Artificial Intelligence (AI) applications are blooming in many sectors and transforming the future of supply chain planning, but there’s a newish player recently making a lot of waves and taking the spotlight in the AI conversation. ChatGPT, the AI-powered chatbot created by OpenAI, amassed an impressive 1 million users in its first five days live, offering the world a fascinating glimpse into the current state of AI capabilities.

Unlike traditional chatbots, the ChatGPT (Generative Pre-trained Transformer) model has been trained to generate responses based on data from a vast array of sources such as books, articles, reports, and websites. So, you could say it’s a well-educated chatbot, and it’s remarkably good at assembling fragments of information into a coherent narrative. But its sense of authority may deceive you. As an AI model, it lacks personal experience, and its knowledge only goes up to the end of 2021, and it can’t connect to the internet to find the latest information. In fact, at the time of writing this we asked ChatGPT “what is ChatGPT?” and the response was: “I'm sorry, but I am not aware of a model called "ChatGPT."

ChatGPT stands out from previous language models for its gratifying ability to handle feedback about its answers, admit its mistakes, challenge incorrect premises, and even recognize inappropriate requests and reject them. The model responds to elaborate questions quickly and credibly, and the answers sound legitimate – which begs the question: how accurate is the information provided?

We put ChatGPT to the test to see how accurately it can respond to some questions about supply chain planning technology. These are the questions we asked, the AI-generated responses, and what our human experts think about the answers.

Why is it important for companies to focus on configuration rather than customization when it comes to supply chain planning technology?

ChatGPT said:

It is generally more efficient and cost-effective for companies to focus on configuration rather than customization when it comes to supply chain planning technology. Customization involves making significant changes to the software to meet specific needs and requirements, which can be time-consuming and expensive. In contrast, configuration involves setting up and configuring the software to meet the needs of the company, without making significant changes to the underlying code.

Focusing on configuration can help companies get up and running with their supply chain planning technology more quickly and at a lower cost. It can also make it easier to upgrade or migrate to new technology in the future, as customizations may need to be re-implemented each time.

Overall, it is generally more efficient and cost-effective for companies to focus on configuration rather than customization when it comes to supply chain planning technology. This can help them get up and running more quickly and at a lower cost, and can make it easier to upgrade or migrate to new technology in the future.

Our comments:

We’d agree with ChatGPT’s answer here. When selecting supply chain planning software you want to look for solutions that are easily configured to align with your business and priorities. As noted above, this helps accelerate implementation and time to value, reduces overall costs and allows for an easy upgrade path. A configurable solution also means industry best practices and domain expertise are codified in the software. On the flip side, a customized solution, often one where a vendor paints a highly elaborate vision for what could be possible, will cost an order of magnitude more and possibly take years to implement.Additionally, using highly customized software can make process change management harder for the entire organization. Companies and their selected vendor tend to bake in poor and under-performing business practices accelerating their negative impact on the organization. Another potential pitfall is talent. As people move on so does their knowledge of the system and the unique customizations baked in. In the long run, this will halt your supply chain maturity progression.

What is composability and why is it important in supply chain planning?

ChatGPT said:

Composability refers to the ability of different systems or components to be combined and integrated in a flexible and modular way to create new functionality or capabilities. In the context of supply chain planning, composability is important because it allows organizations to build and customize their supply chain planning systems to meet their specific needs and requirements.

For example, an organization might have a transportation management system (TMS) that is designed to optimize the routing and scheduling of shipments, a warehouse management system (WMS) that is designed to optimize the movement and storage of inventory within a warehouse, and an enterprise resource planning (ERP) system that is designed to manage various business processes, such as finance and accounting, human resources, and production planning.

If these systems are designed to be composable, the organization can easily integrate them to create a more comprehensive and integrated supply chain planning system. This can help the organization streamline its operations, improve efficiency, and better respond to changing customer demands and market conditions.

Overall, composability is important in supply chain planning because it allows organizations to build and customize their systems to meet their specific needs and requirements, which can help them optimize their operations and better respond to changing market conditions.

Our comments:

It’s interesting how ChatGPT focused on the business architecture and used an example of execution systems (transportation and warehouse) connected with ERP to help define composability in supply chain planning. Here you can see where the AI didn’t quite stick to the question. However, the point the chat bot makes is important – systems must work seamlessly together. Composability isn’t integration, another point we’d say ChatGPT didn’t quite nail. Instead, it is about orchestration, modularity, discovery, and autonomy and democratizing technology delivery and giving different users the choice to create new capabilities, products and decisions. We often hear the analogy of Lego bricks and how you can build a masterpiece out of any combination of bricks and know that each brick will ‘snap’ together.

What advice would you share with companies planning for supply chain digital transformation?

