SEJ LeveragingGenerativeAI F
SEJ LeveragingGenerativeAI F
Generative AI
All rights reserved. No portion of this book may be reproduced in any form without
permission from the publisher, except as permitted by U.S. copyright law.
For permissions, contact [email protected].
CONTENTS
CONTRIBUTING
Introduction 6 WRITERS
KRISTI HINES
Part I: How Generative AI Works & 9
Former Associate News Editor,
How Best To Use It
Search Engine Journal
Defining Narrow AI & Generative AI 10
LUDWIG MAKHYAN
Limitations & Dangers Of Generative AI 12 Head of Technical SEO,
EssilorLuxottica
Revolutionizing SEO With Google’s 15
Search Generative Experience VINCENT TERRASI
Co-Founder, Draft & Goal
How An AI Tool Can Quickly Facilitate 28
High-Quality, SEO-Friendly Content
Creation EDITORIAL
KATIE MORTON
Part II: Scalable AI Tools For SEO 31 Editor-in-Chief
Introduction
2023 was a breakout year for artificial intelligence (AI),
and 2024 does not show any sign of slowing down. Kristi Hines
Former Associate News
Editor, Search Engine Journal
Generative AI features became a part of the user interfaces of top search engines,
social media networks, advertising platforms, productivity software, and SEO tools.
While AI has been a part of most platforms for years, generative AI tools – those that
use deep learning AI models to generate new outputs based on user inputs
(prompts) – exploded.
In 2023:
With non-stop breaking news about new AI research, large language models (LLMs),
AI startups, GPT wrappers, and AI agents, it may take time to determine which
solution best suits your objectives.
There may soon be an AI-powered tool that simplifies all the challenges you face in
your workday. As an exercise, make a list of your common workflow challenges. That
might help connect your thought process as you explore AI tools.
Bing offers AI-powered deep search, chat, summaries, and image creation
capabilities via Copilot with GPT-4.
In addition, the top advertising, business, marketing, productivity, and SEO platforms
are integrating generative AI chat and tools.
Aside from using AI-powered tools for SEO, marketers may consider creating custom
AI tools that can be promoted to attract links, increase brand visibility, and
generate leads/sales.
Observing how AI chatbots conduct web searches can also provide insight into how
search with AI works and how to optimize content for both.
The core defining feature of an AI algorithm is that it can “learn” to act upon inputs for
autonomous decision-making or problem-solving. IBM defines AI this way:
Shallow machine learning models require user input to structure and categorize data.
Deep learning models don’t – they can independently categorize and understand the
relationships between inputs.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 11
Generally, the scope of these algorithms is narrow. They can learn to perform specific
tasks based on sets of training inputs. Within this narrow scope, AI models can
significantly outperform humans. AI has been able to handily defeat human chess
masters for years.
In search, Google uses AI ranking systems to match words and concepts together to
deliver relevant results, as well as detect spam and predict the quality of webpages.
The core difference that sets generative AI apart is the ability to create new data.
This greatly increases the variety of applications you can use the models for.
While an “AI” algorithm could look at images and categorize them, a “generative AI”
algorithm could tell you about an image, take actions based on the attributes of an
image, or create new images.
Without getting too into the weeds, transformers are a unique way of encoding
language data and analyzing the relationships between the tokens created. While
LLMs require a large amount of data and human effort to train and maintain, the
power of the autonomous analysis and output speaks for itself.
LLM chatbots can translate between languages and return human-like responses to
prompts as if they understand what’s being typed into them.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 12
This unique capacity to generate new data is the defining feature of generative
AI, allowing it to perform an impressive array of new tasks. It’s also the source of
significant risk and ethical debate.
That’s why, throughout this book, we will not use the terms “AI” and “generative AI”
interchangeably. For the purposes of clarity, we will differentiate between “narrow AI”
and “generative AI,” but both of these terms fall under the umbrella of “AI.”
So when you see “narrow AI,” we’re discussing AI algorithms that could be based on
machine learning or deep learning neural networks and perform narrow functions.
