is understanding why you want to do this in the first place. And so if your goal with the content on your site is to drive traffic to organic search, if you’re it’s to build awareness, those are the things that you’re looking to be you’d be looking to measure in terms of the effectiveness of one version of this versus the other.

Christopher Penn 12:29
Exactly. Now, we that was the simple version. One of the things that is challenging about Search Console, is that you don’t get the query terms alongside with the pages. I’m not sure why they don’t let you have at that. But you can only get that through the API. So if you’re familiar with the API, or API’s in general, you can, this should look familiar, if you’re not, one of the things you can get is programmatically Get out your data to see what pages and the associated search term are being impacted. So here, that AI and SEO Post, the the query term being searched for is BERT SEO. So that is very helpful for when you’re writing your prompts, to be able to say be sure to include concepts about BERT and SEO.

Katie Robbert 13:36
So with the content that you just had chat, GPT rewrite, you know it? Would you suggest that we take what was just rewritten by chat GPT and stand it up against the original posts, so don’t optimize the original post, but standard up against and have them running in parallel on our site to see which one performs better?

Christopher Penn 14:02
For the purposes of an AB test? Yes. Okay.

Katie Robbert 14:09
And I would imagine, and I think I already know the answer to this question, like, you don’t have to have existing content. To do this A B test with you could just take, okay, I’m looking at this and I could see, oh, big Webmaster Tools. That’s a topic that I know enough about that I could write I could do, in some ways, Chris, I think you’d like to call it a bake off like a head to head have chat GPT-2 write a piece of content about Bing Webmaster Tools. And then I’ll write a piece of content about Bing Webmaster Tools. We’ll put them both up, have the same promotion plan around them and see which one does better. Is that another way to approach this ad test?

Christopher Penn 14:49
Absolutely. And in fact, if you if you have it set up in your account, you have to opt into it. Google will give you content ideas. It says these are things. This content ideas are based on searches that might lack good results, which is Google’s nice way of saying, hey, we need you to do some free work for us. But, you know, there’s some really good, interesting questions in here, kind of the kinds of questions that some you might want to legitimately have on your website.

John Wall 15:26
You can easily copy and paste right over to GPT.

Christopher Penn 15:31
Exactly. So here’s a good one, what can’t you measure in Google Analytics?

Katie Robbert 15:43
And so John, so at this, at the start of the show, you were talking about wanting to learn more? Is this giving you some ideas around how, you know, for the marketing over coffee podcasts, you could utilize chat GPT, or even within the business development stuff that you do for Trust Insights? Now, you’re always sort of mentioning a B testing subject lines for emails, would you use chat GPT to do this? Yeah, cuz

John Wall 16:08
it’s just it’s so efficient, cranking out copy, right? The because that example you talked about before, where it’s like, okay, the two of us do this, you get, we’re all kind of used to that thing, where you take one piece of copy, and you sit there and you bang out a second version of it in, you know, 10 minutes or whatever, but to be able to just cut and paste five times and have it spit back five versions, and then you can pick and choose what you like. And the thing with that is really the additional insight, you know, this is pulling from such a huge corpus of data, that you’re gonna get new sentences or new ideas that you would never have thought of, you know, by generating 10 different angles, you’d be sure to find two or three things that you, you know, hadn’t even thought about or considered. And that’s really, it’s kind of like, you know, no charge brainstorming. I mean, it’s a great way to just continue to crank out stuff without too much pain.

Katie Robbert 16:56
That makes sense. And, you know, and I’m wondering, I think there’s probably two different ways that you could approach it in terms of getting that content to a B test. You know, Chris, in terms of prompt engineering, would you actually ask chatty Beatty, you know, write 10 email subject lines that I can do a B testing with? So that there would would chat GPT know, to make to slightly vary them so that you can start to see what’s working, what’s not.

Christopher Penn 17:25
Yep. Done that. With writing headlines, reading tweets, for example, is a very another very popular one.

Katie Robbert 17:34
So what are we looking at here?

Christopher Penn 17:36
So this was this content idea. From Google Search Console. We’ve now had chat GPT-2 draft an answer to the question, what can’t you measure and Google Analytics? Now, to your point, Katie, you would want to have a human subject matter expert, also write the same article, ideally, without looking at the chat GPT-2 version? Keep churches state separate, and then put both of them up and see which one performs better.

