Artificial Intelligence (AI) tools and the future of B2B Marketing

AI tools: friend or foe?

The future is here, people. Kids don’t need to do homework anymore and I might as well retire from my marketing career early. The recent rise of scarily-advanced Artificial Intelligence (AI) tools has the potential to be the biggest disrupter since, well, a global pandemic, especially in the education and marketing space. And while we never think it’s a time to panic (unless I see a Harry Potter size spider running at me, then it DEFINITELY IS TIME TO PANIC), we do want our clients and friends and families to get on the front foot as this technology continues to develop.

What are these AI tools then?

Well, let’s just ask one of them. I’ll check with ChatGPT how it would define itself: Me: What are Artificial Intelligence (AI) tools like ChatGPT? ChatGPT: Artificial Intelligence (AI) tools like ChatGPT are computer programs that can mimic human intelligence and perform tasks that would typically require human intelligence to complete. These tasks include natural language processing, image and speech recognition, decision making, and problem solving. ChatGPT is a specific type of AI tool called a language model, which is trained to understand and generate human language. Other AI tools include computer vision models, which are trained to understand images and videos, and machine learning models, which are trained to identify patterns in data and make predictions. Back to me, again (I swear). Clear as mud, right? So far I’ve found that it’s easier to understand in context of application – what do these tools do versus what they are.

How can we use these newer AI platforms?

Education is probably where we first started hearing a lot of buzz – kids are ONTO this tech, and we think parents should be, too. You may have seen New York in the headlines for banning Chatbots on both students AND teachers’ devices. I’m probably in the camp that thinks it might be better to adapt the lesson plan than try to put the cat back in the bag. Without being cute though, it’s probably the end of essay homework and online assessments as they are today. There might be a need for more one-on-one, in-classroom and qualitative approaches to learning. And you know what? I personally think this might be a good thing. Plus, students will need to learn how to best use this technology. Remember when teachers told us we had to learn mathematics because it’s not like we would walk around with calculators in our pockets? And now that’s what we literally do with our smart-and-soon-to-be-even-smarter phones. This new technology isn’t likely to go away, so how to do we prepare the next generation for how they might need to use it in their chosen career (if that career even exists yet! **Thinks back to managers from my early days saying social media will never be a job…**) That’s probably all we wanted to say on education for now – I’d just encourage parents to be aware and, again, don’t panic! Instead, perhaps start using these platforms yourself so you’re better placed to help and advise your kids. What we’d really like to focus on is what this means for us and our clients (self-centred, we know, but we’re only human – again, I promise). 

Types of AI tools

There are many different types of AI tools – here’s a quick run down of some of the common ones (and yes I did ask ChatGPT for this list but it was long and wordy so I’m going to summarise in my own words):

• Language models (like ChatGPT) which are trained to understand and generate human language which could be used for translation, editing or content creation.
• Generative models (like DALL·E 2) which can create new data that is similar to existing data for things like image and video generation – in fact, I can thank Midjourney for the futuristic feature image it made for me when I asked it to make an AI marketing image.
• Machine learning models – these can identify patterns in data and make predictions (i.e. image classification, sentiment analysis and predictive maintenance). One of our clients, The Daily Edit, uses a machine learning model for a number of practical uses, such as analysing the news and finding missing details or misleading text (will they see the end of ‘fake news’? One certainly hopes so!)
• Robotics and autonomous systems – a pretty obvious one to understand given the rise of autonomous vehicles and machines.
• Recommender systems – these are used to make personalised recommendations to users based on their interests and behaviour – I’m sitting here typing this to you now while listening to a playlist that Apple Music has tailored for me based on my listening habits, though getting a little bit of whiplash flipping between my eclectic hip hop, classic, country, opera and oldies faves (ahhh! Here comes some Jimi Hendrix’ Red House, one of my top 50 easily, maybe even top 10, how did you KNOW, Apple? You get me.)

Right, there are more on the list but that’s enough to give you an idea. The reality is, we’re all probably already using tools that rely on artificial intelligence. Many of our marketing tools also incorporate some AI, whether it’s our CRM (customer relationship management), Google Ads or crowd pleaser Canva.