And when you see “generative AI,” we’re discussing a specific type of deep learning
neural network that produces outputs based on statistical probabilities.
This distinction is critical because, for example, text transcription can be done by either
type of AI, but generative AI transcription will have distinct capabilities and features.
While the market is changing rapidly, at the time of publication, SEJ’s official
recommendation is that you:
This is a particularly conservative stance, especially in the SEO and marketing realm.
But, I hope to convince you that:
Exceptions:
We see exceptions in use cases where a generative AI tool creates outputs using
inputs of your original work or has a limited role. For example:
One great example is advertising platforms where generative AI is baked directly into
the features. It might be impossible (or unwise) to completely avoid using it. This is
less problematic if the algorithms base their outputs on a limited data set like your
website. Just be sure that humans assess all outputs.
The five core issues associated with using these models for content are as follows:
2 There are unresolved legal and copyright questions about how these models
work. We will not attempt to interpret ongoing litigation and legal decision-
making. We know there are several in-progress lawsuits over image and
language-based generative AI models, and the direction and impact of those
decisions are unclear.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 14
This presents many unknown risks when publishing the outputs of generative
AI, despite what the tools may claim to offer for protection. As former associate
news editor Kristi Hines points out, “The outcomes may affect how AI tools
work, how much they cost, and what it takes to develop them safely. It may
also make you revisit any AI-generated content you’ve previously published to
ensure it is safe to use, personally and professionally.”
ChatGPT Creator Faces Multiple Lawsuits
ChatGPT Faces Legal Woes Worldwide
New York Times Vs. OpenAI
A timeline of generative AI lawsuits
3 There are unresolved privacy and safety issues with many large language
models that limit the kinds of information you should input into them. This
includes any protected or personal information, information covered under
non-disclosure agreements (NDAs) and embargos, and anything else that
could be sensitive.
4 Anyone can now create content at scale to a base level of quality. Generative
AI is not a significant advantage in either strategy or content quality because
anyone can apply the same automation with similar results. Publishing the
same statistically probable content as everyone else is not a great way to
stand out.
5 Despite soaring user bases and profits, generative AI tools can be unpopular and
polarizing with certain audiences. Hines points out: “You should also ask yourself
whether AI-generated content meets the standards of users when it comes to
quality, accuracy, and helpfulness. How will your primary audience, customers,
partners, and readers respond if they discover your articles, item descriptions,
product photos, or demo videos are AI-generated? Some brands have received
unwanted scrutiny over the perceived misuse of AI-generated content.”
At SEJ, we developed – and are continually updating – a policy about how generative
AI should be used internally and how we communicate information about it to you, the
readers. This is an example of that policy in action.
All this being said, there are plenty of SEO use cases for generative AI. As you read
this ebook, I hope you’ll discover that creating content for publishing is a narrow view
of how limited AI and generative AI can improve SEO workflows and outcomes.
Revolutionizing SEO
With Google’s Search
Generative Experience
The advent of Google’s Search Generative Experience
(SGE) is revolutionizing online search, ushering Vincent Terrasi
Co-Founder, Draft & Goal
in a new era of contextualization and intuition in
information discovery.
It also discusses the knowledge of large language models (LLMs) such as OpenAI’s
GPT, Google’s Bard, and Microsoft’s Bing AI, highlighting their limitations and potential
in SEO content creation.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 16
This development has a significant impact on how SEO professionals need to think and
plan their content strategies.
The user experience is also changing, as AI-guided search results are easier to find.
Answers are quickly accessible without having to sift through multiple tabs and pages.
Understanding how generative AI works and extracting its knowledge using new
methods is essential to position yourself effectively and understand its limitations.
SEO project staff need to understand these limitations in order to maximize their
content creation efficiency.
There are two types of knowledge: that which comes from the data used for training
and that which is in the search engine index and is used as part of the answers.
To illustrate this, I’d like to show you how we can map this knowledge.
It ensures that all facets of a topic are covered, increasing the relevance and quality
of the content. Using an LLM for thematic mapping offers unique advantages in
generating new ideas and perspectives.
