The burgeoning complexity of tasks that AI agents are expected to perform necessitates a robust framework for managing work states. Traditionally, AI agents have focused on the execution of static tasks without a continuous reflective process on their work state. This limits the agents' ability to manage complex, evolving tasks that require adaptability and nuanced understanding of progress at any given moment. Recognizing the importance of dynamic task management, we introduce a novel AI agent model centered around an explicit work state. The work state captures the entirety of the agent's operational status and provides a medium for recording task evolution-from high-level planning to execution and eventual completion. This state is articulated through "work notes," a concept inspired 1

Most research studying social determinants of health (SDoH) has focused on physician notes or structured elements of the electronic medical record (EMR). We hypothesize that clinical notes from social workers, whose role is to ameliorate social and economic factors, might provide a richer source of data on SDoH. We sought to perform topic modeling to identify robust topics of discussion within a large cohort of social work notes. We retrieved a diverse, deidentified corpus of 0.95 million clinical social work notes from 181,644 patients at the University of California, San Francisco. We used word frequency analysis and Latent Dirichlet Allocation (LDA) topic modeling analysis to characterize this corpus and identify potential topics of discussion. Word frequency analysis identified both medical and non-medical terms associated with specific ICD10 chapters. The LDA topic modeling analysis extracted 11 topics related to social determinants of health risk factors including financial status, abuse history, social support, risk of death, and mental health. In addition, the topic modeling approach captured the variation between different types of social work notes and across patients with different types of diseases or conditions. We demonstrated that social work notes contain rich, unique, and otherwise unobtainable information on an individual's SDoH.