Artificial Intelligence for Product Managers: Empowering Dog Parents
By Phil Geist
This past Spring, Professor Catherine Fang taught the course "Artificial Intelligence for Product Managers." The course focused on the principles and practices of artificial intelligence (AI). Students learned about unlocking the value of data and how it has the potential to transform businesses and, ultimately, human experiences. Students gain hands-on experience and learn how to apply AI concepts to solve real-world problems through a group project.
Two students, Sangeeta Yadav and Young Yoon, tackled the real-world challenge of improving health care for dogs. Their aim is to empower dog owners through the creation of an AI-powered conversational chatbot that offers personalized, AI-driven health insights. You can learn more about their project journey by reading the interview below.
General Questions
Specific Process Inquiries
Outcome & Impact
Reflection & Learning
Technical Questions
Future Directions
General Questions
Four Paws is an AI-powered conversational chatbot that provides personalized insights for managing the health of dogs.iii:
Can you provide a brief overview of your project and what inspired you to select the topic you chose?
Four Paws: [Sangeeta Yadav]
I have loved dogs since childhood and my family had two dogs that passed away a few years ago. I also witnessed friends struggle to manage their dogs’ health and that experience motivated me to dive deeper into this topic.
iii:
Is there a motivation as to why your group is interested in advancing dog’s healthcare?
Four Paws: [Sangeeta Yadav]
After interviewing a number of dog parents, shelter staff, and pet health insurance professionals we discovered that a pain point was receiving timely and cost-effective assistance when a dog gets sick. This issue is largely driven by unaffordable health care costs and limited access to veterinarians in times of need.
iii:
What is the goal of your project?
Four Paws: [Sangeeta Yadav]
Our goal is to empower dog parents with personalized health insights and timely guidance for proactive dog care.
iii:
Essentially your tool empowers dog parents to love their dogs more fully—by helping them understand what is going on with their health. Can you provide more details about your conversational chatbot?
Four Paws: [Sangeeta Yadav]
We created a web-based, AI-powered conversational chatbot to mimic how a dog parent observes early symptoms and guides them through a series of questions to determine the severity of their dog’s symptoms. The chatbot then provides recommendations and resource links from accredited veterinary organizations.
iii:
What is your long term vision for this project?
Four Paws: [Sangeeta Yadav]
Our vision is to develop a comprehensive solution dog parents can trust that helps them analyze health symptoms and track health patterns over time. It is our goal that the platform will manage all health conditions and offer options to connect with the nearest vet.
Young Yoon
MSSM '24
Specific Process Inquiries
The biggest challenge was focusing too much on AI technology rather than the problem itself.iii:
What were the biggest challenges you faced while developing your project?
Four Paws: [Sangeeta Yadav]
One of the main challenges was to think about the problem first and then try and come up with a solution. Since we developed this project in an AI class, we were originally too excited about the potential of what this technology is capable of. Because of our initial excitement, we spent some time doing it all wrong and learned lessons from our first batch of initial failed solutions.
iii:
Can you tell me about what the collaboration process was like between the two of you? How often did you meet? How long was each meeting usually? How did you divide and conquer the specific tasks of your project?
Four Paws: [Sangeeta Yadav]
Young and I have known each other for the past two years and have worked well together in the past. For this project we met a couple of times each week for one to two hours. I took on the market and user research, UX design, and other product/ business specific tasks. Young took on setting up AWS and development tasks including working on comparisons between OpenAI and Amazon Titan.
Outcome & Impact
The target audience for FourPaws is made up of dog owners who make infrequent visits to the vet or lack access to pet health insurance.iii:
What were the key findings or results of your project? Were there any unexpected results? If so, what were they and how did you address them?
Four Paws: [Sangeeta Yadav]
Market watch reported that over 30% of pet owners avoid taking their dogs to the vet due to high costs. In our user research, 80% of the folks didn’t have pet insurance and most dog parents only take their dogs to the vet when they find out something serious is going on. How can someone classify whether or not their dog’s condition is serious?
Our goal is not to replace veterinarians, but instead to provide a trusted platform that guides and directs dog parents who may not have pet health insurance. We hope to give these dog parents better guidance to make informed decisions and actually encourage them to take their dog to the vet when their findings indicate that their dog may be dealing with a more serious condition.
iii:
I see your platform as a tool that educates the novice dog owner who may be single or not have a community to bounce ideas off of. What would you say is the target audience for your project?