This approach not only helps to organize ideas in a logical way but also to identify gaps
in existing content.
Choose a niche topic and identify the relevant keywords. You can start with the LLM of
your choice, but I prefer one approach.
The first is to use Google’s generative AI, such as PaLM 2, if you have a good
command of Google’s tools (for your information, I have set up a training course
on Data Marketing Labs).
Brainstorming
For each expression, you’ll ask the LLM to brainstorm by creating several passages
related to the expression.
I’m often asked why I make several passages. The answer is simply because, depending
on the creativity threshold and the answers in Google’s index, the LLM may have
slightly different answers. This allows the field of possibilities to be included.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 20
Here’s a picture where I’m using PaLM 2 to generate topics that the AI knows perfectly
well and that are searched for by web users. The more topics you ask for, the better the
coverage of your topic.
Extraction
Next, you can extract all the entities mentioned in relation to a concept.
Initially, I used Python libraries, but now you can use an LLM because the task is very
simple for it.
In the end, everything is stored in an array, and you can count the number of times a
concept appears. I’d like to explain this part in more detail.
In this image, you can see that for each of the previous topics, I’m doing five
generations to try to recover as many relevant elements as possible, which will help me
generate the mind map.
For each generated text, I use PaLM 2 to extract the important terms, and everything is
stored in a table.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 21
As you can see, each step takes place in a Google Colab, which provides ready-to-use
tables and makes it easy to sort your data with a few clicks.
Next, you can build the thematic map from this prompt.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 22
**Topic:** Bike
**Subcategories:**
Visualization
You can visualize the whole thing using mind-mapping tools, and the results
are very instructive.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 25
I invite you to search for it, and then you can request the generation of your mind map
from the table from the previous steps.
Now, I’d like to suggest some advanced actions to anticipate Google SGE.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 27
Integrate the map into your content research and writing process.
Turn each sub-theme into a webpage, blog post, or other form of content and
link them together to create an interconnected web of content.
It’s enriched with detailed examples and explanations and focuses not just on
topic optimization, but on prioritizing content quality and targeting specific
search intentions.
The combination of a skilled writer and AI can enhance content optimization, using
tools to maximize the efficiency and relevance of your ecosystem.
With the advent of generative AI, any SEO professional can build their own tool.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 29
Whether you’re creating new content from scratch, optimizing a draft pre-publish, or
improving existing content, Writing Assistant helps you write better content in less
time by providing real-time guidance as you’re writing.
Generates detailed content outlines: Writing Assistant solves one of the hardest
parts of creating content – getting started – by automatically generating a
content outline relevant to your target topic.
Assesses how well content adheres to search topic intent (and how to
improve): Ranking is important, but what’s more important is making sure you
match the intent of what people are searching for.
That’s where the Questions to Answer functionality comes in. It analyzes how well
your content addresses the top People Also Ask (PAA) questions from Google and
gives guidance on how to improve if needed.
Some are free, while others have free and paid options.
ChatGPT, Claude, Gemini (formerly Bard), Perplexity, and Poe offer free plans and
premium subscriptions starting at $20 monthly.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 33
ChatGPT gives subscribers access to GPT-4, DALL·E, file uploads, beta features,
web browsing with Bing, over 1,000 third-party plugins, the ability to create
custom chatbots (GPTs), and a store full of custom GPTs.
Claude by Anthropic offers a larger context window than most, making it better
for tasks involving large chunks of text or uploaded documents. Subscribers get
access to the latest model and beta features.
Google Gemini Advanced utilizes Ultra 1.0 to connect to Google Docs, Google
Drive, Gmail, YouTube, Flights, Hotels, and Maps.
Microsoft Copilot (GPT-4) uses the web and plugins from Instacart, Kayak, Klarna,
and Shop.
Perplexity provides answers to questions with deep search and sources. Open-
source models from Meta and Mistral AI are available in Labs. Subscribers can
switch between GPT-4, Claude, Gemini Pro, and online LLMs.