ChatGPT said:

Here are a few pieces of advice for companies planning for supply chain digital transformation:

  1. Start with a clear strategy: It is important for companies to have a clear strategy in place for their digital transformation efforts, including specific goals and objectives, a timeline, and a budget.
  2. Engage key stakeholders: It is important to engage key stakeholders, including employees, customers, and suppliers, in the digital transformation process to ensure that their needs and concerns are taken into account.
  3. Focus on data: Supply chain digital transformation relies heavily on data, so it is important for companies to ensure that they have high-quality data and that it is properly structured and maintained.
  4. Choose the right technologies: Companies should carefully evaluate their needs and the capabilities of different technology options before making a decision, and should choose technologies that are scalable, easy to integrate, and supported by reputable vendors.
  5. Plan for change management: Digital transformation can require significant changes to the way that companies operate, which can be challenging for employees. It is important for companies to have a clear plan in place for managing the transition and to provide training and support to help employees adapt.

Our comments:

Pretty impressed with these five pieces of advice from the AI bot and don’t have too much more to add without turning this response into a mini whitepaper! However, the response here is oversimplified. On the topic of strategy, it’s important to mention you must have a goal and outline a clear and agreed-upon strategy by key stakeholders, taking into consideration your supply chain maturity journey – where the company is now and where it wants to be to address challenges and gain agility to quickly pivot as market conditions change. Data is a critical part of any business process change – so much of the world today runs on data and, as they say, garbage in garbage out.

With the proliferation of data and the ability to make data-driven decisions to help remove bias, the right technologies are critical both to support your needs today as well as into the future. Make sure that technology aligns with your vision. Find a vendor that shares your vision and can help make it a reality.

The last point around change management is crucial and goes back to the AI bot’s second point of engaging and aligning with key stakeholders. Change can be hard and you need to ensure everyone is marching to the same beat, heading in the same direction. Spend extra time around this area to help ensure your set up for success.

What supply chain planning software capabilities should companies look for to fully orchestrate the supply chain network?

ChatGPT said:

As companies mature in their supply chain planning, they will need more advanced software capabilities to fully orchestrate their supply chain network. Some capabilities that companies may want to look for include:

  1. Advanced Analytics and Machine Learning: Software that provides advanced analytics and machine learning capabilities to help companies analyze data, predict demand, and optimize various aspects of the supply chain.
  2. Network Design and Optimization: Software that can help design, optimize and plan the entire supply chain network including logistics, production, and inventory to align with the company's goals and objectives.
  3. Advanced Integration: Software that allows for seamless integration across different systems and platforms, including ERP, CRM, and financial systems, to have a holistic view of supply chain operations
  4. Collaboration and communication: Software that provides collaboration tools and a central platform for communication and sharing information with suppliers, customers, and other partners in the supply chain network.
  5. Real-time monitoring and visualization: Software that provides real-time monitoring and visualization of the supply chain network performance and the ability to track inventory, logistics, and production in real-time.
  6. Advanced Risk management: Software that provides risk management capabilities such as monitoring and alerting on supply chain risks and providing what-if scenarios for risk mitigation planning
  7. Digital twin: Software that provides a digital twin of the supply chain network that simulates the performance and allows to test different scenarios and strategies
  8. Automation: Software that automates different parts of the supply chain planning process such as procurement, inventory and logistics management

Our comments:

In addition to specific capabilities, it is important to ask questions to help assess a business’ unique needs, how mature the organization is and where they want a transformative journey to take them. Companies need to recognize specific areas of focus based on their planning maturity journey to support their progression and prioritize the implementation of different capabilities as appropriate.

Take the time to look inward to assess what is working well, what can be improved and what needs a major overhaul. From here you can start to understand what capabilities in a supply chain planning software solution that you need today and what capabilities you’ll need 2, 3 or 5 years from now. Take a read of the eBook, 5 Key Questions to Set Your Supply Chain Planning on the Right Path for a deeper dive into this area.

Conclusion

ChatGPT has garnered a lot of attention from schools worried about students using the system to complete homework to programmers asking the bot to help solve some pretty complex coding challenges. On the supply chain front, its answers are basic – the responses you’d expect. What is the most impressive though is how it delivers conversational answers with a sense of authority. Sometimes the chat bot is spot on – impressive responses. Other times it is off the mark but delivered in a convincing way.

While offering an exciting glimpse of AI applications in supply chain and other sectors, ChatGPT is still in early stages and it’s important to acknowledge its limitations. Understanding that false information can be generated and delivered in a convincing manner means that the information provided by the model should only be used in circumstances when the errors can be judged or corrected by humans. As with everything, we suggest you fact-check what ChatGPT has to say!