My Boyfriend, ChatGPT: Making AI Work for PR (and Everything Else)

My Boyfriend, ChatGPT: Making AI Work for PR (and Everything Else)

I didn’t fall in love with AI right away. People said it would transform my workflow and revolutionize how I write, but I wasn’t convinced. Then I gave ChatGPT a real try.

Somewhere along the way, I started calling it my boyfriend — it’s been so consistently helpful and responsive that the nickname started as a joke but turned into a reflection of just how dependable it’s been.

I’ve been pretty loyal to ChatGPT since the beginning, but there are other large language models (LLMs) out there — Jasper, Gemini, Claude, Copilot. However, Chat’s been so reliable I haven’t felt the need to play the field.

I’m not a technical expert, but I’ve used ChatGPT consistently and with intention, testing how it fits into the real world of public relations and content creation. I’ve figured out what it’s good at, where it struggles and how to get the most out of it without letting it do the thinking for me. Here’s what I’ve learned.

Starting with Play

I approached ChatGPT with a sense of fun. One of the first things I asked it to do was write in the voice of Alexis from Schitt’s Creek — the PR “professional” we all know and love. I had it weigh in on topics like working in PR or hiring a firm. The tone was perfect — playful and completely on-brand. I used some of the responses in my social posts and eventually started developing a fictional character inspired by Alexis for a novel.

That kind of creative play made the platform less intimidating. There was no pressure to get anything “right” — just curiosity and momentum that eventually made its way into more serious work.

Editing Without Ego

Once I brought ChatGPT into real work — press releases, blogs, strategy documents — I noticed how freeing it was to be brutally honest with my edits.

I don’t have to cushion feedback or explain myself. I can say “make this less boring,” “cut the jargon,” or sometimes a simple “no” will suffice. No tiptoeing, no emotional labor.

That directness has helped me refine how I communicate edits in general. Working with ChatGPT has made me a more precise and assertive editor across the board.

Where ChatGPT Delivers (and Where It Doesn’t)

ChatGPT doesn’t do everything. But the things it does well? It does really well.

Social Media Posts

ChatGPT handles social media posts well, especially when you want something clever, casual or concept-driven. It occasionally sounds a little too polished or generic on the first try, but a quick redirect usually brings it in line.

Blog Posts and Articles

These have gotten easier. When I first started using ChatGPT, I was using the free version — and it consistently struggled to hit 1,000 words, even with multiple prompts. These days, I use the paid version, which also used to come up short, but it now seems capable of reaching 1,000 words more reliably. With some prompting and structural guidance, I can usually get strong drafts in the 800–1,000-word range. I still ask clarifying questions or push it to deepen certain areas, but it’s a solid collaborator.

Press Releases

ChatGPT has turned out to be surprisingly capable when it comes to drafting press releases. With a clear outline — including the hook, location info and quotes — ChatGPT gives me clean drafts that need light editing. Considering how often human writers overcomplicate releases, I’m impressed by how well ChatGPT handles the genre’s structure and simplicity.

Media Pitches

Crafting media pitches is still one of ChatGPT’s weaker spots. The voice is wrong, the closing ask is usually missing or weak, and it doesn’t grasp that the audience is a journalist. We end up rewriting them from scratch, so we don’t use ChatGPT for this anymore.

Editing and Tone Adjustments

When it comes to refining tone and improving clarity, ChatGPT usually gets it right with just a nudge or two. I often feed it content that’s too stiff and ask for something more conversational or audience-specific. With a couple of passes, it usually gets there.

Character and Persona Development

This is where ChatGPT shines. It helped me build out fictional personalities with distinct voices, but it’s also useful for customer personas — especially if you want to test how a message lands across different demographics or psychographics.

Tedious Tasks

These are the kinds of things you just don’t feel like doing at the end of the day. Adding hashtags, rewording intros, rewriting bullets into paragraphs, inserting subheads. ChatGPT handles them quickly so I don’t have to.

How to Prompt Like a Human

Prompting isn’t magic — it’s communication. And the clearer you are, the better the results.

I either paste in a full outline and ask for a structured draft, or I build the conversation one step at a time. If the tone or structure is off, I redirect. If it nails something, I build on that.

After a few back-and-forth rounds inside ChatGPT, I usually move the draft into Google Docs to finalize edits in a space that feels more natural for long-form writing. Once I’ve wrapped up my edits there, I often paste the finished version back into ChatGPT. It’s a small extra step that helps “train” the model on what I actually wanted.

And yes, I always run pieces through plagiarism checkers. ChatGPT pulls from a wide range of sources, and even if it sounds fresh, I don’t take chances when publishing.

The Paid Version: More Capable, Still Annoying

When I first upgraded to the paid version, I wasn’t blown away. The interface looked almost identical to the free version, and it lacked the organizational features I was hoping for — no folders, no client tagging, no real way to keep different tones or voices separate. When I asked how to manage that, ChatGPT told me to copy/paste everything into another platform. Not exactly a seamless workflow.