Poe hosts dozens of official chatbots powered by the latest models from
Anthropic, Google, Meta, Mistral AI, OpenAI, and Stability AI. It also allows you
to create custom chatbots on many of those platforms. Subscribers get more
access to the latest models.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 35
Meta launched a Meta AI chatbot to generate images and search the web with
Bing on Messenger, Instagram, and WhatsApp.
Snapchat’s My AI was one of the first AI chatbots that users could direct
messages and integrate into group chats.
X, formerly known as Twitter, launched Grok for Premium+ subscribers, which has
access to X posts/tweets as “sources” for responses.
Bytedance was also working on an AI model, but the parent company of TikTok
allegedly did it in a way that violated OpenAI and Microsoft TOS. This hasn’t appeared
to delay the platform’s AI plans, but it may affect the future availability of the
CapCut plugin for ChatGPT.
While not a social media platform, you can chat with Pi via Inflection on Messenger,
Instagram, and WhatsApp.
Some platforms allow you to add essential context about yourself, your work, and what
you are trying to accomplish so that AI provides the best response for your needs.
In addition to having an AI tool with direct access to your company’s data, you have the
confidence that comes with a platform you already use. These types of tools may also
be more likely to be privacy-conscious and protect information (but always read
the terms!).
LEVERAGING GENERATIVE AI TOOLS FOR SEO 38
The following are examples of platforms with scalable AI features for advertisers,
marketers, agencies, teams, and enterprises.
Accounting: Intuit
Advertising: Amazon Ads, Google Ads, LinkedIn Ads, Meta Ads, Microsoft Ads,
Bing Ads, Yahoo Ads
Analytics: Mixpanel, SimilarWeb
Business Intelligence: Amazon Quicksight, SAP
Coding: AWS, GitHub, StackOverflow
Communication: Slack
Customer Relationship Management & Marketing: HubSpot, Salesforce
Customer Service: Amazon Connect, CallRail, Intercom, LivePerson, ServiceNow,
Vertex Contact Center, Zendesk
Ecommerce: Amazon, Shopify
Email Marketing: ActiveCampaign, Constant Contact, Mailchimp, Omnisend
File Management: Dropbox
Graphic Design: Adobe, Canva
Hiring: LinkedIn
LEVERAGING GENERATIVE AI TOOLS FOR SEO 39
It’s now possible to connect different platforms and functions together, use chatbots to
create your own tools, or even customize generative AI tools for your purposes. These
are a few of the ways you can develop your own solutions.
ChatGPT allows subscribers to build GPTs – chatbots that use GPT-4 with web
browsing, DALL·E, and code analysis with custom instructions, knowledge files, and
actions to complete specific tasks.
Microsoft Copilot Studio allows 365 users to create custom Copilot experiences using
your company’s data.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 41
Poe users create custom chatbots using eight of the most popular AI models. You can
give each chatbot specific instructions for each conversation and knowledge files
to reference.
Screenshot from search for [chat gpt app], Google, January 2024
Making a free tool or inexpensive solution for you or your clients that can be promoted
on a webpage could lead to links, brand visibility, and a new tool for lead generation
and sales.
It’s beneficial since OpenAI allows GPT builders to place a website link on the
GPT page.
You could also create a new product/income stream for your business or your clients.
Be aware of the disclaimers for using AI, as mentioned at the beginning of this section.
It’s also essential to research the risks of developing custom generative AI features
for others.
Learn how to build custom chatbots and GPTs with these free courses and guides:
ChatGPT Prompt Engineering for Developers (DeepLearning.AI)
Quickstart Guide to Building Generative AI Copilots (Microsoft)
How to Create a Custom Bot (Poe)
Automated AI Agents
Do you want to automate tasks with AI?
With Zapier (and plans starting at $20 a month), you can connect your ChatGPT
account, Claude (via API), or Cohere (via API) to thousands of popular business
applications to create automated workflows.
