Microsoft Archives - Post Control Marketing

In integrating AI into my courses, I’ve had experience using Custom GPTs. They can be very beneficial over broad AI use as they focus specifically on a single task or project to help the user – whether student, professor, or professional. For example, I have used JobsGPT in a previous blog post as a way to help predict how AI will impact the skills marketers need in the future so that I can adjust my course material.

I was also recently inspired by an article in Chronicle of Higher Ed. In “Teaching: Can AI actually help students write authentically?” Beth McMurtrie shares how Jeanne Beatrix Law, director of composition at Kennesaw State created a custom GPT Writing Guide Assistant. She found a way to engage students with AI to teach critical thinking and the writing process through prompting versus having AI write for students.

I also realize my students need to gain experience working with AI such as custom GPTs and agents to prepare for today’s marketing jobs. The latest CMO survey reports use of generative AI in marketing increased by 116% since 2024 – now 15% of marketing activities. As a hopeful sign, the same survey reports companies are still growing their marketing teams – 5.3% last year and predicted 5.0% in 2025.

The Primary Goal of My GPT

My goal in creating the Social Media Audit GPT was to provide students with a learning assignment to teach step-by-step an important course concept. Social media audits are an amazing strategic tool but students often struggle to understand them completely – even with new examples in the 4th edition of my Social Media Strategy book.

This custom GPT takes students and professionals through the process of completing a social media audit through prompting, and you can ask questions at any time along the way. It also has the benefit of focusing on source materials to ensure accuracy.

To create the Social Media Audit GPT I gave it an article I wrote on this blog last year detailing the process for conducting a social media audit with a social media audit template. I see the custom GPT as a great support to in-person instruction giving each student access to how I would tutor them in this key concept 24/7. For those using my Social Media Strategy text in classes, this is a great supplement to support your instruction.

Social Media Audit Template To Improve Social Media Marketing Strategy. — I trained the GPT on the Social Media Audit template from my Social Media Strategy book.

Secondary Goals of My GPT

A secondary goal was to show students how to use AI responsibly to empower their learning, not harm it. Creating a custom GPT is a key demonstration of AI integration and teaching AI literacy versus AI bans labeling all AI use as cheating. This helps teach responsible AI use for students tempted to use AI to complete assignments.

Another secondary goal is to teach students how to work with AI as a partner in developing marketing strategies. The GPT is not a replacement for those creating a social media strategy for an employer or client. The AI agent doesn’t complete the audit.

I instructed the GPT to not collect data for the user it to prompt them to formulate their own insights. The real value of a social media audit is getting into each social media platform and seeing what’s happening with your own eyes. I built the AI as a strategy development assistant demonstrating how students or professionals can use custom GPTs and AI agents in their future or current marketing careers.

How I Created The Custom GPT

I had a working model of this Social Media Audit GPT several weeks ago as a Microsoft Copilot Agent (AI-powered assistant), but it was stuck inside my institution – you can only share with individuals or groups in your organization/company. Google Gemini Gems (custom AI experts), and Anthropic Claude Projects (curated sets of knowledge) have similar limitations in that your custom AI agent, gem, or project can only be shared internally within your organization.

Only OpenAI’s custom GPTs can be published on the open web and mobile app to be shared publicly. Anyone can use Custom GPTs with a free ChatGPT account, but to create a custom GPT you need at least ChatGPT Pro (at $20 a month). Before this, all my AI use was limited to only models and tools that I could access for free (so my students wouldn’t have to pay).

Yet with custom GPTs, I was in the opposite situation. As Marc Watkins explained recently, while OpenAI and Google are giving away premium subscriptions to students, they have not extended that offer to professors. I finally secured some funding to purchase a ChatGPT Pro account.

One thing I like about my blog is I own it and control what is published there. With this GPT I’m relying on OpenAI to host for me. If I downgrade to a free account, I can’t access it. Thus, I’m locked into paying $20 a month to manage and update. OpenAI, if you’re reading, please extend the free Pro account to educators, not just students.

GPTs Are Essentially Good Prompts

What is a custom GPT? OpenAI says “a version of ChatGPT for a specific purpose.” MIT Sloan explains, “Custom GPTs are helpful AI tools tailored for specific domains or contexts. GPTs differ from standard chats through ChatGPT due to custom instructions and the ability to keep a knowledge base in addition to what ChatGPT has been trained on. This allows users to create a custom GPT to address a specific need that might be hard for ChatGPT to achieve on its own. The process … requires no code, and involves using specific prompts and your own data to provide insights into a particular field.”

