So when I saw\u00a0ChatGPT<\/a>\u00a0in action, I had two thoughts.<\/p>\n One, my entire career is ruined and I’d better learn how to weld or something because it’s like five months away from stealing my job and maybe my wife.<\/p>\n And two, I wonder how this works for cold email.<\/p>\n I ran\u00a0several tests using ChatGPT to figure out what it can and can’t do for cold emailers<\/strong>.<\/p>\n Here are five great ways ChatGPT (and its future descendants) can aid your cold email copywriting<\/a>.<\/p>\n And… there are also five big ways ChatGPT\u00a0alone<\/em>\u00a0won’t be able to take over your entire cold email operation. You can (and should) read up on those here as well.<\/p>\n Here are five ways\u00a0you can start using ChatGPT immediately<\/strong>\u00a0in your cold email copywriting.<\/p>\n I’m not going to bury the lede here:\u00a0ChatGPT can absolutely handle the first drafts for most cold emails.<\/strong><\/p>\n No more staring at a blinking cursor wondering how to dive in.<\/p>\n For this experiment, I decided I would be a lead gen agency promoting our services to real estate agents in Bethesda, Maryland.<\/p>\n My first prompt to ChatGPT was:<\/p>\n The result:<\/p>\n I don’t love it. It’s\u00a0too wordy<\/strong>\u00a0and messed up a crucial fact. (I’m not a fellow real estate agent, I’m from a lead gen agency. Well, in reality, I’m neither. But in this example case I’m the latter.)<\/p>\n So I prompted ChatGPT to tighten it up and to get the fact right.<\/p>\n That’s much better. Now that I got that squared away, I can have ChatGPT\u00a0try writing the email a few other ways<\/strong>.<\/p>\n I also tried out other prompts like You can keep refining your email ad nauseam, trying different styles, tones, and lengths<\/strong>. And by the time you’re done, you should have a great\u00a0first draft<\/em>.<\/p>\n I wouldn’t recommend sending this email as-is. It’s\u00a0too generic to be effective<\/strong>. (Or, at least, to hit maximum effectiveness.)<\/p>\n But as a jumping off point? ChatGPT can write great first drafts to save you lots of time.<\/p>\n And if you decide you\u00a0do<\/em>\u00a0want to roll with ChatGPT’s result unedited? At least\u00a0you probably won’t get caught<\/strong>.<\/p>\n Here was the result when I checked the first cold email with an AI and plagiarism detector:<\/p>\n ChatGPT can also give you\u00a0subject lines<\/a>\u00a0to try out with your email. And\u00a0it can bang out those subject lines at scale<\/strong>.<\/p>\n Those aren’t all winners but there are three or four in there that caught my eye has having potential.<\/p>\n And as with the email copy, I can\u00a0direct ChatGPT on tone<\/strong>.<\/p>\n This is, hands down,\u00a0my favorite thing ChatGPT can do for cold emailers<\/strong>.<\/p>\n I got my hands on 40 possible subject lines in less than a minute. Not all are winners, but each list of 10 has a few potential candidates. (Plus if I’d tried to write 40 subject lines myself, it would’ve taken an hour and not all would be winners there either.)<\/p>\n And if I wasn’t happy with this 40, I could keep on generating to find better and better subjects. At least until I ran into the dreaded ChatGPT And that’s not all: ChatGPT can also generate subject line +\u00a0preview text<\/a>\u00a0pairs.<\/p>\n It took me a lot of work on prompts to get it right (ChatGPT\u00a0really<\/em>\u00a0wanted to write long preview text), but these are impressive results:<\/p>\n So how do you choose from the subject lines and email messages you’ve generated?<\/p>\n With this many possibilities in front of you,\u00a0A\/B testing<\/strong><\/a>\u00a0is pretty much essential<\/strong>.<\/p>\n Here’s how to\u00a0use GMass’s spintax to run quick split tests on multiple email messages<\/strong>.<\/p>\n (You can also use this same technique on subject lines. Yes, you\u00a0could<\/em>\u00a0test subjects and email messages together. But I always recommend against testing multiple variables in\u00a0single A\/B tests<\/a>.)<\/p>\n In the Gmail compose window,\u00a0connect your Google Sheet<\/a>\u00a0to GMass and enter your subject line.<\/p>\n Then type Type Once you’re done adding variations, type Now go into the\u00a0GMass settings<\/strong><\/a>\u00a0for the campaign. Go to the\u00a0Advanced<\/strong>\u00a0section and check the box next to\u00a0A\/B Test<\/strong>.<\/p>\n Your options are:<\/p>\n Percentage to send before making a decision.\u00a0<\/strong>In the screenshot above, the first variation would go to 20% of your list and the second variation would go to a different 20%. That makes up the 40% total to send to before making a decision. After that,\u00a0the remaining 60% of your list would get the “winning” variation<\/strong>.<\/p>\n Decide when?