Katie Robbert 18:08
I think it’s an interesting exercise, especially for companies that are really feeling like chat TPT is the answer to a lot of issues or resources that they might be facing right now. You know, there’s a lot of companies that are cutting back on budgets. And so they’re looking to chat GPT to fill some of those gaps, especially around writing, and their content marketing, which is all well and good. But I think that, you know, running an experiment like this before making that decision, is probably a good way to gauge whether or not chat GPT can, you know, write to the quality that your brand is accustomed to? Now, is there a way to train chat TPT specifically on your voice, your style of writing, like no more that you use it? Will it? learn who you are and what you want to say?

Christopher Penn 19:04
Not yet in OpenAI is Discord server, they were saying that fine tuning is not available for chat GPT-2 yet.

Katie Robbert 19:11
And so that’s another consideration. And which is why running an AB test is a really good idea before making those hard and fast decisions to have a tool like chat GPT stand in for a human because you know, Chris, your point, what we’re talking about is you can’t fine tune it. You can’t train this large learning model to your specific criteria. Basically, the tone and the content is what you’re going to get is what you’re going to get, you can add into the prompt, make it warm, make it friendly, make it Stern, you know, you can sort of give it those cues, but it will never truly mirror the way that you write or that you you know, your brand tends to speak about things and so that’s a consideration as well.

Christopher Penn 19:56
Exactly right. However, that said if they are plenty of copies of ideas, you know, in the content ideas section, if there’s stuff that you want take a crack at having a chat GPT-2 version of it might, even if you don’t do the AV test might be better than not having anything at all.

Katie Robbert 20:17
No, and I think that that makes a lot of sense. And so, you know, what we had talked about in terms of the risks is making sure that you have a human who’s editing it to make sure that it’s not saying anything egregious ly incorrect. You know, so back to the notion of a b testing. So Chris, if we go to chat GPT, again, you know, what would it look like for you to ask chat GPT-2, right, you know, five, email, you know, subject lines for a sales pitch for our Google Analytics 4 course. We want to AV test.

Christopher Penn 20:58
I feel like we’ve have some of that written down somewhere.

Katie Robbert 21:06
Well, let’s pretend we don’t, what would How would someone get started with that, if they want to start an AV test for email subject lines.

Christopher Penn 21:13
So first thing we have to do is provide guardrails on my system. So we need to one of the more popular things to do is in your prompts to structure and to tell it what kind of person it is. Not because it understands that but because the words and phrases that you use and that will contextual give a context for that. So let’s do this as well as email. talise. Highly. Of okay.

Katie Robbert 21:55
So one thing to note, as Chris is writing this out, is he’s not naming an individual person, he’s giving the characteristics of the person who is writing, as chat GPT-3, so an email marketing expert, writing highly effective subject lines for emails that get opened more than others, that is a very specific type of person. And that is something that chat GPT-2 can start to understand of like, okay, you’re looking for the following things got it.

Christopher Penn 22:23
Right. So that is, that is our first set of guardrails. In doing that it helps it understand what it is that we want to be doing. But more specifically, knowing that it’s, it’s in the context of email marketing, right, I did, I finally did find my Okay. Task and compelling. Subject Lines.

Katie Robbert 22:57
So John, I hope you’re taking notes is I’m gonna make you start doing this for our emails.

John Wall 23:01
Now, this is it. I’ve got I just throw in a random subject line that said, generate five versions. And yeah, it goes, it pulls, you know, because the line was, first look seven weeks to showtime. And it gave me countdown to showtime, get your first look and seven weeks, don’t miss out first look, in seven weeks get a sneak peek. First look in seven weeks. So yeah, it just, you know, it’s a great way to just fire up synonyms.

Katie Robbert 23:24
Nice. I like that. And I would imagine, Chris, you know, especially since it’s a subject line, you could probably put in the guardrails to have, you know, write this no longer than X number of characters, or something like that to

Christopher Penn 23:39
guess what I’ve done is I’ve provided it now all the relevant facts to help with the construction of those subject lines as well. This is important, you can’t just, you know, again, you don’t want to leave very much up to chance you want to have as much as possible in the prompt, so that it knows what it is you’re talking about. So let’s go ahead and put this in the system.

John Wall 24:15
Yeah, isn’t it amazing? There’s like so much more variation in that, you know, it’s not just like, playing the swap out synonyms game, you’re getting totally different stuff.

Christopher Penn 24:24
Yep. As doing that all from the, the requirements. So if we think about this, this is nothing more than requirements gathering, right? And then it does the thing based on what you provided.