For example, I can create a workflow that connects Gmail, ChatGPT, and Slack and
works when a new email matching a search is received.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 45
If you’re willing to do a small amount of coding, Zapier also offers actions that connect
GPTs to Zapier’s platform of app integrations.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 46
This would allow you to create a GPT that discusses your plans for the day, sends your
schedule to Google Calendar, or adds to-do list items as new tasks in Asana.
Learn how to build AI products with the following courses and learning paths:
Generative AI Learning Plan for Developers (Amazon)
Machine Learning Engineer Learning Path (Google)
Develop Generative AI solutions with Azure OpenAI Service (Microsoft)
Microsoft Azure AI Fundamentals (Microsoft)
Prompting To Understand
AI Discovery
There are three reasons you should explore the art of prompting.
1. Detailed prompts can get you closer to the response you want from
generative AI tools.
If you hired a web developer, you wouldn’t tell them to make you a website. You would
tell them about your business, products, customer demographics, and the functionality
you want (blog, ecommerce store, chatbot, knowledge base, etc.) so they could build a
unique website for your company.
2. Understanding prompts can help you optimize your content for the future
of AI in search.
The following is an example of a prompt offered to users of Perplexity in its FAQ to help
find specific information.
In it, Perplexity suggests that the user be specific about the information they need.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 50
When the user enters the suggested prompt into Perplexity, they may be asked a
question to narrow down the results, such as the size of the vehicle or price range.
Then, Perplexity offers a summary of the sources with information about safety features
and fuel efficiency for 2023 SUVs.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 51
Publishers could use the results of AI-powered answer engines like Perplexity to
reverse engineer why AI chose each source for the query.
As tech companies teach users to create prompts that combine context with a specific
goal, brands must get to know the prompts used in AI answer engines, like the top
keywords used in search engines.
In the above example of a prompt specifying a computer monitor that is best for
working with spreadsheets, several results are from popular retailers.
Ecommerce store owners could use these examples to better optimize product
and category pages for a chance to get in front of a customer with a specific
purchasing intent.
3. Knowing the sources used for AI-generated answers will allow brands to
determine the top publications products must be featured on to reach AI chat users.
Using the right prompts, brands can pinpoint the publications featured most often as
sources by AI chatbots for their target customers.
It may also give brands an idea of how they would want to be featured in AI answers for
ad campaigns.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 54
Soon, search engines may not be the primary way people discover content, research
purchases, and find places to shop.
They may ask ChatGPT, Copilot, Gemini, Meta AI, or another AI chatbot. That’s what
Google’s CEO reportedly anticipates.
Notably, many of the top tech platforms offer guides to prompting for users and
developers alike.
What Is Prompt Engineering? (Amazon)
Prompt Engineering For Generative AI (Google)
Prompt Engineering With Llama 2 (Meta)
Learn About Copilot Prompts (Microsoft)
LEVERAGING GENERATIVE AI TOOLS FOR SEO 56
See also: List Of 16 GPT SEO AI Tools Publicly Available Right Now
LEVERAGING GENERATIVE AI TOOLS FOR SEO 58
Imagine that every call your business receives is the key to unlocking insights that
can supercharge your marketing strategy, elevate sales performance, and
propel revenue growth.
AI can save your team countless hours and provide them with laser-focused insights.
Traditional marketing attribution often grapples with accurately identifying the source
of conversions.
You can use AI to analyze customer calls and extract invaluable insights from
these interactions.
From identifying key phrases that resonate with the audience to uncovering trends that
shape consumer behavior, AI is like having a direct line to the pulse of your audience,
enabling you to optimize keyword bidding strategies and discern the sources driving
valuable leads.
Integrating ChatGPT
With Google Sheets
For Enhanced Data Ludwig
Makhyan
Analysis Head of Technical SEO,
EssilorLuxottica
ChatGPT remains one of the most talked about tools in the world of SEO.
Some users are finding ways to leverage the platform for content and SEO; others use
it to create ads, optimize meta titles, create structured data, and be more productive
overall.
And being more productive by integrating ChatGPT and Google Sheets together
makes a lot of sense to me.
