AI-enhanced search & chatbot (2024)

This project centered on analyzing the integration of an AI assistant in search, and the transition experience to the chatbot. I needed to identify the delta between OCI's intent recognition and intelligence of the response, versus a user's expectations. We also wanted to understand where the most fitting location for in-depth answers belonged compared to quick results, and how users mentally distinguished and behaved depending on the two. My role as a researcher on this project was to analyze the effectiveness of our new AI-in-search component and strategy.

read case study

Screenshot of a search panel showing available OCI services and a Ask Oracle gen AI option at the bottom.

Screenshot of the GenAI results. The text reads: All users saw the Oracle Assistant button and correctly assumed this would continue the conversation. None of the users wanted to be moved there automatically - they want to click into the Assistant to engage with it. When in the chatbot, participants still want to keep their current page under the chat, but carry over the content of their search/question. It is alright to change the experience between the search and the dropdown based on the intent we detect, but the core answer should be the same. What can change is the level or depth of information - all users expect direct links and information from the search, and more thorough results, additional information, and automated tasks from the chatbot.

AI exploratory survey (2023)

The OCI UX Design team was charged with creating a support chatbot to improve the Oracle Cloud user experience, while also building chat-style responses into global search. To ensure we were providing the optimal experience and integrating AI in a thoughtful, scalable way, the research team was brought in to explore general user attitudes around AI assistance throughout the console and in a chatbot. To achieve this we launched a 300-response survey and analysed the themes.

read case study

A screenshot of AI exploration survey results. The text reads: "Based on shifting expectations spurred by the rise of ChatGPT, users have new ideas for where assistance should be found… Participants expect to find AI integrated into pathways where users might need recommendations to increase efficiency. When asked to rank where they expected to find assistance, participants noted:
search, chat, and workflow initiation. "

Resource Limits (2024)

Cloud platform resources are restricted, or limited, for a variety of reasons. OCI operators must establish limits according to their capacity and finances. Limits as an OCI service has many complications. This project reviews the OCI limit process end to end to identify pain points and present suggestions to alleviate them, covering both platform and workflow issues. To achieve this, I interviewed limit experts & operators, and analyzed the limit process from initial request to final approval, from the experience of a product manager, ticket engineer, and external users.

This page is still under construction. Please check back in a few days.

Source Code Management (2024)

This research project centered around auditing the migration of engineers to a new code repository and management tool, and reviewing the usability of the tool itself. This was achieved through user interviews and contextual inquiries, functionality audits, and feature comparisons. The result was a list of issues and their associated recommendations.

This page is still under construction. Please check back in a few days.