Katie Robbert 24:39
And so now in terms of an AV test, you know, if you’re running an email marketing, your system likely has some kind of an A B test function built in. So what you would do is you would have the body of your email and then load up all of these different headlines to then run, setup your test in that system, and then you can start to see You know what, the headlines that chat GPT wrote actually doing pretty well. Or I do pretty well on my own. And I don’t need chat CBT to be writing headlines for me. So that’s where you start to measure the effectiveness of using a tool like this in your marketing, is it performing better? Is it performing the same? Is it performing worse? You know, if you have a large email campaign, probably not the best time to be running a B tests, you know, you kind of want things to go well, and be predictable. You know, but that all comes down to your level of risk and what you can accept, is it a time to experiment? That really depends on if you’re okay with some of the emails not doing as well.

Christopher Penn 25:42
Exactly. So again, to what you were saying, Why do another test, what’s now switched up to you are going to do to some Instagram stuff?

John Wall 25:54
Yeah, it does make me feel bad for the times in the past where I’ve sat there and had to like crank out 15 versions of Google ads, to be able to do variants on copy there, it just makes life so much easier.

Katie Robbert 26:08
I mean, it’s like the early settlers, John, they had to turn their own butter. And now machines do it for you. I know

John Wall 26:13
this is this is the advent of the machines.

Katie Robbert 26:24
And so what Chris is doing is now you’re changing context, where there’s other elements included in an Instagram post versus an email subject line. So you’ve included things such as suggested caption, suggested image, and then that way, so it’s not going to give you an image, but it will describe the type of image that you could use alongside the caption.

Christopher Penn 26:58
I like that it has all the emoji in it.

Katie Robbert 27:02
This is something that you and I will never see eye to eye on Chris. For those who are new to the conversation, I am not a big fan of emojis. And Chris is a big fan of emojis. And we just we just have a difference of opinion. And it’s a respectful difference of opinion, it is just not my thing.

John Wall 27:25
It is going deep on emoji, though. It’s not just like a couple miles and stars. I mean, this is like, you’ve got some some,

Christopher Penn 27:32
yeah, it’s got all the analytics emoji.

Katie Robbert 27:40
Just like any other system, you know, you can now put these, you know, you can go through these and decide which of these do I want to put up on our company Instagram page to see does it drive more traffic to our GA four course or does not, you know, are people not engaging. And so this is where, you know, as Chris was showing his simple spreadsheet, you’d want to do something similar for any of the other AB tests that you’re running, to make sure that you’re actually gathering the results. Because otherwise, what’s the point of doing it in the first place. Because what you want to understand is, can chat GPT create something that is just as effective, if not more effective than what a human can create, you know, and so there’s going to be a lot of, you know, things that you still want humans to be creating. But for something like an Instagram caption, that might not be a bad idea, especially if you have a lot of social media posts that you want to start to get out there and increase the frequency in which you’re posting.

Christopher Penn 28:37
Exactly right. Now, if you want to do a more advanced system of measurement, the what we’ve shown with the spreadsheet is, is good, it’s a good place to start. There is a technique from biostatistics called survival testing, we have also been called propensity score matching, things like that. And what that does is you designate which are the treatments, aka the chat GPT driven, you know, made posts or emails or whatever. And then you designate everything else as your control. And it will go through your data, try to do apples to apples comparisons across the data and eventually come out with an assessment that says here is here is the change the lift from the treatment. Now this is synthetic data. This is not because we have not obviously run this yet. But this is an example of in this case for the for the treatment factor. The treatment resulted in 117% more conversions. 62% more engaged sessions. 34% more sessions in general 17% More scrolled users, meaning users scroll all the way down the page and a lower bounce rate. So in this case, the treatment that was applied, really lifted. This this set of pages up compared to other kinds of pages on our website. So this treatment would be considered highly successful. So if you start with a catalogue of the just the, the URLs or whatever, and then you can get the relevant data out of Google Analytics, you can build some very advanced models for understanding Wow, this this data did not really lift these posts up or or crater them.

Katie Robbert 30:29
So what do you think John? Are you going to record an episode of marketing over coffee and then have chat GPT-3, record an episode of marketing over coffee and see which one performs better?

John Wall 30:39
See what you can do? Well, the easy hit for this is transcripts, you know, we have a bunch of old transcripts that were automatically generated, just to paste them in here and say, hey, you know, proofread these and clean them up, I’m going to AV test that we’ll see how accurate the thing get. Because if it can get to 85 90% accuracy and cleaning of transcripts, then that just becomes a new way to do business.

Christopher Penn 31:01
I think it’s actually really good at that.