AI Prompt Framework Template with 1. Task/Goal 2. AI Persona 3. AI Audience 4. AI Task 5. AI Data 6. Evaluate Results. — AI Prompt Framework Template for writing good prompts – what you need to create a GPT.

Creating a custom GPT is essentially writing a good, detailed prompt that users of the GPT will begin a chat from that background and knowledge. In creating my Social Media Audit GPT I wrote a long prompt explaining what I wanted it to do following my AI Prompt Framework of Task/Goal, Persona, Audience, Task, Data, and Results.

In the image below I marked up my GPT prompt to sections of the AI Prompt Framework. The text on the top was my original building the Copilot Agent and adjustments. The text in the bottom right is the adjustments I made in custom GPT.

Custom GPT and Copilot Agent prompts to create Social Media Audit GPT.

Test Your GPT To Make Changes

An important part of this process is to test your GPT as a typical user to see how well it performs. If you find something wrong simply tell the GPT what you like and what needs to change. You can test it in a Preview column next to where you instruct the GPT.

One of the first adjustments I made was to clarify that I wanted the GPT to have the user visit each social platform and report results. An earlier version searched the web and reported back its analysis. I tested the social audit GPT with a running brand (see below).

I like to run so I chose to test Social Media Audit GPT with Saucony running shoes and apparel

Once you’ve tested the GPT you’re ready to publish! Click the “Create” button in the top right. Then click “Share” at the top right. In that pop-up screen select “Only me,” “Anyone with the link.” or “GPT Store access.” After choosing GPT Store your GPT will be available at https://chatgpt.com/gpts for anyone with a ChatGPT account to access. Search by name or click “My GPTs.”

The custom GPT you make is only limited by your discipline knowledge, the data you provide, and the strength of your prompt.

Have you explored creating a Copilot Agent, Gemini Gem, or Open AI Customer GPT? How might you use this in your teaching for professional practice?

Please try the Social Media Audit GPT and share any feedback you have. A great feature of custom GPTs is you can revise and update.

This Was Human Created Content!

ChatGPT was released to the public six months ago and quickly became the fastest application to reach 100 million users. OpenAI reached this milestone in just two months compared to TikTok’s 9 months and Instagram’s 2 ½ years.

The result of this enormous attention is that the world has quickly become aware of the advanced capabilities of generative AI. As of March 2023, 87% of consumers had heard of AI and 61% somewhat understood what generative AI is and how it works.

ChatGPT generates text from text prompts through a chatbot, but that’s not all generative AI can do. The popularity of ChatGPT also brought attention to OpenAI’s image generation tool. DALL-E 2 generates images from text prompts through a chatbot.

A table listing and describing generative AI integration in major software platforms. — Which generative AI tools will you use for digital and social media marketing?

Despite the mass attention, AI tools have been around for years.

I first wrote about AI in a 2019 post “Artificial Intelligence And Social Media. How AI Can Improve Your Job Not Steal It.” In it, I talked about how AI was being used in algorithms, automation, machine learning, natural language processing, and image recognition.

That post also talked about how AI was used in chatbots to simulate human conversion, in predictive and prescriptive analytics, and in content generation. Examples included Patern89 which has been using AI to analyze content combinations and placement for optimization since 2016. Another example was Clinch which has used AI for content automation and personalized dynamic ad content across channels for years.

Since ChatGPTs release, there’s been a race to integrate generative AI.

The race began with ChatGPT being added to Microsoft’s Bing search engine. Then Google announced plans to integrate its generative AI Bard into Google search. Other platforms quickly announced integrations with OpenAI’s ChatGPT and Google’s Bard such as Salesforce, Hootsuite, HubSpot, and Adobe. Microsoft and Google are even integrating ChaptGPT and Bard into Microsoft 365 and Google Workspace office software for writing, spreadsheets, and slides.

Yet they’re not the only options. Other generative AI tools include Jasper.ai and Copy.ai, for writing, and Midjourney and Stable Diffusion for image generation. Tools like Synthsia generates videos with human avatars and professional voiceovers from text prompts. Other examples of generative AI are summarized below.

AI content generation tool uses:

Content research/Data collection
Brainstorming/Idea generation
Copywriting/Copyediting
Summarizing/Note taking
Image (photo/illustration) generation
Video clip/Podcast clip generation
Transcript generation/Automated post prep
Ad/Post variation generation
Video generation
Podcast/Voice over generation
Presentation generation

Generative AI tools come with new skills and considerations.

A new skill with these next gen tools is prompt writing. Prompts are the natural language used to ask a generative AI tool to produce something. More descriptive specific prompts produce better results like prompts that describe the tone of writing or style of an image. Yet be mindful potential of copyright issues with prompts to create text or an image in the style of a famous person without their permission.

