I had ChatGPT do my homework, and then I critiqued it.

Obviously, using ChatGPT to do homework is unethical and illegal. But it wasn’t this time! My assignment was to have ChatGPT create a blog post for me about the future of AI in digital marketing. After some messing around with the prompt (which I will talk more about later), this is what it came up with.

Prompt (kinda) “Imagine you are a digital marketer. Write an informational blog post for LinkedIn about how AI and machine learning could be used in the future of digital marketing.”

ChatGPT: “As a digital marketer, I am always excited about exploring new technologies and tools that can help me deliver better results for my clients. And one technology that has caught my attention in recent years is artificial intelligence (AI) and machine learning (ML).

AI and ML have the potential to transform the future of digital marketing by enabling marketers to make data-driven decisions, automate repetitive tasks, and deliver personalized experiences to their customers. In this post, I will explore some of the ways AI and ML could be used in the future of digital marketing.

Predictive Analytics

One of the most exciting applications of AI and ML in digital marketing is predictive analytics. By analyzing vast amounts of data from multiple sources, AI algorithms can predict customer behavior, preferences, and needs. This information can be used to create personalized marketing campaigns that resonate with individual customers. According to a report by Aberdeen Group, companies that use predictive analytics in their marketing strategies have a 2.9 times higher click-through rate and a 3.1 times higher open rate than companies that don't.

Chatbots

Chatbots are another application of AI and ML that have gained popularity in recent years. Chatbots are software programs that use natural language processing (NLP) to interact with customers and provide support or information. By using AI and ML, chatbots can learn from customer interactions and improve their responses over time. This means that customers can get the information they need quickly and efficiently, without the need for human intervention. According to a report by Chatbots Magazine, chatbots can save businesses up to 30% in customer support costs.

Personalization

Personalization is a key trend in digital marketing, and AI and ML can help take it to the next level. By analyzing customer data, AI algorithms can create personalized experiences for individual customers, such as personalized product recommendations, email campaigns, and website content. Personalization can help businesses build stronger relationships with their customers and increase customer loyalty. According to a study by Segment, 71% of consumers say that personalized experiences influence their purchasing decisions.

Image and Voice Recognition

Image and voice recognition are two more applications of AI and ML that could transform the future of digital marketing. Image recognition algorithms can analyze images and videos to identify products, logos, and other visual elements. This information can be used to create more targeted and relevant ads for customers. According to a report by MarketsandMarkets, the market for image recognition is expected to grow from $16.6 billion in 2020 to $38.9 billion by 2025. Voice recognition, on the other hand, could be used to create more personalized experiences for customers. For example, a customer could use voice commands to order a product, and the AI algorithm could personalize the experience based on the customer's previous interactions with the brand. According to a study by PwC, 49% of consumers use voice assistants to research products and services.

In conclusion, the future of digital marketing looks bright with the integration of AI and ML. Predictive analytics, chatbots, personalization, image and voice recognition, and many other AI-powered tools and technologies are transforming the way marketers reach and engage with customers. By leveraging these technologies, businesses can create more personalized and relevant experiences for their customers, increase customer loyalty, and ultimately drive more revenue. As digital marketers, it's important for us to stay up-to-date with the latest AI and ML trends and tools to continue delivering better results for our clients.”

?

Wow! What a good response, and it certainly blew away my expectations. Using ChatGPT is a very unique and fun experience. I highly recommend trying it yourself and asking it about something you’re interested in.

The ChatGPT experience:

ChatGPT knows a lot. Asking different marketing questions leads to some great answers and creative solutions. However, the magic comes from the prompt. You may have noticed I put “(kinda)” after my initial response. What I wrote up there, “Imagine you are a digital marketer. Write an informational blog post for LinkedIn about how AI and machine learning could be used in the future of digital marketing”, was my initial prompt. It gave me a similar yet different answer to what I said it wrote. I noticed initially it made a lot of claims without data, so I asked it for more data points to support what it wrote. Specifically, I asked it “could you include more data in your first response?”. It gave me some data and sources for the data when I asked about it further. However, I wanted to then integrate those data points into the actual blog post.

Since ChatGPT remembers the conversation, I asked it “Can you repeat the initial prompt but add one piece of data to each of your points”. I thought this would be the final question I asked, but no. It gave me a whole blog post but forgot to add the conclusion this time. How mildly annoying. Finally, I asked it to add a conclusion to the response above and it finished the blog post for me. A strangely long experience, but the end result turned out well! This whole experience shows just how important your prompt is. I thought my initial prompt was already very specific, but I left out many important parts.

Here are some tips for prompts to get ChatGPT to give you exactly what you want on the first try:

• Give it context. Notice how I said “Imagine you are a digital marketer” at the beginning. This helps ChatGPT know what to write and the style it needs to write in. It also helped keep the response relevant to specifically digital marketing, rather than just analytics.
• Be specific. That whole “adding data” problem could have been avoided if I asked it to add data in my first prompt. Be concise and specific about exactly what you want.
• Give it a platform it’s writing to. Copy is different on every platform. A tweet is worded much differently than a blog post. ChatGPT will tailor its content to whatever platform you specify, so be sure to mention it in the prompt.
• Give it a tone. If your copy is supposed to be light-hearted, be sure to mention that in your prompt. Clearly, this blog is meant to be informational, so I told ChatGPT to write it that way. This affects the style of your prompt dramatically.
• Refine refine refine. Never be satisfied initially, the bot doesn’t care if you nitpick its answer. If the response is too long, ask ChatGPT to make it shorter. If it forgot to add an intro, tell it to add an intro. You can keep adding and removing aspects of what it wrote to make the copy perfect.

These are just some tips I have realized in my time working with ChatGPT. Here is a great blog post that goes into more detail about how to write a great ChatGPT prompt.

So, how did ChatGPT do?

After much refining, the blog that ChatGPT wrote initially looks great. However, it lacks a lot of detail. The blog hits all the right points but glosses over them without explaining why AI will impact that area. A direct quote from the blog says “Personalization can help businesses build stronger relationships with their customers and increase customer loyalty”. This is true, but it fails to explain why personalization helps build stronger relationships. Personalization works because customers feel more valued, connected, and satisfied with the brand which helps to increase loyalty. ChatGPT only covers the basics and does not elaborate further.

Additionally, the way ChatGPT writes feels robotic. Every sentence it writes has a similar structure, tone, and feel. The best copy combines many different lengths and styles into it. Here is a quote from Gary Provost, a writing instructor, that highlights this exact concept.

ChatGPT’s work is not perfect. It has many flaws and can even flat-out lie to you if you’re not knowledgeable enough to catch it. However, ChatGPT creates an amazing basic outline for you to build off of. It is a great resource that all professions should be trying to utilize. Especially marketers.

How digital marketers can use ChatGPT

The obvious use that comes to mind is copywriting. From slogans to blogs, ChatGPT can create interesting copy in an instant. Using the right prompt will save marketers a ton of time so they can focus on other aspects of digital marketing. I find it unlikely that copywriting will continue to be a profession in the future. Copywriting may be part of a bigger marketing job, but I think AI systems will replace full-time copywriters eventually.

ChatGPT is also surprisingly creative. If you are brainstorming ideas, it might be good to ask it for an idea. It could create a good idea your team did not think of. Thinking of AI as an additional creative team member can help prevent groupthink and lead to more innovative solutions.

ChatGPT is a unique tool that has taken the digital marketing world by storm. Its capabilities are beyond any other AI system that came before it, and it is only going to improve in the future. What may seem like an impractical tool today may become the leading technology in the future. Digital marketing is constantly evolving, and a good digital marketer should stay on top of these innovations.