[et_pb_section fb_built=”1″ admin_label=”section” _builder_version=”4.16″ global_colors_info=”{}”][et_pb_row admin_label=”row” _builder_version=”4.16″ background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.16″ custom_padding=”|||” global_colors_info=”{}” custom_padding__hover=”|||”][et_pb_text _builder_version=”4.24.0″ _dynamic_attributes=”content” _module_preset=”default” header_font=”|600|||||||” header_font_size=”2.2rem” header_font_size_tablet=”2rem” header_font_size_phone=”1.8rem” header_font_size_last_edited=”on|phone” global_colors_info=”{}”]@ET-DC@eyJkeW5hbWljIjp0cnVlLCJjb250ZW50IjoicG9zdF90aXRsZSIsInNldHRpbmdzIjp7ImJlZm9yZSI6IjxoMT4iLCJhZnRlciI6IjwvaDE+In19@[\/et_pb_text][et_pb_text admin_label=”Text” _builder_version=”4.24.0″ background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}”]<\/p>\n
Clinicians regularly navigate complex, emotional conversations. However, <\/span>opportunities to practice these skills are limited. Traditional training with live <\/span>standardized patients is effective but resource-intensive, requiring significant <\/span>time, cost, and coordination.<\/span><\/p>\n SPARC (Standardized Patient Avatar for Reflective Communication <\/span>Practice) <\/span>offers a new path forward: a virtual, AI-powered patient that enables <\/span>clinicians to practice anytime, anywhere, with instant objective feedback that <\/span>supports ongoing skill development.<\/span><\/p>\n [\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row admin_label=”row” _builder_version=”4.16″ background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.16″ custom_padding=”|||” global_colors_info=”{}” custom_padding__hover=”|||”][et_pb_text admin_label=”Text” _builder_version=”4.24.0″ header_2_font_size=”2rem” background_size=”initial” background_position=”top_left” background_repeat=”repeat” header_2_font_size_tablet=”1.8rem” header_2_font_size_phone=”1.6rem” header_2_font_size_last_edited=”on|desktop” global_colors_info=”{}”]<\/p>\n [\/et_pb_text][et_pb_text admin_label=”Text” _builder_version=”4.24.0″ header_3_text_color=”#294A76″ header_3_font_size=”1.2rem” background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}”]<\/p>\n Planning for SPARC started in July 2025 and work on the project will proceed in the six stages outlined below.<\/p>\n [\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”1_2,1_2″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”1_2″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_text admin_label=”Text” _builder_version=”4.24.0″ header_3_text_color=”#294A76″ header_3_font_size=”1.2rem” background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}”]<\/p>\n [\/et_pb_text][\/et_pb_column][et_pb_column type=”1_2″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_text admin_label=”Text” _builder_version=”4.24.0″ header_3_text_color=”#294A76″ header_3_font_size=”1.2rem” background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}”]<\/p>\n Stage 2: Initial Design & Prototyping (In Progress)<\/b><\/p>\n [\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”1_2,1_2″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”1_2″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_text admin_label=”Text” _builder_version=”4.24.0″ header_3_text_color=”#294A76″ header_3_font_size=”1.2rem” background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}”]<\/p>\n [\/et_pb_text][\/et_pb_column][et_pb_column type=”1_2″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_text admin_label=”Text” _builder_version=”4.24.0″ header_3_text_color=”#294A76″ header_3_font_size=”1.2rem” background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}”]<\/p>\n [\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”1_2,1_2″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”1_2″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_text admin_label=”Text” _builder_version=”4.24.0″ header_3_text_color=”#294A76″ header_3_font_size=”1.2rem” background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}”]<\/p>\n [\/et_pb_text][\/et_pb_column][et_pb_column type=”1_2″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_text admin_label=”Text” _builder_version=”4.24.0″ header_3_text_color=”#294A76″ header_3_font_size=”1.2rem” background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}”]<\/p>\n [\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_text admin_label=”Text” _builder_version=”4.24.0″ background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}”]<\/p>\n [\/et_pb_text][et_pb_text admin_label=”Text” _builder_version=”4.24.0″ background_size=”initial” background_position=”top_left” background_repeat=”repeat” global_colors_info=”{}”]<\/p>\n As you might expect, creating a fully functional AI avatar requires careful orchestration of many systems. The following diagrams outline keys processes used the bring the avatar to life!<\/p>\n [\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”2_3,1_3″ make_equal=”on” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”2_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_image src=”https:\/\/education.ufl.edu\/etc\/files\/2025\/10\/SPARC-P-Agent-Printout_Page_1_Image_0001.jpg” alt=”Diagram showing how a generic multi-agent system interacts with the user.” title_text=”Multi-Agent AI Systems” show_in_lightbox=”on” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_image][\/et_pb_column][et_pb_column type=”1_3″ module_class=”vertical-center” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_text _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n This diagram shows how a multi-agent system typically interacts with the user.<\/p>\n [\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”2_3,1_3″ make_equal=”on” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”2_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_image src=”https:\/\/education.ufl.edu\/etc\/files\/2025\/10\/SPARC-P-Agent-Printout_Page_2_Image_0001.jpg” alt=”Diagram showing AI training document processing” title_text=”Multi-Agent AI Systems” show_in_lightbox=”on” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_image][\/et_pb_column][et_pb_column type=”1_3″ module_class=”vertical-center” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_text _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n Documents used to train the AI model may contain sensitive information and must be processed. All curated files are converted to text, and then they are then fed to a helper application that removes personally identifiable information.