\u00a0<\/strong>You can choose\u00a0how long to run your test<\/strong>\u00a0before declaring a winner.<\/p>\n Decide how?<\/strong>\u00a0If you choose automatic, GMass will send your winning variation to the remainder of your list at the end of the testing period. And you can decide how GMass will determine the winner: Using opens, clicks, or replies. If you choose manual, you’ll receive an email with the A\/B test results where you can decide which variation to send to the rest of your list.<\/p>\n A\/B testing is\u00a0this<\/em>\u00a0easy with GMass. So with the volume of possibilities you’ll get from ChatGPT,\u00a0it makes sense to\u00a0<\/strong>always<\/strong><\/em>\u00a0test at least a few of them<\/strong>\u00a0in every campaign.<\/p>\n We hear it all the time: No one likes writing\u00a0auto follow-ups<\/a>. You put everything you had into that initial email.<\/p>\n The follow-ups then become a challenge to see how many different ways you can say, “Hey did you see my original email? Are you interested?”<\/p>\n So\u00a0offload your follow-ups onto ChatGPT<\/strong>.<\/p>\n It’s a lot easier to use theirs (with some edits) than start from scratch on your own.<\/p>\n I prompted The emails were too generic for my liking so I tried a few other prompts. And ultimately, I found a prompt that got ChatGPT to write a sequence using the strategy I wanted.<\/p>\n Much like the initial campaign email ChatGPT created,\u00a0I wouldn’t use these emails without editing and tweaking them first<\/strong>. However there’s a solid foundation to work from here so\u00a0these will absolutely save me some time<\/strong>.<\/p>\n To add those follow-ups to GMass, open the\u00a0settings<\/strong>\u00a0for your campaign and go to the\u00a0Auto Follow-up section<\/strong>.<\/p>\n You can set the\u00a0trigger and timing<\/strong>\u00a0for each follow-up. For example, I’m sending the first one after two days if I haven’t received a reply; the second one after five days; and the third one after nine days.<\/p>\n So far I’ve covered ways ChatGPT can\u00a0write<\/em>\u00a0emails and related copy. But\u00a0it can also\u00a0<\/strong>review<\/strong><\/em>\u00a0your copy<\/strong>\u00a0in ways other tools can’t.<\/p>\n There are tools out there to help with grammar and writing (your Grammarlys of the world and such).<\/p>\n ChatGPT can replace a lot of what they offer<\/strong>; here’s an email I fed it with three errors to see if it would catch them. It did \u2014 and even suggested a new clarifying sentence to add.<\/p>\n That takes ChatGPT beyond a copy editor; it’s also a developmental editor.<\/p>\n And ChatGPT has another, even more valuable function in the editing process: It can\u00a0read your email and gauge its tone<\/strong>.<\/p>\n This could be\u00a0quite valuable for non-native speakers<\/strong>\u00a0\u2014 or native speakers who want a second opinion.<\/p>\n For example, I had ChatGPT evaluate the tone on one of the follow-up emails it produced. Here’s what it told me:<\/p>\n Then I tested it by writing a hostile email. And it correctly recognized I was being too aggressive.<\/p>\n Finally, I tried an email with an issue we hear about a lot from non-native English speakers: Being too formal<\/strong>. ChatGPT was able to recognize that this message was unnaturally formal.<\/p>\n I could see a lot of cold emailers using these editing functions<\/strong>\u00a0going forward. Even if you aren’t going to use ChatGPT on the email copywriting side it’s a handy tool to have on the copy editing side.<\/p>\n Plus it never hurts to have a second set of eyes on an email. Even cold, unfixing robot eyes.<\/p>\n Alright. So we just witnessed ChatGPT write an email, dozens of subject lines and preview text options, and follow-ups. We even had it proofread\u00a0and<\/em>\u00a0check our tone.<\/p>\n So are we all out of a job?<\/p>\n Not yet. We’re closer to being wiped out than ever before… but we’re not obsolete yet.<\/p>\n Right now,\u00a0ChatGPT is like a warp zone in a video game<\/strong>. You can use it to skip a lot of the time-consuming grunt work \u2014 but it won’t defeat Bowser for you.<\/p>\n And in the case of cold email, the warp zone takes you past steps like writing multiple drafts, subject lines, and follow-ups. But the big boss at the end is creating a cold email that\u00a0actually<\/em>\u00a0converts. And ChatGPT can’t do that for you.<\/p>\n Here are five crucial facets of cold email where you’ll need to take the reins from AI.<\/p>\n As we saw earlier, ChatGPT can produce email drafts and, depending on how you prompt it, can revise it and tweak those drafts in endless ways.<\/p>\n But even if you spend hours refining your prompts and coaching ChatGPT to write better and better messages,\u00a0you’ll still want to get in there to tweak the copy at the end<\/strong>.