While we’ll explore multiple ways to tie these two solutions together, the easiest
method at the time of writing this post is to:
You can also go directly to the website GPT for Work to install the add-on on Sheets –
and you can use this same method to work with ChatGPT in Excel.
Add-ons make it simple to use ChatGPT with Sheets, but if the add-on becomes
unsupported or stops working, you can use the methods below.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 63
You can use Apps Script inside of Sheets to get this setup. First, you’ll want to:
Sign up for the Open API.
Make note of your API key (Personal > View API keys from the top menu).
Open Google Sheets.
Go to Extensions > Apps Script.
ChatGPT has the code available for easy copying, which is outlined below:
Code to copy:
const options = {
method: “POST”,
headers: {
“Content-Type”: “application/json”,
“Authorization”: “Bearer “ + SECRET_KEY
},
payload: JSON.stringify(payload)
};
try {
const response = UrlFetchApp.fetch(OPENAI_URL, options);
const responseData = JSON.parse(response.getContentText());
} catch (error) {
console.error(“Error calling OpenAI API:”, error);
return “Sorry, there was an error processing your request.”;
}
}
You’ll need to work your way through the code and change certain parameters.
Primarily, you’ll replace “YOUR_OPENAI_API_KEY” with the API you jotted
down previously.
A quick test run of the =callChatGPT(“How can you help me?”) function will let you
know if it’s working. The function should print out a list of items ChatGPT can help
you with:
Inside your Sheets cells, you can call the Script using the following “callChatGPT(CELL-
AND-ACTION-HERE),” and it will provide a response. Google might ask you to accept
certain permissions, so be sure that you do if you want the script to work.
You may also utilize the function based on other cells, for example:
Put these keywords in cell A1: seo, chatgpt, google sheets.
In B1 cell input this function: =callChatGPT(“Provide a meta title for an article
based on these keywords:” & A1).
Tweak this formula based on your data, keywords, and other details.
Integrating ChatGPT reduces the need to switch between both products and will boost
your productivity in the process.
Create an ideas section for titles to help you come up with titles that are more
clickable or user-friendly.
Make fast work of mundane tests, such as coming up with meta descriptions or
product descriptions.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 67
Tables help you visualize data and are great when reporting to clients, but they’re
tedious to fill in. You can also use ChatGPT to generate tables for your data to better
view and understand your data.
Title lengths.
Meta tag lengths.
Bounce rate changes.
When it comes to making sense of your data and analyzing it, you can have ChatGPT
run the calculations for you and then create charts or tables around it.
Visualizing your data will make it easier to analyze and use it.
I’m sure you’ll find many great uses for ChatGPT and Sheets, but the following are some
that I’ve found to be personally useful.
1. Generate Tags
Together, ChatGPT and Sheets make it easy to generate tags for products and build up
your product tag library.
Just create a task for GPT, and it will generate tags for each product you select, saving
you so much time in the process.
2. Clean Lists
Sheets and GPT can work together to help you clean up your lists.
Let’s say that you have a list of names. Because users input their names, some may be
in all capital letters, and others may have emojis or inconsistencies in capitalization.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 68
GPT can use the GPT_FILL function to clean up your name list and standardize it for
easy use and organization.
3. Create Descriptions
Using the script, you can generate short product descriptions based on examples on
your spreadsheet.
ChatGPT will analyze your example and generate descriptions that match the tone and
style of your brand.
With similar functions, you can use Sheet and ChatGPT to generate:
Ad copy.
Taglines.
Titles.
More.
ChatGPT can create ad copy that’s on-brand, captivating subject lines for emails, and
other copy that will engage customers. With these tools, you can save your marketing
team time and generate compelling content that converts.
5. Create Outlines
Creating outlines for blog posts can be time-consuming. Integrating ChatGPT into
Sheets will save you time by generating outlines for your posts in seconds.
GPT can provide a structure for your posts and create outlines that will keep
audiences engaged.
6. Keyword Research
With Google Sheets and ChatGPT, you can save time with keyword research. Just feed
GPT a primary keyword and ask it to generate suggestions. The chatbot will generate a
list of potential target keywords.