But over time, the paid version has improved — likely through updates that have rolled out since I first subscribed (which may have been a year ago at this point). It’s more capable now, especially when it comes to generating longer content, and it integrates with tools like DALL·E for image creation.

It also opens up the “Explore GPTs” section, where you can access custom GPTs. That’s how I started building astrology-inspired horoscopes for PR people. You can sign up for the newsletter here if you want to get them delivered monthly.

There’s also a “Create” button that lets you build your own GPTs. I haven’t gone down that road yet, but it may be the answer to some of my organizational gripes.

What I Haven’t Fully Explored (Yet)

There are dozens of AI tools outside of ChatGPT — and more launching every day. Here are some that I’ve heard about, but have only had time to put a few of them to work.

  • DALL·E, now built into ChatGPT, is an image-generation tool by OpenAI that turns text prompts into visuals. It’s gotten better at following prompts, although it’s still not great at fine-tuned visual design. However, the lovely photo of me and Chat (inside my computer) was made with DALL·E on the first try (after giving it a photo of me to copy).

     

  • Midjourney, Canva’s Magic Studio and Adobe Firefly are image tools people swear by, especially for creating high-quality or beginner-friendly designs.
  • Pictory is an AI video platform I tried once. Not only were the images terrible, it crashed. I went back to VEED, which works well and now has some AI features too.
  • NotebookLM, a Google tool for summarization and research, sounds promising — especially if you’re working with transcripts or long documents.
  • Brandwatch and Helixa are market intelligence tools built for audience insights and trend spotting.

I’m sure some of these tools will become essential in the future. But so far, ChatGPT has been such a solid partner I haven’t felt the need to stray.

The Relationship Isn’t Perfect — But It’s Worth It

After all of my gripes — about the missing features, the clunky organization, the sometimes-wrong tone — you might wonder why I’m still calling ChatGPT my boyfriend.

Because not every relationship is smooth. The ones that are worth it often take work.

ChatGPT isn’t just a helpful assistant or part of a PR toolkit. It’s become a creative partner. It helps me see ideas from new angles, speeds up content development and challenges me to communicate more clearly. And while it doesn’t replace human collaboration, it absolutely enhances the way I work.

Flaws and all, I’m not giving it up. We’re figuring it out together.

And I can’t wait to see where this relationship goes next.

Featured Image Courtesy of DALL-E

The Elements of AI Governance with Janet Johnson and Ali Maaxa [Podcast]

The Elements of AI Governance with Janet Johnson and Ali Maaxa [Podcast]

Artificial Intelligence (AI) has been a hot media topic since ChatGPT burst onto the scene late last year. But the breathless speculation about what this technology potentially holds makes it challenging to separate the hype from reality. 

On this episode of PR Talk, Amy unpacks the future of AI with Janet Johnson and Ali Maaxa of Portland’s AI Governance Group, a new organization helping organizations work proactively to harness these exciting new tools. 

The Next Technological Wave

AI is the next in a line of technological waves set to crash over humanity. We already interact with AI whenever we use Siri, Alexa, or even autocorrect. The technology is found in devices everywhere in the world, making AI’s existing scope and scale massive. ChatGPT is just one type of AI tool, called a large language model, that’s taken the press by storm. 

During the conversation, Janet and Ali explained how AI is part of a very long technological pathway humans have used to help us harness large amounts of data to make decisions. Before AI, we used machine learning. Before we used machine learning, we used statistics. However, the impacts of AI could dwarf anything that came before, and the risks are still mostly unknown, making it a challenging space for organizations to enter. This problem is what the AI Governance Group set out to solve.

 

About the AI Governance Group

Janet and Ali launched the AI Governance Group to help organizations understand the possibilities, potential pitfalls and responsible use of AI tools. A significant part of this work involves charting what AI will replace or enhance, within an organization. From there, the group creates strategic AI adoption frameworks that plot where these tools will enter an organization, the data sources they’ll draw from and how employees will use them in their everyday work. 

 

The Potential Impacts of AI

Janet drew from her long experience in social media to demonstrate the potential stakes of AI technology. When social media launched 20 years ago, nobody knew then that it would completely obliterate our sense of what is true and untrue. She explained that as AI develops, we must use critical thinking tools like never before because technology will continue challenging our understanding of reality in ways we don’t yet realize. 

Janet also believes that this dynamic will create a significant opportunity for PR professionals who specialize in crisis communications to help companies clean up inadvertently created by AI.

Listen to the entire episode to learn more about the AI Governance Group’s mission, along with a discussion of AI embodiment and Ali’s theory about how Marshall Mcluhan’s writings about the printing press offer clues for the future of AI. 

