Generative AI Summaries
Designing LLM-Based Summaries for Homelessness Caseworkers

Overview
Context
-
The City of Austin strives to assist people experiencing homelessness by running a case management service.
-
Caseworkers, who are clinical professionals, handle numerous clients, recording vital information in free-text case notes for decision-making.
-
This work aims to improve caseworker efficiency in referencing client information from the large corpus of text using technology.
My Role
Duration
8 months (Jul 2022 - Feb 2023)
-
Analyzed case notes using statistical and qualitative methods.
-
Designed and conducted user interviews and co-design sessions.
-
Brainstormed design opportunities with the cross-functional team.
Tools
Zoom, Excel, Python.
Team
Team of 4 researchers and data scientists.
Process
.png)
Research
Goal
-
Identify opportunities to build tools for caseworkers to effectively utilize case notes.
-
Inform the design of effective and responsible AI tools.
Data Analysis
​What information do casenotes representing caseworker-client interactions constitute?
The organization provided an extensive corpus of case notes, serving as a valuable resource to comprehend caseworker-client interactions and case note-writing practices.
​
How to make sense of the content though? There are 50,000 case notes!​
Statistical Analysis
Descriptive statistics, topic modeling and clustering to identify patterns based on temporal, demographic and case attributes.
Qualitative Coding
Iterative analysis of representative case notes sampled from clustering.
​