AI tools and B2B marketing

So does that mean that you no longer need a copywriter, graphic designer, editor (or a marketing manager that’s kind of all of these things but none of them, like me?!) Well, yes and no. It’s certainly true that technology has dramatically shaped some industries and businesses (sorry, Kodak but you’re just the easiest heuristic for this). But that same tech also created opportunities for others, especially those of us working in digital mediums. We think these AI platforms will offer a similar (or, gulp, bigger) shake up, and there will be some pros and cons. Some examples: General content / articles

• Pros: It’s really fast and so far grammar and spelling have been exceptional. Its language is conversational and can be tailored for tone and humour. It can save loads of time just getting you started in your writing which I’ve done several times in this article (I’ve noted where), and my teammate Steven has enjoyed using it for editing purposes.
• Cons: These articles don’t seem to have reliable sourcing for things that are stated as fact and often the statements are completely wrong (we did a live example for a client in life insurance and ChatGPT tried to tell us that a good social post would say ‘Life is short and so is our cover!’)

Images / design – pros

• Pros: You can generate something quickly for social media or a website, it can help give you inspiration or ideas and also, if I’m being honest, it’s pretty fun. Perhaps it can be used to help create ‘on brand’ content once it learns how to use your brand toolkit.
• Cons: The images can be a bit strange and creepy in my view, but more concerning is instances where real-life artists’ work is being used or incorporated without credit or permission. When it comes to creating things related to brand, it might be able to create a logo but I don’t think it will ever be able to create a truly unique and bespoke brand identity based on your story and vision and bring it to life.

My teammates and I have had an absolute ball doing our research, and we’ve learned a lot even in these early days. One of the biggest takeaways that my coworker Steven noted is that us as marketers will need to get our heads around ‘prompt engineering‘ – using our marketing expertise to become skilled at developing AI prompts. Translation: crap in, crap out. We’ll need to know when to use AI, what to ask for and how to ask for it. We’ll be able to use these tools to help deliver faster results for our clients when it comes to blogs, SEO and social media, but every inch of the content will need to be reviewed, edited, sourced and quality checked. We’ll need to make sure the content is aligned to the marketing strategy, created in the brand’s tone of voice and appropriate for the audience and channel. There’s great potential to further leverage these tools for marketing automation, analysis and reporting. These should, in theory, be time savers for our team which enables us to focus on overall effectiveness and quality for our clients.

Are there any risks to using the AI platforms?

YES. There are many risks, mostly based on unknowns or things we don’t understand very well yet. The biggest one that we would flag is around privacy and data security (or lack thereof). We would not recommend using your name or any personal details in your search or testing with AI platforms. When we were brainstorming about business use, the idea of using AI to review things like applications in the recruitment process, which in theory could give you a less-biased view of candidates. Sounds like it might be a positive, right? But if you go uploading someone’s resume for an application that was meant to be kept confidential, even if you remove their name you’ve definitely given the AI more than enough information to find out who they are – and then what does it do with that data? We don’t know. So I’d be highly unlikely to share any sensitive information with an AI platform. There is also a risk in relying on the content and data that AI provides – how confident would I be in its accuracy, appropriateness and uniqueness? Not very. Perhaps this will improve over time, with additional quality and plagiarism checker tools and transparency about how the AI works.

Is this a ‘Google killer’?

Well, I don’t know about ‘killer’ but Google should probably be $hit scared. We’ve been hearing that Microsoft is investing $10 billion (yes, billion) in Chat GPT creators, OpenAI. But if you ask ChatGPT if Google should be scared, here’s some of what it says: “ChatGPT is a powerful language model developed by OpenAI, but it is not directly in competition with Google… So, it is unlikely that Google should be scared of ChatGPT, but rather it’s a matter of competition and innovation in the field of language models and AI in general.” But in thinking about its use, it’s hard to imagine the ChatGPT-type platforms WON’T monetise their offer and allow ads and such. And how much easier is it not to scroll through pages and pages of search results? Once the data is live/in real time, you can hop on and ask ChatGPT things like “What is the best marketing team in Australia for B2B businesses?” And the answer will obviously be Businessary **slightly cringey wink emoji here**

Is this the rise of AI and end of human civilisation?

I dunno, if we allow technology to make big decisions for us based purely on logic and numbers and no emotion then probably, LOL! I did ask ChatGPT that same question though, and this is what it said: “No, it is not. Artificial intelligence (AI) is a tool that can be used to improve many aspects of our lives, including business, healthcare, and transportation. While AI has the potential to automate certain jobs, it also has the potential to create new jobs and improve productivity. It is not the end of human civilization but it’s important to consider the ethical and societal implications of its development and use.” I don’t know about you but I don’t feel fully reassured. Either way, if you’d like to make the most out of your b2b marketing in the time we have left in charge of things, you can contact us or even book in a free 15 min appointment with me here.