Four Paws: [Young Yoon]
Our target audience is novice dog owners who may be single or lack a large dog community to consult. Usually these folks don’t have access to pet health insurance or make frequent visits to the vet. They only take their dogs to the vet when they witness serious issues or encounter emergency situations. It is our hope that our platform provides guidance that dog parents can trust instead of relying on hours of mindless online searches.
Reflection and Learning
The FourPaws team learned about the limitations of AI and they addressed those issues by integrating Google Search API. The conversational chatbot aims to aid, not replace veterinary care.iii:
In terms of AI from a technical perspective, what is something new that you learned?
Four Paws: [Young Yoon]
Sangeeta and I have learned a lot about what AI can and can’t do. This was especially relevant in reducing mistakes and keeping our information accurate. We discovered some limitations of AI. Sometimes the AI provided broken links to vet care resources and websites. To fix this, we had to develop a solution that integrated with the Google Search API to ensure the URLs are correct and up-to-date.
iii:
So far you’ve told me what your project is—can you tell me what you project isn’t?
Four Paws: [Young Yoon]
Our project is not a replacement for veterinary care. It’s specifically focused on dogs, not other pets like cats.
iii:
Managing veterinary office ratings could turn into quite the quagmire–what solution have you adapted to avoid that tedious task?
Four Paws: [Young Yoon]
Actually, as of now, the rating we provide along with the map comes directly from Google star ratings. Yes, we understand that managing veterinary office ratings ourselves could become a complex and contentious task.
Technical Questions
This project influenced the views of the FourPaws team and how they can use AI capabilities for meaningful purposes.iii:
How has this project influenced your academic or career goals? Do you look at anything differently with a new perspective since completing the project for class?
Four Paws: [Sangeeta Yadav]
This project was very impactful for us, as dogs play a central role in our lives and society as a whole. We took on a serious problem that can have a huge impact on millions of dogs and dog parents, since so much time and energy is spent on taking care of our furry family members. By going through the process of problem discovery and understanding the pain points of dog parents–we became more committed to solving their issues. This project also shifted our views on how we view AI, since it initially can be seen as a fun tool, but we deeply admired how it can also be outfitted for meaningful purposes if used properly.
iii:
Can you explain a particularly complex aspect of your project. What tools or technologies did you use, and why did you choose them?
Four Paws: [Young Yoon]
One particularly complex aspect of our project was integrating AI with instructional prompt engineering. This was crucial to ensure that the AI could ask the right questions and guide dog owners effectively to provide the right feedback. This process helps the AI reach a symptom-based conclusion accurately and effectively. After multiple test rounds, we ended up choosing OpenAI’s GPT-3.5 as a default generative AI model for its great context recognition capabilities and natural language processing power we could get at low cost.
iii:
From a technical perspective, what were the main differences between ChatGPT models 4 and 3.5?
Four Paws: [Young Yoon]
The main differences between GPT-4 and GPT-3.5 lie in their capabilities, accuracy, and features. GPT-4 is more advanced, offering improved handling of nuanced language, greater contextual understanding, and the ability to generate more accurate and reliable responses. It also supports multimodality, meaning that it can process both text and images, which is a significant upgrade over GPT-3.5.
Future Directions
The dream of the FourPaws team is to create a mobile app for dog parents to track and analyze their dogs' health and provide insights based on comprehensive data and comparisons.iii:
If time and resources were of no issue and you had unlimited resources at your disposal—what would your dream for this project be?
Four Paws: [Sangeeta Yadav]
We are thinking of a mobile app in which a dog parent can create their dog profile, add key information about their dog such as breed, age, weight, any pre-existing condition or concerns, zip code etc. Dog parents can start by asking questions in symptom analysis and as we add more dogs and data to the platform we hope to provide insights on overall health performance based on benchmarking factors like breed, age, and weight.
iii:
Dogs are often thought of and referred to as “man’s best friend.” Over the course of this project – was there anything that made you think differently that you’d like to share?
Four Paws: [Sangeeta Yadav]
Throughout this project, our love for dogs has only deepened, especially when talking with dog owners who all corrected me to say "dog parents" or referred to their dogs as their children. This shift in perspective highlights how integral dogs are to our families and underscores the profound bond we share with them. Dogs bring out the best in us and the way dogs foster connections between people is truly remarkable.