Katie Robbert 31:05
Well, and you know, when we started at the beginning, talking about use cases, you know, it’s one of the use cases that isn’t used as frequently as net new content generation. So definitely, you know, consider using Chachi Beatty to clean up transcripts to clean up copy, to do some editing. And then you can a B test that, you know, the AV test can also be something in terms of time savings and accuracy. It doesn’t have to be something externally facing. But what you really want to be doing is measuring the success and understanding is Chad GPT-2, making their lives easier and doing things better and enhancing and supporting or is it just the shiny object that we’re all getting distracted by and it’s no better than what our highly trained marketing team is already is already doing. And so, you know, we will continue to keep, you know, challenging you and expecting you to be testing these things. Because, unfortunately, people make these snap impulse decisions about these new tools. And you really need to put it through its paces before you say, You know what, this, this replaces my whole content marketing team, that’s probably not a great way to be approaching it.

Christopher Penn 32:17
Exactly. So this is an example to what John was saying, let’s fix grammar, spelling, nation.

John Wall 32:30
Oh, and you’ve got pro activated over here. So it’s not going to fight back on the size of anything.

Christopher Penn 32:39
So this is from this week’s In-Ear Insights. And what’s it’s doing, that’s very nice. It’s fixing a lot of the weirdness that transcripts create. So it’s, it’s adjusting the punctuation and making it a little bit cleaner, it doesn’t dramatically change the text. In fact, you know, the wording is, is pretty much word for word, but just the weirdness of the way transcripts come out the automated transcripts, this does a terrific job with them.

Katie Robbert 33:08
I think that makes a lot of sense. So any other thoughts on how to be a B testing? Chat? GPT?

Christopher Penn 33:21
I mean, that’s, it’s like everything. You’ve got you, you want to sit down and figure out what are the five P’s? What do you what’s the purpose? Who’s going to do it? What’s the process for doing it? We talked a lot about that today with the spreadsheets and things. The platform is the email, social media, text messaging, is it a blog post, deciding where you’re gonna test, and then choosing the good measures for measuring the performance? So like, what constitutes good measures, it might not be the analytics we chose today, right? If you are concerned about search, it might be search impressions, that is your your measure of success. But whatever it is, you need to make sure that you’re clear about it in order for the software and all of your tests to assess them correctly.

Katie Robbert 34:15
Make sense? John? Final thoughts?

John Wall 34:18
Yeah, a big thing was when we were talking about a be upfront that pretty much pigeon holed me, I was thinking about email and maybe some web stuff, but being able to use this across all the ad platforms, you know, especially when you’re doing campaigns where you have 510 15 variations. It’s a great way to make your life a whole lot easier instead of having to wordsmith it all yourself. Oh,

Christopher Penn 34:39
yeah, for sure. I mean, crank out a couple of 100 Google ads.

Katie Robbert 34:43
Yeah. And I think that that’s the really good takeaway is that, you know, it doesn’t have to be that boxed in traditional thinking of what an AV test is. There’s a lot of different ways that you can be testing the effectiveness of your content across multiple platforms. So hopefully from This episode, you’ll get some ideas on how to be testing your own content using chat GPT-2, especially if it’s something that your company or agency is looking to start utilizing even more.

Christopher Penn 35:11
The one other thing I would strongly suggest is if your team has technical skills, you should be using the chat GPT-2 API. This the web interface is kind of like the AI playground, it’s a great place to test things out. But then when you want to scale, use the API because you can that you can get a known prompt that works for you like, write 100, Google AdWords ads, or write an ad, Google ads about this topic, like we did with GA four. And just run that code over and over and over again, and you’d end up with hundreds or 1000s of email subject lines, or Google ads, copy whatever the case may be, you know, 10 at a time and chat TPTs is a time saver. But having systems that can do it, you know, by the hundreds of 1000s is really a big time saver.

Katie Robbert 36:01
I think that’s an excellent pro tip, Chris, thanks. Thanks for that. Anything else?

Christopher Penn 36:07
I think that’s it for this week. See you all next time. Thanks for watching today. Be sure to subscribe to our show wherever you’re watching it. For more resources. And to learn more, check out the Trust Insights podcast at trust insights.ai/t AI podcast, and a weekly email newsletter at trust insights.ai/newsletter Got questions about what you saw in today’s episode. Join our free analytics for markers slack group at trust insights.ai/analytics for marketers, see you next time.


Need help with your marketing AI and analytics?

You might also enjoy:

Get unique data, analysis, and perspectives on analytics, insights, machine learning, marketing, and AI in the weekly Trust Insights newsletter, INBOX INSIGHTS. Subscribe now for free; new issues every Wednesday!

Click here to subscribe now »

Want to learn more about data, analytics, and insights? Subscribe to In-Ear Insights, the Trust Insights podcast, with new episodes every Wednesday.

Leave a Reply

Your email address will not be published. Required fields are marked *

Pin It on Pinterest

Share This