ARIZONA WATERBOT
AI-powered water assistant built to simplify access to trustworthy water information for Arizona residents
Overview
The Arizona Water Chatbot was developed to provide residents with accurate, timely, and relevant information about water usage, conservation, and regulations. This project involved researching conversational experiences and user interfaces, followed by creating a custom GPT-based chatbot using OpenAI's technology.
Impact
The Arizona Water Chatbot provided precise, easy-to-understand information tailored to the user's knowledge level, enhancing accessibility and relevance for both novice and expert users. This improved community engagement and informed water usage decisions.
Context and Need
Arizona residents often struggle to find accurate, timely, and relevant information about water usage, conservation, and regulations. This lack of accessible information leads to confusion and inefficient water use, underscoring the need for a reliable, user-friendly solution to provide essential water-related information.
Analyzing the competition
To design the Arizona Water Chatbot, an analysis of similar websites was conducted to understand effective information presentation.
Coding Interview Responses
The data was analyzed using a bottom up approach where we organized our findings into groups and then labeled them. We analyzed the “think-aloud” responses that we received from all the participants.
User expectations from a chatbot
User interviews were conducted to gain a deep understanding of users' information seeking behaviors.
"I currently use Google"
Google's Strength — Broad Information Access
Users appreciated Google for its efficiency in providing a broad overview of water-related information. They found it reliable for general queries, highlighting its role as a valuable starting point.
Identified Gap — Locating Specific Local Information
When seeking detailed information specific to their locality, such as updates from the city's water department, users encountered difficulties. This gap points to the potential benefit of a dedicated tool that simplifies access to localized water information.
The "faceless" user persona
This section introduces a 'faceless' persona to guide the chatbot’s development, focusing on user behaviors and needs while avoiding stereotypes. It provides an overview of the users' motivations, goals, technical abilities, and challenges in finding water-related information, informing the chatbot's design to better meet such users' needs.
Testing the Arizona Water Chatbot — Interpretation of chatbot's responses
Positive Interpretations
Features that were well-received and positively impacted the user experience.
04
Negative Interpretations
Areas where features did not meet expectations or hindered user satisfaction.
10
Participant Suggestions
Insights and recommendations provided by users for future improvements.
12
Pivoting to building a Custom GPT
— GPTs by OpenAI
For the next stage of the project, I proceeded to develop a custom GPT — Arizona Aqua Advsior with the same instructions given to the already existing water chatbot.
