Martech Strangelove: How I Learned to Stop Worrying and Love the GPT Bomb

Secrets to Martech Success with GPT

“I can no longer sit back and allow GPT infiltration, GPT indoctrination, GPT subversion, and the international GPT conspiracy to sap and impurify all of our precious human thoughts.”

“Well, boys, I reckon this is it – combat toe-to-toe with the GPT Robots.”

Intro

Some of us are contrarian humans and it’s not in our nature to follow fads.  And so, in November of last year when these pre-trained AI transformers – lurking backstage for years — took the main stage, and then threatened to hack into nuclear codes, those of us so inclined raised our eyebrows and dug in on the side of us carbon-based thinking units.  

I’ve been to two tech conferences in the last month and witnessed firsthand the growing mayhem around this new-age AI.  No doubt one big difference between now and the emergence of the 90’s AI is the speed at which this hype cycle reached a crescendo, and the extent to which GPT is being sold like snake oil to cure all ailments.  And like search in the late 90’s, the speed and ease at which it has entered into the public conscious, and even the accessibility for anyone to use it, has got everyone’s attention.

Accompanied by Langchain, AutoGPT, autonomous agents, prompt engineers, embeddings, and hallucinating large language models – GPT along with a whole new universe of techniques and terms have exploded onto the scene.  Within months all major Martech vendors scrambled fighter jets to launch press releases on yet to be released GPT-infused software.

But then a few days ago, 8 months after G-Day, I popped onto my bank’s website, and the same old UI with the same old poorly personalized experience, sorely lacking self-driving marketing features or an optimized customer experience stared back at me.  Seems maybe deep-learning NLP wasn’t the only thing taking LSD.

The coming out of these inventions is interesting – captivating in fact.  And misunderstand me not, as a big lover of GPT’s rhymes, poems, pictures, and puns, I was very intrigued by its chic performances.  Equally fascinating is that as pack animals, it’s in our human DNA to follow; to want to be part of the latest fashions.   And so GPT gets my alpha dog / tech beauty queen of 2023 vote. 

Still, coming to terms with this latest knighted AI craze — “Sir GPT” — might be prudent.  Without kneeling at its throne, even non-conformists might have to accept it as an eventual buddy, same as happened with smartphones and search a quarter century ago.

So here are 4 tips for Martech leaders on how to approach the GPT mania.  

Tip 1: Do your GPT homework – Separate fact from fiction

With each Martech vendor offering GPT, consider asking these questions:

  1. Show me the GPT features in your software?  When and in which version will this be available?  Can you give me some precise plans around availability?
  2. Can you show me the top features you believe will produce a quantum leap in impact in terms of either lift or productivity (versus features that are simply automating legacy processes)?
  3. What about the value I will get from using these features?  If you can’t show me actual case studies yet, show me projected value, and the math used.
  4. I work in a very large business, so how can I use these features practically and responsibly within an enterprise change management process?
  5. How much will this cost?  Not just the GPT subscription cost, but any other costs that will go into putting this into production.
  6. Can I trial some of these features today?  How much will that cost?
  7. How can I set up a fair test of these features against my baseline?
  8. What are the top 3 features on your roadmap that have nothing to do with GPT?

The answer to that last question will be telling for several reasons.  First, it will give insight into the overall Martech roadmap and strategy, whether balanced — or worse, hastily constructed.  Second, the features mentioned will help with a comparison to your goals and priorities, and how well aligned they are.

As a marketer, consider these as potential use cases:

  • Safely generating alternative subject and body copy for existing promotional offers.  For example, new subject lines for emails, website tile and call to action labels, and offer descriptions.
  • Built-in assistants to automatically configure marketing components that previously required manual set up.  For instance, when creating a campaign in a certain category, and providing basic information, GPT assists in pre-populating fields to minimize manual key entry.
  • For inbound channels, GPT provides more intelligent chat bot assistance.   It does a better job answering basic questions, searching knowledge bases and documentation for answers, and learns from feedback on whether its answers were helpful.

Tip 2: Run some experiments

Consider running a few controlled experiments to gauge GPT’s applied value.  

To ensure the tests are useful, make sure to measure against a known benchmark.   Ask if the experimental design is reproducible, fair, scalable & cost effective.  In other words, will the test be easy to set up?  Can it be run repeatedly in a short period of time (producing adequate experimental results to measure against the benchmark)?

  • To test new copy, pit GPT’s proposed writing against the champion.   Randomly assign GPT’s offer to a 2% sample of customers.  Does it outperform the champion over time?
  • Do the built-in assistants really save time in configuration?  Or is it a bell/whistle that looks good in a demo, but that real-life users won’t use?  Do usability testing with the real users to find out.
  • Do the chat bot interactions result in higher NPS scores?   After each chat bot session, ask for an NPS score for the session, and compare that with current scores.

Tip 3: Study the results and invest accordingly

This tip may seem obvious.  However, the knee-jerk reaction might be to adopt the new feature(s) if the test results show any improvement over the baseline.   But make sure to weigh the total costs versus the actual benefits.  If the lift is meager, but the costs high, the ROI might not be there.

In addition, network and study your peer’s experiences as the Guinee pigs.   Are the projects going well?   Are they producing the expected results?   Is there a stark difference between what was on the glossy brochure versus how the real-life experience turned out?  In other words, learn from the mistakes of others.

Tip 4: Stay the course – with a solid overall DNA – Data aNd Analytics – Modernization Strategy

Massive data and fine-tuned analytics are the core materials of GPT (or any successful application of AI), and both must be the genome that fuels every company.  Firms must weave data & analytics into their organizational fabric to fundamentally transform two aspects of their business in careful balance: a hyperfocus on personalized customer experience while becoming operationally efficient.

But where to start?   Here are three things to concentrate efforts on:

  1. Implement advanced analytics to improve customer experience: By compiling and analyzing customer data across a variety of channels, you’ll gain insights into their preferences and behavior. This will support personalized services, development of appropriate products and services, and improved customer engagement.  In addition, use predictive analytics to identify the best channels to reach your customers.
  2. Optimize operations and reduce costs through data-driven decision-making: By analyzing operational data, you can identify inefficiencies and bottlenecks in your processes. This can help streamline operations and reduce costs. For example, banks can use data analytics to optimize loan approval processes, improve credit risk management, or reduce fraud.  Telcos can analyze real-time network performance data and even identify potential issues before they occur and take proactive measures to prevent them.
  3. Build a data-driven culture and foster data literacy among employees: To fully leverage the power of data and analytics, you need a culture that values data and encourages data-driven decision-making. This requires not only the right technology and infrastructure but also a workforce that is knowledgeable about data and analytics. Winner brands will provide training and resources to help employees develop data literacy skills and create a culture that encourages experimentation and innovation.

Conclusion:

In the end, though there will be a few lucky hares, for the majority the tortoise-like approach is the winning strategy.

Oh, by the way, I took my intro words, plugged them into GPT, and gave it the following prompt. 

————————-

GPT prompt: Write me a pun based on the fable of the tortoise and the hare using this prose <inserted above intro words>

————————-

GPT response:

In the world of AI, a contrarian thought I bore,

As GPT took the stage, its hype soared and more.

But now I’ve come to terms with this AI craze,

Sir GPT, they call it, deserving some praise.

I won’t kneel at its altar or its throne,

But I’ll let it into my life, like Google once known.

Tech conferences showcased mayhem and noise,

With Langchain, AutoGPT, and AI toys.

Martech vendors scrambled, their releases to boast,

Yet my bank’s website remained a poor host.

No self-driving marketing, no personalized flair,

Perhaps deep-learning NLP was also on a wild tear.

These recent inventions captivate, it’s true,

And I love a good pun, rhyme, or verse that’s new.

But as pack animals, we follow the alpha’s lead,

And GPT claims my alpha dog award, indeed.

So here are four tips for Martech leaders to heed,

Do your GPT homework, experiment and succeed.

Study the results, invest wisely in this race,

But remember, the tortoise’s approach sets the winning pace.

————————-

This robot is kind of a cute poet.  But Sr GPT, you didn’t exactly write a pun, so allow me to assist you:

If one takes the hare’s approach you may be “hare today but goon tomorrow.”