You can use these keywords as “seeds” for your research or, at the very least, review
them to ensure they’re worth targeting.
Inside of Sheets, you can use GPT to make schema markup suggestions based on the
content and type.
For example, if your contact displays your address and phone number, ChatGPT can
provide schema markup suggestions to help search engines better understand the
information on your page.
You can also ask ChatGPT to provide you with internal linking ideas. Just provide a page
topic to get more related topics for internal linking.
Want to streamline your competitor and content gap analyses? ChatGPT can help.
Just input some data about your competitors and ask GPT to provide you with
some insights.
You can even ask the chatbot to provide suggestions for missing topics or areas to
expand in your content.
Just provide ChatGPT with some background on your content landscape, and it can
provide suggestions right in Sheets.
Integrating ChatGPT into Sheets can help enhance data analysis, save time, and
streamline processes.
Once you have an API key, integration is simple, and you’ll have access to a number of
functions that you can use to analyze information, create charts, generate ideas,
and more.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 70
However, for simplicity, it’s easier to use add-ons that take care of the integration
without scripts.
Once you connect ChatGPT and Sheets, you’ll be able to crunch numbers and ask the
chatbot to begin helping you handle tedious tasks.
Even generating metadata or creating titles can be immensely helpful. You can even
have ChatGPT help you create redirects or add rules to robots.txt.
Example Formulas
Here are some example formulas you may want to use:
Input the main keyword in the A1 cell and some secondary keywords in
the B1 cell.
Voilà – now you have an outline, meta title, meta description, and FAQ schema that
goes with your keywords.
OpenAI’s GPT-4 with Vision (or GPT-4V) expands the capabilities of the already
impressive ChatGPT platform.
This feature integrates image analysis, allowing the AI model to process and
understand visual inputs. It opens up a number of fascinating and helpful use cases
for SEO pros and marketers, including generating descriptions of images quickly, as
well as interpreting and pulling data out of graphs.
While GPT-4V’s potential is undeniable, its release comes with risks that businesses
should consider carefully.
The visual capabilities of GPT-4V are available to ChatGPT Plus, Teams, and
Enterprise subscribers. Here are some fun examples of people using it:
LEVERAGING GENERATIVE AI TOOLS FOR SEO 72
GPT-4 with Vision could write product descriptions for your sales pages and
Amazon listings.
It could help you get started with basic coding for a particular website design based on
a screenshot.
It could write an article based on data from a website or ebook, such as the
State Of SEO 2024.
It can be an especially useful feature for marketers who need to analyze charts or
analytics data quickly in a short amount of time.
Save time by getting GPT-4V to create descriptive alt text for your images based
on their content. This is essential for web accessibility and image SEO.
GPT-4V could analyze pages and images, potentially suggesting which structured
data schemas may be applicable. This aids search engines in understanding and
effectively indexing your site.
As with all AI-generated content, it’s essential to review output from GPT-4 with Vision
for accuracy. It still hallucinates and poses other risks. Also, only use image inputs that
you have the right to use.
Potential biases during image analysis and interpretation could negatively impact
different demographic groups.
Risks posed by the model have resulted in limitations, such as its refusal to offer
analysis of images with people.
Overall, brands interested in leveraging GPT-4V for marketing must assess and mitigate
these and other generative AI usage risks to use the technology responsibly and avoid
negative impacts on consumers and brand reputation.
OpenAI announced that the GPT-4 with Vision model will power Be My Eyes Virtual
Volunteer, a digital visual assistant designed for the visually impaired.
Be My Eyes plans to beta-test the feature with corporate clients, emphasizing its
commercial potential beyond its primary audience.
The potential applications of GPT-4 With Vision for businesses, marketers, and SEO
professionals could be groundbreaking.
However, all users should remain cautious due to the potential privacy, fairness, and
cybersecurity issues posed by GPT-4 with Vision and other AI models.
LEVERAGING GENERATIVE AI TOOLS FOR SEO 84
And if you want to learn more about getting discovered in AI search platforms, you
should read these articles: