\n<\/p>\n
AI fans like to rhapsodize about all the great things they can do with ChatGPT and other AI assistants. Here\u2019s a glimpse into how my agency uses an advanced form of ChatGPT to help us with copywriting for an email A\/B test.<\/p>\n
Although I can\u2019t reveal everything \u2014\u00a0I need to protect my client\u2019s privacy and competitive information \u2014\u00a0I\u2019ll share as much as possible, including the steps we used to build the test and how ChatGPT helped us get there.<\/p>\n
When we started working together, I told our private instance of ChatGPT that his name is Chad, and my name is Katie. Since then, Chad has become a valuable staff member. At first, we needed extra time to train him in how we do things at my agency. But it was time well spent because he now delivers what we\u2019re looking for with just a few refinements.<\/p>\n
Chad takes away the terror of the blank white page. He helps us launch our work faster, reducing the time we spend spinning our wheels trying to find a good starting point for writing copy. Then, he steps aside, waiting for us to edit and refine, do the actual work or give him another task.\u00a0<\/p>\n
We use a paid version of ChatGPT (currently it uses GPT-4o) because it keeps both ours and our client\u2019s intellectual property out of the training pool and gives us access to GPT-4o\u2019s memory feature, among other benefits. This saves us hours of update time, streamlines our operations and focuses our prompt writing on other tasks so that we\u2019re always working with our most updated information.\u00a0<\/p>\n
Also, because we use the paid service that has been trained with our own information, everything Chad produces is inspired by our work, not by whatever he picks up from outside sources.<\/p>\n
Dig deeper: How to use AI in email marketing without losing the human touch<\/a><\/em><\/strong><\/p>\n Chad meshes with our advanced testing methodology because it is far more extensive than just comparing a variant against a control. We develop the hypothesis and bespoke strategy for the testing program and turn Chad loose on creating those variants once we give him his prompts.<\/p>\n Holistic testing looks at all of the factors that go into optimizing an email campaign. We test entire emails against each other according to the hypothesis we created for the test. This goes beyond simply testing subject lines or calls to action.\u00a0<\/p>\n I created this method to derive more reliable insights about our customers \u2014\u00a0not just which subject lines get more opens in a single test but what motivates them to act. We can apply these insights throughout the company because our email subscribers represent our customer base.<\/p>\n We wanted to persuade more people to view and order their personalized products. We used orders as our success metric. We tracked open and clicks, but they were not the primary measurements.<\/p>\n A well-formed hypothesis is the foundation for any testing program, whether simple or complex. It gives you the \u201cwhy\u201d for the test, what you expect will happen and the parameters for setting up and running the test.<\/p>\n This was our hypothesis, which we wrote using what we learned in previous testing for this client and for others:<\/p>\n \u201cWe believe the email body copy that incorporates at least one element specifically tailored to appeal to each of the four personality types \u2014 spontaneous, methodical, humanistic and competitive \u2014 will generate more web visits compared to the control version of the email, which lacks this personalized approach.\u00a0<\/p>\n \u201cThis increase in web visits is anticipated because the personalized content is likely to resonate more effectively with a broader range of recipients, engaging their specific interests and motivations, thereby enhancing the likelihood of them visiting the website and converting.\u201d<\/p>\n<\/blockquote>\n The control is the email the client had been sending, with no copy personalized to reflect any of the four shopping motivations mentioned in the hypothesis. The variant, which we composed with Chad\u2019s assistance, includes copy that would appeal to each of those four motivations. We split our testing audience into two random sections and sent the control to one and the variant to the other.<\/p>\n Here is the prompt-and-response process that we used to create the copy for the variant email:\u00a0<\/p>\n Prompt 1: <\/strong>We ask Chad to familiarize himself with Bryan Eisenberg\u2019s Four Buyer Modalities<\/a>.<\/p>\n Prompt 2:<\/strong> I ask Chad to familiarize himself with my client\u2019s company, its products and brand tone of voice. I also asked Chad to list the benefits of my client\u2019s products.<\/p>\n Prompt 3: <\/strong>I tell Chad what we want. <\/strong>I asked him to update and improve the client\u2019s version of the campaign email to reflect our hypothesis and create the copy for Variant B. I added the hypothesis to the prompt, uploaded an image of the email and asked Chad to extract the copy from it. He returned the copy in text form so we could copy and adjust it. We also asked for some refinements.