Comparing Ai vs. human generated content writing

Emily Gertenbach
Jun 27, 2022

If you search for “Ai content writing” on Twitter, there’s a nearly endless stream of results. Most of them are marketing tweets talking about whatever the hot new artificial intelligence content writing tool is; a few are discussing what it was like to use one. And it’s definitely a hot topic in search — just look at this five-year graph from Exploding Topics:

A teal chart shows an upward trend for keyword searches

The idea behind Ai content writing is simple, and appealing: don’t spend time writing copy or paying someone to do it. Instead, pay one flat fee a month (or nothing! Some are free!) and have a computer write your content for you.


It sounds almost too good to be true...and it is. Kind of.


Ai writing can be a real mixed bag


It’s 100% true that Ai content creation tools exist, and they do work on a functional level. If you give the Ai writer a prompt, it will produce content for you. Whether or not it’s high-quality content you want, though, is another story.


Now, you may be thinking to yourself, “of course you're going to say that, you’re a writer. You don’t want to find your job outsourced to a machine.” And you aren’t wrong, it’s true. I wouldn’t be delighted to find myself replaced by GPT-3 or LaMDA (which, despite recent news reports, is not actually sentient).


But, I like technology and I’m willing to admit when I’m wrong. So I tested some Ai content writers. And I gotta say . . . by and large, they aren’t ready for prime time. I can definitely see that they will be ready for widespread content marketing use one day, and I’ll need to learn to play nicely with the robots. But we aren’t there yet.


My first experience with an Ai content writer


My curiosity about Ai writing began to pick up when I heard about a company that claimed it could create fully unique content outlines for writers using its Ai technology. That piqued my interest. I’m not ready to be fully be replaced by a machine, sure, but I can recognize the value in using Ai to support my work. I already use Clearscope, which is a tool that analyzes SEO content and evaluates its ability to rank against competitors. It’s really handy.


I signed up for the company’s Ai content generator tool. I’m not going to name names, but . . . if you’re in the content world you’ve definitely seen their ads (or you will after reading this — thanks, algorithm!)


To test this program out, I prompted the Ai to create a long-form content outline based off of a topic I’d already outlined for one of my clients. I wanted to see how it compared to what I put together.


A big problem


What I found was that the program directly copied an article from my client’s largest competitor, including pulling text and headers verbatim from that competing content. I knew this was the case because I had very recently read all of that competing content as part of my research process.


If I hadn’t realized it though, and actually relied on the program to do my blog article outlining, I would have wound up with something probably bordering on plagiarism. Not great. Admittedly, the tool was accurate, but to use it would still require a heavy dose of human involvement and intervention.


Testing two freemium Ai writing tools


That experience left me even more curious as to how some of the other Ai content writing software tools I hear about work in practice. While the original tool I tried was specifically geared toward outlining, I wanted to see what some other programs marketed for full-on website copy creation could produce.


So, we’re going to do a little test. Here’s how it will work:

  1. I’m using a topic I’ve already written about for clients and am familiar with: campaign tagging.
  2. I’ll feed keywords on this topic — ones I know I can get clients to rank for when creating organic content — into each Ai tool.
  3. I’ll adjust the Ai tool’s settings and request that it continues to produce content until I hit whatever the free or trial plan maximum is for that particular product.
  4. We’ll compare it to some original content I’ve written on the same topic, keeping in mind adjustments for length.


My point of reference for this test will be an article about campaign tagging that I wrote for a client. The article went live in January 2022. At the time of writing this comparison piece, my client’s original article is ranking on the first page of Google for “campaign tagging,” “url tagging,” and five other keywords. The draft I submitted to my client was over 3,500 words long and had a Clearscope score of A-, which was recommended in order to be competitive.

A screenshot of a website shows a content score of A-

My inaugural Ai content experience was with a paid tool. Typically, I expect a paid service to offer a higher degree of accuracy than a free one, but that isn’t guaranteed. As such, I’m going to test two other Ai writing programs that use a free or freemium model.