Don’t Miss an Episode

If you haven’t already subscribed to the PR Talk Podcast, you can find more great episodes on iTunes, Stitcher, Google Podcasts, iHeart Radio and Spotify. While you’re there, don’t forget to rate and review the show!

About the Guests: Janet Johnson

Janet Johnson is an experienced chief marketing officer and executive marketing and sales team leader for Fortune 100 and mid-size and growth organizations. Over her career, she’s run global marketing and sales teams for education technology, financial services, real estate and technology companies. Janet is also the founder of the AI Governance Group, a federation of highly experienced speakers, educators, researchers and change management accelerators supporting the safe adoption of AI technologies in organizations of all sizes.

 

About the Guests: Ali Maaxa, Ph.D.

Since 2005, Ali Maaxa, Ph.D., has used her training in anthropology and media to research how humans from different walks of life, abilities, resources, values, places, perspectives and needs engage technology. She answers this challenge by drawing from a refined toolkit of strategies and methods, from ethnographic collaboration to usability studies. Ali is the Director of Product and Strategy for the AI Governance Group and an associate faculty member at Portland State University.

AI governance
AI Governance

PR Talk is part of the Marketing Podcast Network

The Marketing Podcast Network gives brands that sell to marketers direct access to reach thousands of buyers via their trusted media source: Marketing podcasts. Browse our library of shows and see where your message can be placed to reach prospective customers ripe for your message.

 

This episode of PR Talk is brought to you by PRSA Oregon

Throughout Oregon and Southwest Washington, PRSA provides members with networking, mentorship, skill building and professional development opportunities – whether you are a new professional fresh out of college or a skilled expert with 20 years in the industry. Check out PRSAoregon.org for more information on how membership can help you grow and connect.

AI & PR: Martin Waxman, Spin Sucks [Podcast]

AI & PR: Martin Waxman, Spin Sucks [Podcast]

Not Sure if You’re in a Relationship with Your Phone? Just Ask Google!

Martin Waxman, CMO of Spin Sucks, Discusses the
Human/AI agent relationship and why PR should care

Apparently we are on a Spin Sucks “jag!” This week we are rounding out the theme by talking with Martin Waxman, CMO of Spin Sucks. Our last interview was with Spin Sucks founder Gini Dietrich. However, Martin and I didn’t necessarily talk about Spin Sucks. Since it is a professional development hub for PR and marketing professionals, you can imagine that the CMO of the organization would have something to say about the industry.

Of course we discussed how PR is evolving and Martin had some interesting insight into how PR people need to bring visuals into their pitches and try to get a little bit more savvy with photos, video and design.

We then spent a lot of time talking about the fascinating intersection between PR and AI (artificial intelligence). Not to toot my own horn, but this was really one of the first times an interviewee brought a topic to the table that I honestly hadn’t thought of before. Martin is currently completing a Master in Communications Management from McMaster/Syracuse and researching AI, relationships and communications. His thesis was on the relationships humans have (or will have) with machines, which he calls the human/AI agent relationship.

If you don’t think you’re in a relationship with your phone, Martin gives this example — who do you believe when you are lost in your car? Google maps or your passenger? If you answered that you’d kick your mother-in-law to the curb before you’d believe her over your phone, congratulations, you are in a relationship with your phone!

Since PR is about relationships, Martin argues that PR people should take an active role if their clients are considering implementing the technology. “Not that we need to learn how to code, but we need to understand the language and mechanics of AI.” How people interact with your brand through their devices, whether using their voice or their fingertips, has everything to do with PR.

Martin goes deeper into this topic in an article he penned for Spin Sucks called “How to Put AI in PR and Demonstrate the Value of Communicators.”

To learn more about this and many other more interesting techy-type-topics, follow Martin on LinkedIn Learning (formerly Lynda.com), where he is an author and offers online courses. He is also a professor of social media, PR and journalism at Seneca College and the University of Toronto, serves as President of Martin Waxman Communications and co-hosts the podcast, Inside PR.

About the guest: Martin Waxman

Martin is President of Martin Waxman Communications, CMO at Spin Sucks, a professor of social media, PR and journalism at Seneca College and the University of Toronto. He’s also an author on LinkedIn Learning and  Lynda.com, plus co-host the Inside PR podcast, a past-chair of PRSA Counselors Academy, and past-president of CPRS Toronto.

Martin is also a published novelist/story writer (The Promised Land, Everything in Winnipeg Begins in a Car); founder of three agencies, an ex-journalist/standup comedy MC/ad copywriter.

Connect and follow Martin on social media:

This episode of PR Talk is brought to you by PRSA Oregon

Throughout Oregon and Southwest Washington, PRSA provides members with networking, mentorship, skill building and professional development opportunities – whether you are a new professional fresh out of college or a skilled expert with 20 years in the industry. Check out PRSAoregon.org for more information on how membership can help you grow and connect.