<\/p>\n An effective\u00a0cold email<\/a>\u00a0needs<\/em>\u00a0to do four things:<\/p>\n ChatGPT can address all four of those in\u00a0generic<\/strong>\u00a0ways. But no matter how well you prompt it,\u00a0it will never achieve a full understanding of who you’re emailing, what you offer, and who you are<\/strong>.<\/p>\n I tried getting as specific as possible when prompting ChatGPT to add social proof to an email. But the results still have a generic vibe. I’d be better off writing that section manually than trying to prompt my way to success.<\/p>\n ChatGPT also trends toward being way too wordy. You can prompt it to keep things shorter \u2014 but\u00a0you’ll still find extraneous words throughout the copy<\/strong>.<\/p>\n You want\u00a0every word of a cold email to matter<\/strong>.<\/p>\n So sentences like “Our team of experts uses a variety of proven tactics and strategies to target potential clients in your area and get them interested in your services” are antithetical to your mission.<\/p>\n That’s a\u00a0whole lot of words just to cough out something painfully generic<\/strong>. What lead gen agency\u00a0doesn’t<\/em>\u00a0do everything described in that sentence? That’s not a differentiator.<\/p>\n ChatGPT can lay the foundation for your cold email \u2014 but you need to take over from there.<\/p>\n Cold emails need\u00a0personalization<\/a>\u00a0to work. That was true before ChatGPT and it’s true after.<\/p>\n And cold emailers have been trying to use AI for personalization for a few years now. There’s an entire niche of\u00a0cold email AI line writers<\/a>\u00a0which… um… casually stalk your contacts’ website and LinkedIn, then write personalized opening lines.<\/p>\n Of course, those are all misconstruing “reciting facts about a person” with “personalization.” The\u00a0most effective form of personalization<\/strong><\/a>\u00a0is demonstrating you understand a person’s business \u2014 and their needs and problems<\/strong>.<\/p>\n ChatGPT can’t really do either of the types of personalization I’ve described.<\/p>\n It won’t do the whole stalking bit; ChatGPT doesn’t do internet research based on your prompts.<\/p>\n So there are no opening lines here about “I heard you on XYZ podcast and you provided some great insights” or “I see you attended the University of Kansas in 2005, must have been a great time while getting a great education.”<\/p>\n And it may\u00a0try<\/em>\u00a0to address a recipient’s problem… but it’s just guessing. And, again,\u00a0it trends generic in its guesses<\/strong>.<\/p>\n You<\/em>\u00a0don’t have to be generic. You can take the time to research an industry, business, and market to accurately ascertain a recipient’s problem and how to best address it.<\/p>\n Using the running example through this article, you could research the Bethesda, Maryland, real estate scene. You could find who the top agents are.<\/p>\n Then, you could reach out to the agents who aren’t on that list. Offer your services which will help them overtake the\u00a0specific<\/em>\u00a0top agents in their market.<\/p>\n ChatGPT is wildly impressive, but\u00a0personalization still needs to come from a person<\/strong>.<\/p>\n There are lots of proven cold email formulas you can use for your copywriting.<\/p>\n You might like the Problem-Agitate-Solution template. Or the Attention-Interest-Desire-Action template. Or the Star-Chain-Hook method. Or one of the many other methods for writing concise, effective sales copy.<\/p>\n ChatGPT doesn’t write with that level of nuance. As I’ve said earlier, it’s wordy. It often\u00a0lays out the information in the email without instinctively building toward the close<\/strong>.<\/p>\n I’ve tried to get it to follow copywriting best practices and it does its best… but still can’t quite nail them. For example, this is getting there but not what I’m looking for…<\/p>\n So… if you want ChatGPT to follow your preferred formula, you’ll need to work hard on different prompts. And even after you get ChatGPT’s best result \u2014 it will still take editing and finessing on your part.<\/p>\n ChatGPT can handle a lot of your writing but\u00a0it’s not ready to take over on strategy<\/strong>.<\/p>\n You’ll still need to figure out the strategic aspects for your campaign like:<\/p>\n ChatGPT will\u00a0try<\/em>\u00a0to give you advice on these strategic decisions if you prompt it to do so… but the advice is generic.<\/p>\n Which is what you’d expect. It’s regurgitating middle-of-the-road answers from the hundreds of blog posts from which it learned.<\/p>\n Here are its thoughts on follow-up sequences.<\/p>\n And here are its thoughts on scheduling.<\/p>\n ChatGPT won’t make any definitive, well-reasoned strategic suggestions<\/strong> on your behalf.