<\/p>\n Prompt 4: <\/strong>I provide more specific direction, asking him to blend the copy into one paragraph addressing all four personalities, not one paragraph per personality as he had provided.<\/p>\n Done!<\/strong> I now have the first draft of an opening paragraph that incorporates the elements I outlined in our hypothesis. The copy presents the benefits clearly and concisely while including elements targeted toward the four shopper personalities I mentioned in the hypothesis.\u00a0<\/p>\n Edit and improve. <\/strong>Now that Chad had helped to create the first draft of Variant B, it was time for me to roll up my sleeves and refine it, so that it became the final version. Using the single paragraph plus the four paragraphs previously provided, I created two versions and asked the team to vote on which version they preferred and to rationalize why. This was a beneficial exercise, as it meant they began to understand each of the personalities.<\/p>\n Dig deeper: 3 ways email marketers should actually use AI<\/a><\/em><\/strong><\/p>\n Here are my tips for learning and using genAI to streamline your workload and improve your email marketing and testing:<\/p>\n The process I outlined here uses higher-level genAI. If you have not worked with genAI, large language models like GPT or chatbots like ChatGPT, don\u2019t try this yet. Instead, spend time learning the process.<\/p>\n As with any skill, you need time to become proficient at using genAI. Your first attempts likely will not be as productive as ours, but neither were ours when we began working with chatbots. But we kept working away and eventually learned how to speak to a non-sentient being without relying on unspoken cues and clues.<\/p>\n Experiment with your prompt writing. This is an essential part of using genAI effectively. If you don\u2019t put time and effort into writing prompts that your chatbot will understand, you won\u2019t get good results and you\u2019ll probably spend just as much time going back and forth with your chatbot as you would have if you had gone it alone.<\/p>\n I have never used a published prompt. I consider Chad to be a member of our team (a young, eager junior) and so I treat briefing him as just that.\u00a0I give him a brief \u2014 not a prompt \u2014 of what I want him to do and achieve.\u00a0<\/p>\n When you think like this, you innately provide your bot with everything it needs to deliver the request. About 70% of the time, I will ask him whether he has everything he needs and tell him to ask me questions to ensure he has all the necessary information.\u00a0<\/p>\n As the saying goes, \u201cGarbage in, garbage out.\u201d<\/p>\n Here\u2019s another saying: \u201cYou get what you pay for.\u201d Yes, you can use free AI assistant services like ChatGPT. ChatGPT\u2019s free service is a good training ground for learning prompt writing and working effectively with the assistant.\u00a0<\/p>\n However, your work is not necessarily protected from being used to train other users. When you are ready to incorporate your own competitive or sensitive information, use a paid service that you can configure to keep your inputs and results private.<\/p>\n Your prompts should reflect elements of your hypothesis so that you are testing for reliable results.\u00a0<\/p>\n Chad\u2019s not human, but we treat him as if he were. We gave Chad a name because it helps us frame questions better as if we were briefing a human coworker. Plus, we get better results when we frame our prompts in full sentences and frame our responses with \u201cplease\u201d and \u201cthank you\u201d \u2014\u00a0just as if you were briefing a team member.<\/p>\n I focused my attention here on using generative AI specifically for copy testing. If you would like advice on using chatbots for other parts of your email program, such as writing campaign briefs and message copy, read two of my previous MarTech articles:<\/p>\n I hope this backstage look shows you how working with Chad has eliminated many steps from the creative process without short-circuiting it or compromising our or our clients\u2019 competitive information. Try it for yourself, and let me know how it works for you!<\/p>\n <\/p>\n \n<\/div>\n Contributing authors are invited to create content for MarTech and are chosen for their expertise and contribution to the martech community. Our contributors work under the oversight of the editorial staff<\/a> and contributions are checked for quality and relevance to our readers. The opinions they express are their own.<\/em><\/p>\nUsing genAI in copywriting for testing<\/h2>\n
What is holistic testing?<\/h3>\n
The campaign goal<\/h3>\n
The test hypothesis<\/h3>\n
\n
Testing set-up<\/h3>\n
Process<\/h3>\n
\n
\n
\n
\n
\n
4 tips for creating a good relationship with your Chad<\/h2>\n
1. Take the time to get it right<\/h3>\n
2. Pay for a specialized service<\/h3>\n
3. Always work from your hypothesis<\/h3>\n
4. Be nice to your bot<\/h3>\n