Test subject #1


I learned about our first test program while looking up Ai content writing keywords in Ahrefs — it’s definitely getting increasing attention in search. The company behind this tool says that it can create blogs, ad copy, and other types of content using “state of the art language Ai” in more than 30 languages and 20 tones of voice.


Interestingly, I noticed several typos (mostly around the use of possessives) on the product landing page. I have no way of knowing if they used their own product to create the content, but it gave me pause.


This product does bill itself as an Ai writing assistant and the landing page repeatedly states that it “helps” writers create content faster. I do appreciate the relative honesty here — it’s not touted as a complete writer replacement tool.


  • When setting up my test, I got to tell the Ai:
  • What language to write in
  • What tone to use
  • My intended use case for the content
  • Whether I wanted one or more variations on the result
  • How creative or factual I’d like to be (represented as a sliding scale)


After setting up my parameters, I could enter up to 125 characters to explain the topic and another 125 characters’ worth of keywords. Here’s what I wound up with:


  • Language: English
  • Tone: Informative
  • Use case: Blog sections
  • Variations: 1
  • Creativity: 0 (i.e., most factual)
  • Topic: How to do campaign tagging to track URLs for digital marketing
  • Keywords: Campaign tagging


I asked the Ai to return two paragraphs of content. This is what I got:

Campaign tagging is a process of adding a unique identifier to each URL in a campaign. This helps marketers track the performance of their campaigns and identify which URLs are performing better than others.


Campaign tagging is an important part of digital marketing because it helps marketers track the performance of their campaigns and identify which URLs are performing better than others. Campaign tagging is also important for SEO purposes because it helps search engines index content more efficiently.

This is all factually accurate, but it’s pretty top-level and a little repetitive. If I was going to use this intro to start an article on campaign tagging, I’d flip the two paragraphs, add more content and a subhead in between, and try using it as an introduction.


Without changing any variables, I asked the text generator to produce more content:

Campaign tagging is a process of adding metadata to URLs to track the performance of a campaign.


Campaign tagging is a process of adding metadata to URLs to track the performance of a campaign. This can be done by using Google Analytics or other marketing tools.


Campaign tagging is an important part of digital marketing because it helps marketers understand how their campaigns are performing and what they need to do in order to improve them.

Again, this is all technically correct but very repetitive. It’s clearly picking up on keywords and concepts beyond the sentence I entered during setup, but it’s not able to dive deeper.



Next, I adjusted the creativity level to medium. The Ai returned:

Campaign tagging is a powerful way to track URLs for digital marketing. It helps marketers to know which channels are generating the most conversions and can also be used to track offline conversions. In this article, we will take a look at how campaign tagging works and how you can use it in your digital marketing campaigns.


The first step is to set up your campaign tags on your website’s CMS system or CRM. You will need to create a tag for each of the channels you are using, such as Google Adwords, Facebook Ads, LinkedIn Ads, etc. Next up is to create a URL that has the campaign tag appended onto it. For example if you have a URL that looks like https://www.example-website/blog/post/, then you would make the (Author’s note - where is the rest of this sentence?)


Campaign tagging is a technique that helps digital marketers to track the URLs of their marketing campaigns. Campaign tagging is a technique that helps digital marketers to track the URLs of their marketing campaigns. This ensures they know which campaign leads to which URL. Campaign tagging also enables them to measure the performance of each campaign and compare it with other campaigns.


With this technique, marketers can identify where they need to improve and what areas they need to focus on for future campaigns.

Once I gave the Ai more creative freedom, it began to vary the sentence structure. That was good, but the content was still very repetitive, top level, and even cut some sentences off midway. At no point did the Ai actually begin to explain how campaign tagging worked, which would be essential for an article about the topic. Instead, it hovered on the edges, giving various statements about what campaign tagging is, who uses it, and why it’s useful.


I continued to use this Ai assistant to generate just over 800 words of content and plugged it into Clearscope after adding subheads. It got a grade of C-. Granted, it would need to be longer in order to get a full A++ score, but, given the limited keywords used in what it did produce, I think it would take a fair amount of human intervention to get a rankable piece of content.


