The building world is full of devices generating data with building operations creating more data and all that is fed to the AI. As of now, it’s all been training data for machine learning to create AI for energy optimization and optimized building management with the promise of personalization. With generative AI comes the promise of chatting AI, or AI that generates visual images, but those also need data to be fed by companies. It’s in the early stages, and we haven’t gotten the tools to feed our building data to generative AI. I believe generative AI is calling for our imagination to produce cases where we could utilize such an AI.

In the past, we’ve compared autonomous vehicles to autonomous buildings, which left us aspiring for personalization in the building with an autonomous AI. 

What would such an approach to AI do for buildings? ChatGPT3 is showing us a Q&A interface mimicking humans and engaging us in conversation. What would such a chatbot do for a building?

I did an exercise about this for students seeking masters’ degrees in UX to design an AI user interface for ChatGPT for hospital stakeholders. We can extend that to an office building, apartment, or airport. It goes back to your vision of personalization AI for people in the building. My conversation with a ChatGPT3 building would be different from yours. The same goes for our customers, realtors, and building managers.

Read about the generative AI models and what is the evolving ecosystem and business model shifts and opportunities. The book “Generative AI: A Primer for Product and Business Managers” is ready for pre-order on Amazon.

I asked ChatGPT, and here’s our conversation below. Enjoy!


== Below this is a conversation generated by ChatGPT ==


Sudha: Can ChatGPT be used in automated buildings?

ChatGPT: Yes, ChatGPT can be used in automated buildings as a conversational interface for controlling various systems and devices, such as lighting, temperature, security, and entertainment. For example, a user can interact with a chatbot powered by ChatGPT to request changes to the lighting or temperature in a room or to get information about the current status of the building’s systems. The chatbot can then interact with the building’s automation system to carry out the requested actions.


Sudha: What is unique about ChatGPT instead of a traditional chatbot in this case?

ChatGPT: ChatGPT is a state-of-the-art language generation model developed by OpenAI, which sets it apart from traditional chatbots in several ways:

  1. Natural language understanding: ChatGPT has been trained on vast amounts of text data and has the ability to understand and generate human-like text. This makes it capable of handling complex and varied user requests in a more natural and human-like manner.
  2. Contextual awareness: ChatGPT has a contextual awareness mechanism that allows it to maintain a conversation state and keep track of previous interactions. This allows it to provide more personalized and relevant responses to users.
  3. Generative model: Unlike rule-based chatbots, ChatGPT is a generative model that can generate text based on the input it receives. This allows it to generate unique and appropriate responses to a wide range of user requests

In summary, the advanced natural language processing capabilities and contextual awareness of ChatGPT make it a powerful tool for building advanced conversational interfaces in automated buildings.


Sudha: Can you tell me a unique use case where ChatGPT can help in helping a customer of an automated building?

ChatGPT: Sure, here’s a unique use case for ChatGPT in an automated building: Imagine a customer of the building is having a party in one of the conference rooms. They want to change the lighting and temperature to create a specific ambiance for the party. Instead of manually controlling the lights and temperature, the customer can use a conversational interface powered by ChatGPT to make these changes. The customer can simply send a text message or voice command to the chatbot, specifying the desired lighting and temperature settings. ChatGPT can then generate an appropriate response, confirm the changes, and interact with the building’s automation system to carry out the requested actions.

This use case demonstrates how ChatGPT can provide a convenient and intuitive interface for controlling various systems and devices in an automated building, enabling customers to easily customize their environment and enhance their experience.


Sudha: We can do that with Alexa talking to thermostats today, what’s unique about ChatGPT?

ChatGPT: While Alexa can control thermostats, the uniqueness of ChatGPT lies in its ability to handle a much wider range of tasks and provide a more human-like conversational experience.

ChatGPT can be integrated with various systems and devices in an automated building, not just thermostats. It can handle a wide range of requests and provide information about different systems in the building, such as lighting, security, entertainment, and more.

Additionally, ChatGPT has been trained on vast amounts of text data and has the ability to understand and generate human-like text. This enables it to handle complex and varied user requests in a more natural and intuitive way, providing a seamless conversational experience.

 

== Conversation by ChatGPT ==

 

In summary, while Alexa is a powerful tool for controlling specific systems in an automated building, ChatGPT offers a more comprehensive, human-like, and conversational interface for controlling a wider range of systems and devices, enabling customers to easily customize their environment and enhance their experience.

Editor’s Note: This article originally appeared on www.automatedbuildings.com. See the original article in its entirety at https://www.automatedbuildings.com/2023/02/09/imagining-generative-ai-in-the-automated-building-world.