A new consideration is the data set from which you train AI. Generative AI tools like ChatGPT are trained on data from the open internet. This is what makes it so powerful, but this is also what can lead to copyright issues and sometimes create bias or incorrect results.

Other AI tools like Jasper.ai allow you to train on a specific dataset. For example, a brand could upload all its previous materials to establish a brand voice to write new copy. Adobe’s Firefly draws from Adobe’s stock library and tracks creator images used to ensure copyright compliance.

With the explosion of AI comes limitations and cautions.

Despite the mass adoption, this technology is in its early stages. There hasn’t been a lot of testing. Regulations, laws, and professional standards have yet to be developed. HubSpot suggests the following limitations, cautions, and warnings in using generative AI tools.

Cautions when using generative AI:

AI can’t conduct original research or analysis.
AI can get things wrong so you must fact check.
AI doesn’t have lived experience and human insight.
AI doesn’t ensure quality, strategy, and nuance.
AI can contain biases that are not caught by filters.
AI can have plagiarism and copyright issues.

Despite these cautions, alarm over societal harm, and escalating calls for regulation, the AI race is on. Even while companies, government, and scientists raise concerns, companies continue to integrate AI into mainstream products and services. Below is a sample of what’s been released or announced thus far.

Examples of Early AI Content Generation and Automation Tools in Major Platforms.

Platform	Tool	Function
Hootsuite	OwlyWriter AI	Generates social media captions from URLs in different tone or voice, content ideas from prompts, auto recreation of top posts, and calendar events copy.
HubSpot	Content Assistant	Generate copy for blog posts, landing pages, emails and other content from idea to outline and copy generation.
	ChatSpot	Conversational bot that automates CRM tasks including status updates, managing leads, finding prospects, generating reports, forecasts, and follow-up drafts.
Salesforce	Einstein GPT	Auto-generates sales, service, and marketing tasks, content, targeting, messaging, reporting and personalization across channels.
Adobe	Firefly	Generate images, fill, text effects, and recolor from text prompts plus create content, and templates and edit video with simple text prompts – some inside Creative Suite.
Adobe	Sensei GenAI	Automates tasks, optimizes and generates content and content variations across channels in Adobe’s Experience Cloud marketing platform.
Canva	Magic Write	Generates copy, outlines, lists, captions, ideas, and drafts from text prompts.
Canva	AI Image Generator	Generates images from text prompts and various styles and aspect ratios.
Meta	AI Sandbox	Tools that generate multiple versions of text and backgrounds, plus autocropping creative assets for various ad formats on Facebook and Instagram.
Grammarly	GrammarlyGo	Generates writing and revisions relevant to tone, clarity, length, and task via text prompts in documents, emails, messages, and social media.
Microsoft	Microsoft 365 Copilot	Generates tasks, content, documents, presentations, spreadsheets, emails, reports, summaries, updates across Word, Excel, PowerPoint, Outlook and Teams via text prompts and Business Chat.
Google	Google Workspace Bard	Generate drafts, replies, summaries in Gmail, drafts, summaries, proofs in Docs, images, audio and video in Slides, auto analysis in Sheets, and notes in Meet.

Do Consumers (Your Customers/Target Audience) Want AI?

Another consideration with artificial intelligence is the value consumers may put on human generated content and transparency in the use of AI. I began this article by saying that 87% of consumers are now aware of AI. In fact, 4 in 5 of them are convinced that it is the future.

Yet knowing something is the future and wanting that future are different things. The same consumer survey reveals that 3 in 5 (60%) are concerned or undecided about that future. What people are most concerned about is that AI will change what it means to be human.

As marketing communications professionals we need to stay up to date with all these technology advancements. We should use the latest tools to improve our profession and results for our business or clients. But we should also ensure that new technology is used responsibly and transparently.

Over 77% of consumers say brands should ensure biases and systems of inequality are not propagated by AI-based applications. Over 70% believe brands should disclose when they use AI to develop products, services, experiences, and content.

You Decide How To Best Use AI.

At its best, AI can help with the mundane, repetitive tasks of social media and digital marketing management. At its best, AI will enable you to focus on higher level strategic thinking. At its best, AI will not replace humans, but enable us to be more human.

It’s been 6 months since generative AI was brought to mainstream awareness. Companies are rushing to integrate this technology into everything they do. While we wait for regulations, laws, and professional standards to catch up, let’s use our own judgment in deciding when, where, and how best to use it.

For my latest insights into AI, I began a blog series in Summer 2024 with

Artificial Intelligence Use: A Framework For Determining What Tasks to Outsource To AI [Template]

This Was Human Created Content!