It’s my opinion that this Ai tool really is just an assistant (as they do advertise). It might be useful to help you get over some writer’s block, but the final product will require a lot of human intervention.


Test subject #2


Next, I tried a free Ai article writer that didn’t hedge its bets as much as the first one. This tool said it was suitable for “all your content writing needs” and all levels of writing skill. Interesting! Of course, it also says it can be used to spark new ideas.


Needless to say, I wasn’t quite clear on whether I was going to get (potentially) a full piece of content or just reworded prompts.


I set up this test similarly to the first using the program’s available fields:


  • Topic: Campaign tagging
  • Prompt: How to do campaign tagging to track URLs for digital marketing
  • Creativity level: Balanced


Honestly, the Ai writing tool’s first output was pretty good. It seemed to understand search intent and guessed correctly that I’d be writing a tutorial given my “how to” prompt:

In this tutorial you'll learn how to tag campaign URLs and other campaign data with your campaign ID or tag code. You'll also learn some basic campaign tracking tips, such as how and when to use campaign tracking code.

This particular tool allows the user to continue generating content from the end of the previous output, and rate it with a thumbs up or a thumbs down. Not necessarily full-on machine learning, but still interesting.



I was curious if that Pandora-style rating system would help to fine tune the results, so I asked it to generate some more content:

To create a campaign, you will create an account and select a URL. This page will tell you how you can use the campaign to send digital ads to people who have joined your list. The campaign will be created for you and you should select and set a date and a number of impressions. Campaigns create the ad and then automatically collect the impressions and generate the unique number.

Okay, still not too bad. Campaign tagging isn’t only for serving ads (and it’s very vague about what “list” it’s talking about—email? Doesn’t make sense). However, it’s not terrible. You could feasibly work with this given just a little tweaking.


I decided to try another paragraph, and see how long this Ai could keep going before running off of the rails.



Answer: it immediately ran off the rails. This is what the program returned for its third paragraph:

For example, if you want to create campaigns that target an audience of 2,000, the default campaign size is 500 impressions for each campaign. Use the Campaign Manager to select campaigns, and click the Create Campaign button. (Refer to Figure 5-18.) Click the Advanced button in the top-right corner of the screen to enable advanced features. Click Create. On...

O-kay. Here we run into some problems. While this program provides generally more readable and linguistically diverse content than the first Ai service I tried, it gets way too specific here. The fact it calls out “figure 5-18” indicates to me that it is directly pulling content from other websites and repurposing it here. That’s a big problem if you’re writing content for your business site or that of a client.


This isn’t to say it’s generating purely plagiarized content — I did run it through a plagiarism checker and whatever rewording the Ai did was enough to pass — but you’d need to be very careful to eliminate any text that doesn’t directly align with the way your webpage and platform are set up.


Given the success of the first two paragraphs, though, this particular Ai tool might have some application for writing short e-commerce product descriptions or social media post captions. I’m still not sold on Ai content writing tools for blogging, long-form marketing copy, or business copywriting, though. You’re still gonna need a human marketing team, or at least a freelance writer who knows their stuff.


What could you really do with this Ai content?

A multicolored keyboard on a clear backdrop

Ultimately, neither of these Ai copywriting tools provided real value in the content produced — which is essential for ranking your content organically through SEO. The results were a mix of extremely top level definitions, reworded in several ways, and semi-technically accurate phrases that referenced visuals and features from other webpages.


What do I think would happen if you used a tool like this? First, you’d be pretty frustrated. This wouldn’t be a set-it-and-forget-it experience, and you’d need to do a lot of heavy human intervention. While I didn’t run these programs for more than a few paragraphs, the continual repetition right off the bat makes me very suspicious of any ability to really generate a full article.


Second, even if you could use the Ai to generate content that contained enough keyword diversity (on a good domain) to rank on the first Google SERP, it appears, based on these tests, that the content is unlikely to contain any meaty takeaways or information. If you’re able to get clicks, but can’t actually provide the answers needed in your content, you’re going to have a pretty high bounce rate. Your rank in the SERP wouldn’t last very long, and you’d find yourself in a continual cycle of quick spikes and dips: not great for SEO.

More productive ways to include Ai in a writing workflow


Instead of relying on Ai tools to generate actual content, it’s best—in my opinion—to use Ai and computer algorithms to make your human-centered content writing workflow a little easier. This could be in the form of automation, research assistance, or scheduling, for example.


I happily use Clearscope, as mentioned above, and CoSchedule’s Headline Analyzer to help me speed up the process of comparing my content, and keywords against other pages. I’m still doing all of the drafting, revising, editing, and creating, but I’m able to get some help with the information collection side of things.


There are a ton of Ai content writing startups hitting the market, and there may still be a golden goose out there that really can produce optimized content that is on par with what human bloggers create. I haven’t found it yet, but I’ll keep poking around . . . gotta have a heads up when the robots come for my work, you know.

Can You Use AI for SEO in 2024?

By Emily Gertenbach • 05 Apr, 2024
I recently sat down with Kevin Willett of New England B2B Networking to talk about how AI has evolved over the past year—and whether or not you can reliably use AI tools for SEO. How is AI changing? Kevin: There's been some changes to AI since we last spoke about it, right? Let's talk about them. Emily: We have seen a lot of changes recently with AI. I know you and I had talked about AI in the past. And at that time, ChatGPT, which is a really big AI tool that lots of people are using, wasn't able to regularly connect to the Internet. And now it can if you pay for their premium subscription. You can use ChatGPT to browse Bing right while you're chatting. So I see a lot of people starting to ask, you know, "now that it can connect to the Internet, can this really replace doing a Google search? Can I use it for business research? Can I use it for SEO?" And there's still a lot of unknowns that a lot of people are experiencing around that topic. Which AI tool should someone use? Kevin: I've been seeing commercials for different AI tools. How do I know which one to use? Is one of them better than the other at maybe writing content? Emily: That's a good question. There are some tools that are specifically designed to write content—but they actually all use the same technology that either ChatGPT or one of its biggest competitors, Claude, uses. Those two programs built the backbone of most of the AI writing tools you see today. So, personally, I don't really think it's worth it to pay the premium for an AI writing tool. If you really want to try and do AI writing, I would just use ChatGPT or Claude—you're going to get similar results. Now that said, it's not good for all kinds of writing. It still tends to fall off a cliff, we'll say, when you try to write something long, and there's a reason for that. It's based around probability and how many different variations something can have—it's math. But you can explore using it for really short form things, like an email or maybe the summary for one of your YouTube videos. Can AI help with keyword research? Kevin: Can it help me determine what keywords I should be focusing on? Emily: Unfortunately, no. Not yet. Now if you try to ask ChatGPT, Google's Gemini, or Claude to give you keywords, a lot of times they will produce an answer that has keywords, and it'll tell you how many searches there are per month. And it looks good on the surface, but what you're actually seeing is called hallucination. The AI tool is just making something up. I have tried this many times by asking different AI tools to help me with keyword research, and give me some information about how popular different terms are. They are always wrong. I go and I check these keywords against paid SEO tools that I use. They're wrong, and not by a little bit. I'm talking by, like, tens, if not hundreds of thousands of searches a month wrong in the estimation they're giving. So while you could try using ChatGPT to write headlines for your SEO blog posts, or, like I said, emails, you still need to do your own keyword research using Google or work with someone who can give you a report of keywords. Kevin: It still seems a little scary, to be honest. If I'm relying on it and it's not correct, I'm thinking, "Hey, wow! You know, I'm learning all these new keywords I should be using"…and then find out that I may be putting my efforts in the wrong area. Emily: Yes. It is definitely scary that it can give you answers that seem confident, so to speak, and seem correct, but they're actually really wrong. And I personally am nervous that a lot of busy business owners are going to put time into using this tool, and then creating content and doing SEO things based on what this tool tells them, and they're actually going to be wasting their really valuable time because it's all wrong.

SEO Trends and Expectations for 2024

By Emily Gertenbach • 08 Jan, 2024
I recently sat down with Kevin Willett of New England B2B Networking to discuss the SEO Trends and Expectations for 2024! Check out the conversation below, then submit a question of your own for me to answer in a future blog or LinkedIn post! Biggest Trend of 2024? Kevin: Today I want to play crystal ball with you. I want to talk about 2024. And what do you see as the trend? So I guess the big the first question, what do you think's gonna be the biggest trend of 2024. Emily: So I think the biggest trend of 2024 is something that we've already seen happening, but we're gonna see on a different scale. And that is, a lot of first person user generated content. So you know, if you get on like, Instagram or Tiktok, of course, you're seeing a lot of ads from brands and content from brands that show people who are apparently their real users using that content. And up to this point, a lot of that has been isolated to those video based social media platforms. But Google has rolled out a new search filter, like where you can click like shopping, or news. It's one of those called perspectives. And when you click on perspectives you get, you're supposed to get real people's first person accounts, and a lot of those come from, say, Reddit, or Instagram, but it is possible going forward for individual websites to show up in there. So I think we're gonna see a lot more companies posting that kind of content on their own owned channels, like on what might be their blog now, or their YouTube page, you're gonna see more first person content rather than slick marketing videos. AI in 2024 Kevin: That'd be nice. So you and I have been joking for the last few months about AI. You know, so what do you think AI is going in 2024? Emily: Well, it's definitely not going away. It's something that people are still interested in. And companies like Google and meta are pouring tons of money into developing it. But in all honesty, it's not quite yet at the point where it's truly going to revolutionize the way we do marketing like in the immediate future. Most of the tools that you and I have access to are still using old data from a few years ago, they're still trying to figure out how to make AI like connect to the internet and pull information in real time. And there's definitely some bumps to be ironed out. So companies like Bing and Google are working on adding AI into search. But it's not a finished product. yet. I think that over the course of the next year, we're gonna need to keep doing what we've been doing in terms of marketing, don't throw out what's been working for you start paying attention to some news about AI and search and AI tools and marketing, and just thinking about how you might leverage them in different ways in the future. And I think by the end of 2024, if we do this crystal ball session, again, I think by the end of 2024, looking forward in the following year, we'll be seeing more of a direct impact in the way we think about marketing in the way we do our marketing. Content: Quantity over Quality? Kevin: Emily, one of the pressures as a business owner is to develop content, you know, to use the Content is king expression was so we hear it all the time, you have to have content gotta keep it out there, that sometimes we don't think about the quality of our content. So might that's my question for you. Is it quantity over quality? Which one should win? Emily: At this point? That's a really good question. At this point, quality should win. So in the past, like even just like 5-10 years ago, quantity was really important. You needed to have a lot in order to be able to like it was evolving. It was a numbers game, it was sheer volume, could you produce more content than your competitors? If yes, then people are gonna see you more. Now that's not the case. Search engines have gotten a lot smarter. The people doing the searching have higher expectations now, because we've all just have years of like crappy content thrown at us. So whether you're creating video, audio written content, stuff for your blog videos for YouTube, you're gonna want to focus on high quality. That's what people want. It's what's going to keep them engaged. And bring it back to AI. My initial testing that I've done around how AI search will work in the future shows that these tools are trained to look for high quality content, they're not looking for fluff. So in the future when people searching Google AI is going to return a result for them and you'll be able to have a conversation with the search engine results page. And those tools are showing all the signs of looking for high quality, not volume.

Common SEO questions (and answers!)—part three

By Emily Gertenbach • 13 Dec, 2023
I recently sat down with Kevin Willett of New England B2B Networking to discuss some of his questions about SEO—and I'm happy to answer yours, too! Check out the conversation below, then submit a question of your own for me to answer in a future blog or LinkedIn post! Does domain type matter? Kevin: One of the things I'm confused by is people's blogs. So sometimes I see, you know, .com/blog, sometimes I see blog dot, and then the domain. Does it matter? Emily: It depends. So it's really good question. And it's not something a lot of people think about. So Good going. If you have a relatively small sites, I would say and smallest relative, I would say, under 1000, total pages, I know 1000 Sounds like a lot. But when you think of a site like Amazon, it is expansive. If your site is is like under 1000 pages, you really want to have it structured. So it's like New England B2B dot com slash blog. And what that does is it includes the blog as part of your main domain. So your homepage, and your blog pages, search engines consider them all to be the same entity. Now, sometimes you'll see some businesses especially really, really, really large companies, like big international enterprises, they'll have, you know, company.com, and then they'll have blog.company.com, those are actually treated as two different websites by search engines. Now, these companies are so big, and they have so many pages on both sites that to them, it doesn't really matter. And it actually helps them. There's certain technologies they can use to manage that high volume of content that work better in that way. But for the average person who's out running a multinational conglomerate, you're going to find it more difficult to get your site to rank for search terms. If you have blog, dot your website instead of your website slash blog. That makes sense. Yes. The first two positions when searching Kevin: So we wouldn't be trying to do that to get the first two positions when someone's searching, is that why we would want to have the blog is kind of a separate entity? Emily: So if you if you're a really big company, and you have the blog and a separate entity, then yes, you could wind up getting the first two positions, because you do technically have two websites, the likelihood of that happening is getting slimmer and slimmer because search engines are getting smarter about figuring out when two sites are owned by the same company. But, you know, that's something that I expect might change some more in the future. But right now, that's what could happen. Backlinks and how they work today Kevin: I got a question about backlinks. Cuz I'm dating myself a little bit. I remember 10 years ago, that was the thing, you know, hey, Emily, put it back link to my website, I'll put a backlink to yours. Whether it was websites like hey, these this list of all my friends and it was 30 or 40 backlinks they're valuable is that is a really as important as we thought it was Emily: 10 years ago, totally right. That was a big thing. I remember having to do that for websites I worked for. And at that time, that was a big thing that was really important. Now, it's less so you know? I get messages on LinkedIn, sometimes from people saying that they're backlink experts, and they can help me get lots of backlinks to my site. Working with those folks can actually hurt your site more than help it in the long run. Because the only kinds of backlinks that are really good for your website today in this year, are ones that come about through more of a public relations exercise. So if you're paying someone to just make sure you get links in a lot of pages, search engines are wise to that they know what's up, they're gonna figure out what they're doing. They're gonna be like, hold on, went from having like 100 backlinks to now 15,000. What what is going on here? Something's not right. So what you want to do is, you know, backlinks are great, but you only want to get them from people you really know like, you give me a site back up on your website, you give me a link back to my web page. And that's great because we know each other, and we're associated with each other. Sometimes I answer questions from journalists and bloggers, and these aren't my answers go into articles posted around the internet. Those are valuable backlinks because I was engaged in that process. If a news site wants to link back to you, great, if a big company loves what you do, and you work with them, and they want to link back to you also great, but you don't have to take time out of your day to try to seek them out. Only focus on the ones that come naturally. What does is mean Google is crawling my site? Kevin: You use an expression that Google is going to crawl my site, and I go okay, okay, no idea what that means. What does it mean? Emily: Okay, well, you know, how we call the Internet, or at least he used to call the Internet, the World Wide Web. So think of a spider web. Google has these little, I say little they're not really real entities, but they are software programs called bots, crawl bots, and they go out onto the internet and they figure out what web pages exist, how they relate to certain topics, how they relate to each other. So we call it crawling. Because back when we called it the World Wide Web, the idea was that these bots were like little spiders that would crawl out on the spider web and collect this information, just like a real spider might collect bugs in its web. That term has persisted today, even though we don't say a world wide web as much. So what happens is, these crawl bots or spiders go out and they start with a link. And then they go to the next link and the next link, and then they jump over here and look at a new topic. And they map how all sorts of information fits together. So search engines know that you and I know each other because I'm linked on your website. And I now share these videos that we do on my website. So it's making those kinds of connections, we now have a string of the web drawn between us. But going back to my previous answer, once again, you don't have to worry about amassing the most possible web the most possible connections, you just want to get really strong ones that's based on people you know, and by talking about topics that you're an expert in.
Share by: