It is estimated that in five years, AI will drive 55% of Australian consumer spending by 2030. This projection shows how AI will revolutionise retail in our country. As a retail and point-of-sale (POS) systems expert, it is essential to explore this transformation together and its implications for small brick-and-mortar Australian retailers.

So, we will create a new section in this blog, "AI Musings," to explore artificial intelligence's musing on modern retailing. This space will blend AI-generated insights (approximately 80%) with my thoughts (20%) to delve into the most significant technological revolution in retail today.

The State of Modern Retail in Australia

AI dominates discussions at every retail conference today, signalling its emergence as the new frontier in retail technology.

Adopting AI in retail is not just a prospect; it's happening now. Many retailers already implement AI solutions to enhance customer experiences, optimise inventory management, and streamline operations. For example, our clients have been using AI for years in stock control, but no one is talking about it, and we need to.

I heard about chatbots handling customer queries in a retail firm a few days ago. It was expensive, but as AI becomes more accessible and affordable for businesses of all sizes, we will soon see it in almost all stores.

How AI is Transforming Australian Retail

Personalised Customer Experiences

AI will revolutionise how retailers understand and cater to individual customer preferences, offering a more personalised shopping experience. And it will not take long. If such a system is live in 10,000 shops in one month, that AI will have 800+ years of experience at the end of the month.

Smart Inventory Management

AI is already in our POS system and crucial in predicting demand and optimising stock levels, helping retailers reduce waste and improve efficiency. It has proven vital for retailers who often struggle with inventory management. AI-powered systems can analyse every stock item in the shop with its historical sales data, seasonal trends, and even external factors, like weather.

AI-Powered Customer Service

Chatbots and virtual assistants are improving customer support across online platforms. Currently, 47% of consumers feel comfortable using AI for product selection, while 75% remain cautious about AI handling high-value purchases.

Enhancing In-Store Experiences

AI is set to transform the in-store experience. Retailers use emotional recognition tools to detect customer frustration and seamlessly transfer to human support. This blend of AI and human interaction could be a game-changer for small retailers looking to provide personalised service while optimising staff resources.

Practical Considerations

Cost vs ROI for Retailers

Implementing AI solutions today requires a significant investment, but this is rapidly changing. DeepSeek-R1 is roughly comparable to ChatGPT GPT-4 Turbo, and it is $2.19/128k token, while ChatGPT is $30/128k token, a cost savings of about 93%.

Future Trends in Australian Retail with AI

Looking ahead, the future of AI in retail is bright. By 2030, AI is expected to create 200,000 jobs and $115 billion in economic value, which presents enormous opportunities for retailers of all sizes. That is almost 10% of the Australian economy now.

Voice Commerce

The growth of smart speakers and voice-activated shopping is expected to continue, offering new ways for customers to interact with retailers. I know some clients who now use them in the shop as a translator, and I do, too here. It has helped.

Conclusion

AI is undeniably reshaping the landscape of Australian retail. It is now transforming shopping experiences, retail operations, and customer engagement strategies. We intend to explore this topic here. I encourage our readers to share their thoughts on how they see AI shaping their shopping experiences or what trends they're most excited about.

Let's see how it goes forward together.

I hope you enjoy the new section, "AI Musings."

As a programmer specialising in retail and Point of Sale (POS) systems, I recently embarked on an intriguing experiment: using ChatGPT to create a dashboard without relying on my programming skills. Much discussion has been about ChatGPT enabling non-programmers to write code, with dashboards often highlighted as a key example. I decided to test this claim, and the findings were illuminating.

What's a Dashboard, Anyway?

A dashboard is a visual display that displays important information, commonly called Key Performance Indicators (KPIs). These provide a quick visual overview of the current situation, helping us make informed decisions without the need to sift through large amounts of raw data.

For retailers, dashboards transform massive sales data into actionable insights in seconds.

The Experiment: Following a Non-Programmer's Guide

To simulate the experience of a non-programmer, I followed a YouTube tutorial that promised to teach dashboard creation using ChatGPT.

So, I selected this YouTube here. Please feel free to consider this article as my response article to it.

So, I started with data from our POS software's Sales Report, which has comprehensive insights.

The ChatGPT Experience: Not Quite as Advertised

Data Wrangling Woes

My first hurdle was getting the data into the correct format. While our POS system can export to JSON, I followed the tutorial's suggestion. Later, I found that I had made the correct decision as I would dive into Excel many times to manipulate the data. It became a recurring theme throughout the process.

Paid Account Required

Contrary to the tutorial's claims, I quickly discovered that a free ChatGPT account wouldn't cut it. The credits ran out faster than a sausage sizzle on a Saturday morning. The experiment would have ended if I had not had access to a paid account. Let me know if anyone wants a paid account, and I offer reasonable offers. So, I switched to the paid account to continue this experiment.

Dashboard Dilemmas

After multiple attempts, I managed to create a basic dashboard. However, getting it to look presentable was another story entirely. As any retailer trying to spruce up their shop window knows, making things look good is most of the work.

Real-World Retail Challenges

Then, I ran into the problem of using real-world retail data in an experiment. In business, things are not cut and dry. I would encounter these problems here.

Consignment Stock

Items on consignment threw off profit calculations, as they had no listed cost.

Gift Cards

These presented a similar challenge to consignment stock.

Payouts

While these transactions affect sales numbers, they don't contribute to profit.

I only discovered these issues through this exercise, and it took time to learn these problems each time. The solution was to return to Excel, adjust the data, and recreate the JSON file. It was like constantly restocking shelves but with numbers instead of products and then recreating the dashboard.

The Programming Plot Twist

By now, I had spent many hours. So, when trying to calculate the total profit, I hit another wall. After many attempts, I had enough, so I resolved this by going outside the tutorial's framework. I had to break character and lean on my programming expertise. I delved into the HTML code generated by ChatGPT to understand what was happening behind the scenes. Only then did I finally wrangle the dashboard into something usable!

Now I had this, I could select a department, and it would give me these figures and charts.

Now I had something, but were the figures correct? After five hours of this exercise, I did not check, so it was unusable. In programming and business, it's rarely worth it for one-off jobs. You need stuff that, once done, repeats. Here, you must massage the data extensively before using it. The Bottom Line

It was presented as a quick and easy project for someone with moderate computer skills but turned into a time-consuming ordeal that required the following:

• Over five (5) hours of work
• Extensive Excel manipulation
• The ability to read and understand HTML code
• A paid ChatGPT account

Even after all that, I hadn't yet verified the accuracy of the figures—a crucial step that would likely take many hours more if they were wrong.

Lessons 

While quickly creating custom dashboards is appealing, the reality is not yet here.

For people like us operating in a dynamic and competitive landscape, providing exceptional customer service and support is our key differentiator. So, our support team works hard to respond to client questions, troubleshoot issues, and ensure our point-of-sale (POS) software enables their success. So, when we heard about AI conversation bots that could potentially assist our support team, we were eager to test this emerging technology.

After developing our own AI chatbot prototype and trialling it on actual customer queries, we found there are indeed limitations with AI support today.

We feed it thousands of our customers' queries.

Depending on who accessed its answers, we got these disputed scores. I say disputed as some judges were much more negative than others. This is a consensus score, not an individual view.

- Approximately 23% of the chatbot responses were largely to wholly accurate. These tended to be the stuff that our support staff felt were things they knew well and would have little trouble doing without AI.

- 50% were partially correct but lacked vital details. 

- 15% were unclear due to poorly phrased customer questions. This is a common problem that those who ask questions in the real world to get accurate information need to know much. Rubbish in = Rubbish out.

- 10% were utterly wrong.

Our AI chatbot clearly has room for improvement before it goes live.

However, AI can still provide value when implemented correctly by augmenting our support team’s capabilities. 

Why AI struggles with complex support queries

Through our testing process, we gained insight into factors that limit AI chatbots’ capabilities for software support:

1. Insufficient training data

Like humans, AI systems require extensive ‘practice’ through training data to become highly skilled at specific tasks. Our prototype only had access to a thousand pre-recorded customer support calls from which to learn - this is far too little data to fully grasp the complexity and nuances of troubleshooting what is our system probably the most advanced POS software in Australia.

2. Incomplete understanding of context and ambiguity

Humans draw upon years of world knowledge and experience when interpreting language. AI chatbots currently lack this contextual awareness, so they struggle to clarify vague questions and handle ambiguities. Our clients have a range of English knowledge; some know plenty, we have clients with doctorates and some that barely speak English. So 15% of customer queries stumped our chatbot due to unclear wording that we could easily interpret.

3. Inability to grasp nuanced domain knowledge

POS software is feature-rich and built to handle intricate retailer needs. Most AI systems today would need explicit training to comprehend the industry-specific terminology, workflows, exceptions, integrations, and technical considerations involved. Without directly relevant domain training, the chatbot’s knowledge gaps led it to miss critical details in 50% of test cases.

Best practices for implementation

While the technology still has maturing to do, useful AI assistance is within reach by following guiding principles for implementation:

Ensure sufficient high-quality training data

For accurate learning, training datasets must cover each type of support scenario the AI may encounter. Data should be cleanly recorded without errors that could propagate misleading information. The problem here is that our information is real, and in the real world information with errors is common.

Provide ongoing human feedback.

Humans must continually verify and correct the AI’s responses, allowing its knowledge to evolve through feedback over months and years. This human-in-the-loop oversight is critical. This will take a lot of work.

The future role of AI in customer support

Though AI chatbots cannot wholly substitute for human support staff at this stage, we see bright possibilities for AI assistance going forward:

• Handling high volumes of repetitive queries - Freeing support staff to focus on higher-level, more complex problem-solving for customers.

• Providing 24/7 self-service - Enabling customers to access basic troubleshooting after hours when support staff are offline.

• Supporting human agents - Assisting our support staff with knowledge lookup, documentation, and tracing issues.

While AI support today is imperfect, we are excited by its prospects through careful implementation. Over the next several years, we aim to refine our chatbot to be an invaluable teammate for our human support staff - combining the best human and machine capabilities to deliver exceptional customer assistance. With a spirit of experimentation and patience, as this emerging technology matures, we know that AI promises to improve customer service.

Let me know if you are interested in learning more because this is really interesting stuff.

ChatGPT for Businesses 

Most of our clients are very progressive regarding technology and are as excited about ChatGPT as we are.  

What is ChatGPT

Its an AI chatbot. If you have yet tried out ChatGPT, click here. Make yourself an account, and then give it a try. Ask it some questions, ask it to translate some text into your language, give it some history questions, religious or theological questions, cooking questions, etc. You will be amazed at what it can do. 

This is why businesses today are paying attention to ChatGPT. It is an appealing option for businesses of all sizes looking at improving efficiency because it can save time and money. Exactly what it can do is still being determined.  

Fun fact

I asked ChatGPT to describe itself and put its description into a drawing program; this is how ChatGPT sees itself.

Competitors to ChatGPT

There are several rivals for these products. The most well-known is Bard by Google, but many others are into it; Vicuna is a Japanese product. 

Quality 

Quality is the most crucial point. If the product cannot do the job, what difference does anything else make? Here is a very rough test of the quality of several product results.

I wonder if most users will notice that much difference in quality. All have their strengths and weakness. 

You can check out the quality here and make up your mind.

I feel that the free version of ChatGPT is about as good as Vicuna. Overall I prefer Vicuna for business.

Price

The older ChatGPT is free, but the newer product is $20 per month. The others are all free for now. If you want to try the newer ChatGPT before paying for it, try the others first and the older version of ChatGPT so you will know what you need before jumping into it. One needs to learn to walk before one starts to run.

Availability

All except Bard are available now to an Australian. Bard is officially yet to be open to Australians. If you want to run Bard now in Australia, you need a VPN. 

Everyone is now waiting to see the Chinese product, but it has yet to be available in Australia.

Information

This is a big problem in business; Bard is the only one now with up-to-date information, and the rest are about two years old. Yet a businessperson needs current information. A person will come to a shop and generally wants to know about something recent. This puts significant limitations on its business use in Australia.

Outages

Even with paid services, users need help with using the product. It can be very frustrating. Also, many reports say that OpenAI has made ChatGPT stupider to get faster speeds. 

Accuracy

With a Google search, you know where the information comes from; this is not the case with these products often, and YES, the information they supply is often wrong. 

Since these often do not supply references, you must check the answers you get from these products. Be careful.

Political filter

Except for LLaMA, they all have political filters in place. These can drive you crazy as innocent questions can be refused to be answered as such. Heavy users of these products often will debate if Big Brother is watching them. 

Conclusion

Today we are all paying attention to this technology. It is an exciting technology that has the potential to cut costs and increase productivity. I am more than happy to discuss it if anyone wants. 

Executive summary

> These AI can answer a wide range of questions.
> Businesses are looking for them because of their potential to cut costs, save time, and increase efficiency.
> They all have their pluses and minuses. 
> You may not notice a significant difference in quality 
> These products' limited business applications may be due to outdated information.
> These products give incorrect answers, so you must check their accuracy.