<\/p>\n You’ll still need to make those calls yourself to have a successful campaign.<\/p>\n So you used ChatGPT to help you write a great email campaign. You sent that campaign out to your list.<\/p>\n And now… you’re on your own. The robot has left the building.<\/p>\n You’ll need to handle everything that comes\u00a0after you send a campaign<\/a>.<\/p>\n Most important:\u00a0Handling replies<\/strong>. Yes, in theory you\u00a0could<\/em>\u00a0turn to ChatGPT to write responses to your prospects’ replies. But in most cases, when someone replies, they’re asking for specifics. And ChatGPT doesn’t do specifics.<\/p>\n Other things you’ll need to handle on your own are:<\/p>\nChatGPT Cold Email: Table of Contents<\/h2>\n
\n
5 Ways ChatGPT Can Help You with Cold Email Copywriting<\/h2>\n
1. Write the first draft of your email copy (in different styles)<\/h3>\n
write a cold email promoting my lead generation agency's services to real estate agents in Bethesda, Maryland<\/code><\/p>\n![\"ChatGPT](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-firstemail-tinified.png\")
<\/a><\/p>\ncan you make that email shorter, and also remove the part about me being a fellow real estate agent?<\/code><\/p>\n![\"A](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-revisedfirst-tinified.png\")
<\/a><\/p>\ncan you make it funnier?<\/code> (I highlighted its jokes in yellow.)<\/p>\n![\"A](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-humorfirst-tinified.png\")
<\/a><\/p>\ncan you make the email feel more urgent?<\/code>… can you write the email with a sense of scarcity, letting them know we're not taking on many more clients?<\/code>… and can you make the email just 4 sentences?<\/code><\/p>\n![\"Originality](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-originalityscore-tinified.png\")
<\/a><\/p>\n2. Give you subject line ideas<\/h3>\n
please write 10 possible subject lines for that email<\/code><\/p>\n![\"Subject](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-firstsubjects-tinified.png\")
<\/a><\/p>\n![\"More](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-moresubjects2-tinified.png\")
<\/a><\/p>\nToo many requests, please slow down<\/code> message.<\/p>\n![\"Preview](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-previewtext-tinified.png\")
<\/a><\/p>\n3. Give you A\/B testing possibilities<\/h3>\n
{{spin}}<\/code> and paste in the first variation of your email.<\/p>\n{{variation}}<\/code> and paste in another variation of your email. You can repeat this over and over to test different copy options for this campaign<\/strong>. (Just make sure your list is big enough to send each variation to a nice-sized sample.)<\/p>\n{{end spin}}<\/code>.<\/p>\n![\"Setting](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-setupab-tinified.png\")
<\/a><\/p>\n![\"A\/B](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-absettings-tinified.png\")
<\/a><\/p>\n4. Writing automated follow-ups<\/h3>\n
can you write 3 short follow-ups to the email that will go to people who do not respond?<\/code><\/p>\nPlease write three follow-up emails to send to people who don't respond. Ramp up the urgency with each email and make sure the final email lets them know it's our last time reaching out.<\/code><\/p>\n![\"Good](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-followups-tinified.png\")
<\/a><\/p>\n![\"Setting](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-setupautofollows-tinified.png\")
<\/a><\/p>\n5. Proofreading, gauging tone, and help for non-native speakers<\/h3>\n
![\"ChatGPT](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-proofread-tinified.png\")
<\/a><\/p>\n![\"Evaluating](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-toneofown-tinified.png\")
<\/a><\/p>\n![\"Detecting](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-hostile-tinified.png\")
<\/a><\/p>\n![\"Detecting](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-formal-tinified.png\")
<\/a><\/p>\n5 Crucial Cold Email Elements Where You Can’t Rely on AI<\/h2>\n
1. Writing complete, ready-to-send drafts<\/h3>\n
\n
![\"Social](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-socialprompt-tinified.png\")
<\/a><\/p>\n2. Personalizing your cold emails the right way<\/h3>\n
3. Following cold email copywriting best practices<\/h3>\n
![\"Attempting](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-aidaattempt-tinified.png\")
<\/a><\/p>\n4. Campaign strategy<\/h3>\n
\n
![\"Advice](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-followupadvice-tinified.png\")
<\/a><\/p>\n![\"Scheduling](\"https:\/\/www.gmass.co\/blog\/wp-content\/uploads\/2022\/12\/chatgpt-scheduleadvice-tinified.png\")
<\/a><\/p>\n5. Handling everything that comes\u00a0after<\/em>\u00a0you send your campaign<\/h3>\n
\n