Feature
The Gist
- AI advancements. Generative AI has democratized sophisticated solutions, fueling disruption.
- Need for transparency. Transparency in AI use helps build customer trust and dispel fears.
- Explainable AI. While technical details may be complex, consumers need understandable explanations.
Consumers today have been inundated with news about the latest AI-driven technology: generative AI, conversational AI, machine learning, large language models, AI-driven search engines and AI assistants. To the average consumer, it can be daunting at best, overwhelming at worst. Although many consumers are eager to be able to personally use AI for various tasks in their lives, others are trepidatious when the brands they do business with use AI without disclosing it. That is why transparency is vital when brands use AI. This article will delve into the reasons why transparency is good for both businesses and consumers and how brands are being transparent with their customers about their use of AI technology.
Why All the Fuss About AI?
There are likely to be some consumers who are left wondering what all the fuss is about — after all, we’ve been using artificial intelligence for decades now — and they wouldn’t be wrong. The idea of artificial intelligence has been around since the 1950s. In 1955, Allen Newell and Herbert A. Simon created the first AI application called Logic Theorist. The next year, John McCarthy at the Dartmouth Conference came up with the phrase "artificial intelligence," and the academic field of AI was born. Since then AI applications have continued to evolve and improve, science-fiction movies have included the idea of AI (and unfortunately, the AI villain), and society as a whole has gotten used to the idea of AI. And then came generative AI and ChatGPT.
On Nov. 30, 2022, OpenAI announced the release of ChatGPT 3.5, a natural language processing (NLP) application that enables users to have conversations with a computer. ChatGPT 3.5 is a large language model that was trained on a massive dataset of text from the internet. The text totaled around 570GB and was comprised of 300 billion words, all of which were scraped from the web up until 2019. ChatGPT 4 was officially announced on March 14, 2023, and was trained on a much larger dataset that was scraped from the web up until 2021.
Many may ask why the release of ChatGPT caused so much buzz, concern, and disruption at a time when we had already been using AI, and ChatGPT 1 & 2, for that matter. In fact, many people have used conversational AI chatbots for customer service without any concerns. ChatGPT 3.5 caused so much excitement because it could not only have complete conversations with humans about any topic, it could seemingly create stories, poetry, lyrics, reports, business plans, and images, and do so quite well. When ChatGPT 4 was released, it took the bar exam — and scored in the 90th percentile while ChatGPT 3.5 had scored in the 10th percentile. ChatGPT 4 similarly improved its results on parts of other tests as well such as the SAT and GRE.
Jason Stanley, head of insight at Local Logic, which provides location insights for real estate, told CMSWire that while AI has been around for a while on consumer-facing applications such as Google, Spotify and Netflix, most people weren't even aware they were dealing with AI. "ChatGPT's easy-to-use interface and integration capabilities have led to the democratization of generative AI, enabling even small businesses to implement sophisticated AI solutions, thereby causing disruption," said Stanley.
OpenAI has created an AI model that, if it was human, would likely be the smartest person on Earth. Bells started going off in people’s heads that a), this could be extremely useful for many applications, and b), this could easily take over the jobs of millions. Additionally, because of the AI model’s level of intelligence, alarm bells began to ring in not only the public’s mind, but also the minds of many of the top AI developers in the industry, many of whom petitioned for a pause in AI development so that regulations and guardrails could be put in place to safeguard humanity from potential annihilation and extinction.
While things have calmed down a bit, there are literally thousands of applications across industries that are available now that have been created based on the ChatGPT models, and more are being released each week. Consumers are often unsure if they are speaking with an AI model or a person and are left wondering if the content they interact with was created by a human or AI. They are also concerned that AI may somehow leak their personal data. Thus, the reasons why brands must ensure transparency when it comes to their use of AI in customer-facing applications.
Stanley explained that for businesses that use AI, transparency means openly sharing information about how AI systems work, their objectives and their potential implications. “It implies taking responsibility for AI decisions, acknowledging errors, and outlining steps to rectify them,” said Stanley. “Brands should disclose how they ensure their AI systems operate in a fair and unbiased manner. Transparency involves disclosing what data the AI uses, how it is stored, and who can access it, ensuring compliance with data privacy laws and regulations.” Stanley suggested that brands should aim to make their AI operations understandable to their customers, avoiding excessively technical language or black box phenomena.
Related Article: 5 Ways Transparent Personalization Can Win Over Customers
How to Explain the Unexplainable
If the large language models were based around explainable AI (XAI), then it would be fairly simple to explain to consumers exactly what the AI model is doing, how it came to the conclusions it did and why it did what it does. Unfortunately, it is challenging to explain how large language models work even to those who consider themselves to be technically adept. An article from CMSWire about AI-generated images goes into detail about how AI is able to generate images, and even with a comprehensive AI glossary available, it is still extremely challenging to fully comprehend what is going on inside the AI box.
Fortunately, most consumers could not tell you how their television works either, and that’s OK because they are not concerned that it is doing anything nefarious. Consumers are not necessarily interested in the nitty-gritty details about how AI functions, but rather, they want to know how it is being used by a brand, why it is being used and how will it impact their interactions with the brand. They want to be reassured that it is not collecting information that could be leaked, and if it is collecting data, how it is being used and how long it will be retained. In short, they wish to be reassured that the brand has their best intentions in mind, and that the use of AI will improve the experiences they have with the brand.
Ricky Spears, founder and CMO of RickySpears.com, an internet and gaming tips and tutorials portal, told CMSWire that customers see AI systems without transparency as "black boxes" that make choices or suggestions without a clear reason. "This lack of transparency leads to a lack of trust in brands, which can have negative consequences. People are concerned about privacy and are curious about why their likes and dislikes are tracked." Spears explained that by providing clear explanations of how AI systems make decisions based on human activity, people are more likely to trust those systems and use them in a responsible manner. “When AI systems are able to explain how they make decisions, it's easier for people to identify potential biases or errors in the system.”
As an aside, when asked to describe how it works, ChatGPT 4 itself provided the following analogy that helps to understand how and why it does what it does:
“I'm an artificial intelligence program created by OpenAI known as GPT-4. You can think of me as a really advanced language machine that's great at generating human-like text. Here's how I work:
Imagine you have a gigantic book that contains everything ever written on the internet until 2021 (my last training cut-off). This book has everything from novels and academic articles to social media posts and instructions for making a sandwich. You've read this entire book so many times that you can predict, based on what words come before, what word is most likely to come next in any sentence.
When you ask me a question, I start to generate a response. I take into account the words in your question and begin to predict what word should come next, based on all the patterns I've learned from that gigantic book. I do this one word at a time until I've generated a full response.
I don't actually understand the content I generate. I don't have feelings, beliefs, or personal experiences. I don't know specific information about individuals unless it has been shared in the conversation I'm currently engaged in. I also don't have the ability to access or retrieve personal data from previous interactions unless it's part of the same conversation.
Overall, I'm a tool that's here to provide information and answer your questions to the best of my ability, based on the information I was trained on.”
How AI Is Being Used by Customer-Facing Brands
AI has been used to improve the customer experience by many customer-facing brands over the past few years. For example, 1-800-Flowers partnered with IBM to use its AI-driven Watson program, which it used as a smart virtual shopping assistant with the goal of transforming the online customer experience. 1-800-Flowers’ version of Watson is called Gwyn, an acronym for Gifts When You Need them. Gwyn helps customers discover the best gift to send to family members through the use of customized product recommendations.
IBM’s Watson was also used by the children’s beloved Sesame Street franchise, which partnered with IBM to leverage “cognitive computing” for early childhood education. The concept was to use AI to create products featuring Sesame Street characters and content that is able to personalize responses to individual students based on their skills, interests and developmental trajectories.
KFC partnered with Baidu, China’s version of Google, to use AI along with facial recognition technology in order to predict customers’ orders. By gauging a customer’s age and mood, the AI-driven system is able to recommend the menu items that are the most likely to be ordered.
Similarly, the UK-based fashion brand Thread uses AI to create personalized clothing recommendations for its customers, who take quizzes on style to generate data about their personal style choices. By using this data, the AI application is able to provide customers with personalized recommendations.
Most importantly, these brands were transparent about their use of AI, announced their partnerships with the companies that provided them with AI functionality, and were upfront about the ways that the AI technology would be used to improve their customers’ experiences.
Related Article: Consumer Wants: Privacy Transparency, Online Security, Better Customer Experience
Transparency in Action
Most consumers' concerns about AI focus on AI-generated content, deep fakes, data privacy and whether the content they read or watch has been generated by AI. One can only imagine their concern when the AI application is surgery, and that is exactly the case with Robert Masson, neurosurgeon and CEO of medical tech company eXpanded eXistence. Masson told CMSWire that in the last few months, as CEO and founder of an AI-enhanced surgery software company, he has been talking to people at large about their AI fears, concerns and opinions. "Regardless of B2C or B2B there is a lot of anxiety about it and I believe passionately, not only in the transparency part, but also in the communication regarding mastery of this amazing, powerful tool."
Masson recently spoke at Collision in Toronto and specifically focused on why he is qualified as a 34-year innovation-centered neurosurgeon to bring amazing and powerful tools safely to surgical health care. “The focus of the talk was to address the tool, AI, to recognize its power, its opportunities but also its risks, and talk about process, and meticulous insertion, small steps at a time.”
Webinar
Sep
25
CMS Briefing: A Live Look at What’s Next in AI-Driven Platforms
Learn how leading organizations are using AI‑driven tools to publish faster, personalize smarter and stay secure.
Register
Webinar
On demand
Ready or Not: How Data-First Organizations Are Unlocking Agentforce Potential
Learn how to cut through the noise, activate Agentforce and build a Salesforce AI strategy that actually delivers.
Watch Now
Webinar
On demand
AI in Customer Service: Faster Resolutions, Happier Customers
Don’t let rising demand burn out your team. See how to build a smarter, more resilient support org.
Watch Now
Webinar
On demand
From Hype to High-Impact CX Strategies That Actually Scale
Turn buzzworthy AI and outsourcing trends into measurable CX wins with fresh 2025 data.
Watch Now
Webinar
On demand
Insights to Action Rethinking the Contact Center for Real Business Impact
Join our exclusive webinar to hear CX executives share their innovative strategies for transforming service delivery.
Watch Now
Webinar
On demand
Accelerating Healthcare Ops with AI
Sign up to see how your peers are putting AI to work — and making it stick.
Watch Now
Masson passionately espouses the belief that AI holds promise to be used to enhance and improve the practice of surgery. “We will make surgery better worldwide with this incredible brilliant accelerant of machine learning and predictive analytics.”
“All surgical tools, in our case, can be dangerous if not used in an expert way, but when education, training, experience, and ultimately mastery are used, the best tools change lives and restore health and vitality,” explained Masson, who strongly believes that transparency, education and process are critical to a respectful, and proper insertion of this most powerful tool into our forever-evolving world.
Final Thoughts on AI & Transparency
As AI becomes a regular part of our lives, transparency is vital for brands using this technology. Brands that are transparent about their use of AI are showing respect for their customers’ autonomy and trust. Keeping the lines of communication open regarding AI's operation, implications and data privacy can build trust and dispel fears. A commitment to transparency in AI applications is key for its ethical use and fully realized potential and is an essential part of a successful AI strategy, enabling meaningful, trust-based relationships with customers while improving brand loyalty.