<\/p>\n [\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”2_3,1_3″ make_equal=”on” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”2_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_image src=”https:\/\/education.ufl.edu\/etc\/files\/2025\/10\/SPARC-P-Agent-Printout_Page_3_Image_0001.jpg” alt=”Diagram showing how text documents are converted to JSON and then embedded into a vector database using LangChain and Chroma.” title_text=”Multi-Agent AI Systems” show_in_lightbox=”on” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_image][\/et_pb_column][et_pb_column type=”1_3″ module_class=”vertical-center” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_text _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n Our AI model uses a special multi-dimensional index called a vector database. This vector database is used to identify patterns within data set that will be useful when processing and generating responses.<\/p>\n In our case, we take the text documents processed in the previous step and convert it into JSON. From there, specialized programs called LangChain and Chroma will generate the vector database.<\/p>\n <\/p>\n [\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”2_3,1_3″ make_equal=”on” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”2_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_image src=”https:\/\/education.ufl.edu\/etc\/files\/2025\/10\/SPARC-P-Agent-Printout_Page_4_Image_0001.jpg” alt=”Digram showing how vector database is combined with an open-source LLM into a single knowledgebase which is then used to train each agent.” title_text=”SPARC-P Agent Printout_Page_4_Image_0001″ show_in_lightbox=”on” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_image][\/et_pb_column][et_pb_column type=”1_3″ module_class=”vertical-center” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_text _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n Large Language Models such Open AI’s GPT or Meta’s LLaMA have been designed to create natural sounding text output. When combined with the specialized vector database, the result is a specialized AI model able to respond from a particular point of view.\u00a0\u00a0<\/p>\n <\/p>\n [\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”2_3,1_3″ make_equal=”on” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”2_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_image src=”https:\/\/education.ufl.edu\/etc\/files\/2025\/10\/SPARC-P-Agent-Printout_Page_5_Image_0001.jpg” alt=”Diagram showing how the parent avatar is created.” title_text=”Multi-Agent AI Systems” show_in_lightbox=”on” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_image][\/et_pb_column][et_pb_column type=”1_3″ module_class=”vertical-center” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_text _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n This diagram shows how the parent avatar is created. The process uses mesh tools like Blender which are fed to Character Creator 4 to create a visual representation of the character.<\/p>\n Voiceover audio is fed into NVIDIA’s Audio2Face tool to generate the animation required for facial motions when speaking. The character and animation then get fed into iClone 8 to refine the animation. The Animated Character can then be exported for use on the frontend.<\/p>\n [\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”2_3,1_3″ make_equal=”on” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”2_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_image src=”https:\/\/education.ufl.edu\/etc\/files\/2025\/10\/SPARC-P-Agent-Printout_Page_6_Image_0001.jpg” alt=”Diagram showing how the avatar character interacts with the backend and enduser. ” title_text=”SPARC-P Agent Printout_Page_6_Image_0001″ show_in_lightbox=”on” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_image][\/et_pb_column][et_pb_column type=”1_3″ module_class=”vertical-center” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_text _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n With the data now in place, the AI avatar is ready to interact with users. This diagram shows how the user input from their microphone is translated into a text format which can then interact with the rest of the AI model. In the end, the avatar’s audio and visuals are sent back to the user.<\/p>\n [\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”2_3,1_3″ make_equal=”on” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”2_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_image src=”https:\/\/education.ufl.edu\/etc\/files\/2025\/10\/SPARC-P-Agent-Printout_Page_8_Image_0001.jpg” alt=”Diagram showing the interaction of components powering the AI avatar. Based on NVIDIA’s Digital Human Blueprint.” show_in_lightbox=”on” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_image][et_pb_image src=”https:\/\/education.ufl.edu\/etc\/files\/2025\/10\/SPARC-P-Agent-Printout_Page_7_Image_0001.jpg” alt=”Diagram showing what happens on the backend hosted on HiPerGator. When the user speaks, his words are transcribed using NVIDIA Riva. Next, they are filtered to remove inappropriate or dangerous content and sent to the supervisor agent. ” title_text=”SPARC-P Agent Printout_Page_6_Image_0001″ show_in_lightbox=”on” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_image][\/et_pb_column][et_pb_column type=”1_3″ module_class=”vertical-center” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_text _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n As new responses come in from the user, the HiPer Gator supercomputer goes to work! New input is filtered for safety and fed to the supervisor agent. The supervisor agent passes this data on to the parent and coach models.\u00a0<\/p>\n The parent model generates a response, and then it feeds it back to the supervisor agent. The supervisor then feeds that text into the the animation engine that calculates the animation needed for the text that be said by the avatar. This info gets passed back to the frontend.<\/p>\n The first chart shows an overview of the entire process for generating the interactive character. The second chart shows the specific implementation of backend on housed on HiPer Gator.<\/p>\n <\/p>\n [\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”2_3,1_3″ make_equal=”on” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”2_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_image src=”https:\/\/education.ufl.edu\/etc\/files\/2025\/10\/SPARC-P-Agent-Printout_Page_9_Image_0002.jpg” alt=”Diagram showing how the user’s voice is converted to text that can be processed and how the AI uses the service to produce audio responses.” title_text=”SPARC-P Agent Printout_Page_6_Image_0001″ show_in_lightbox=”on” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_image][\/et_pb_column][et_pb_column type=”1_3″ module_class=”vertical-center” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_text _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n The AI Avatar will depend on RIVA AI Services to handle audio processing. As the user speaks the microphone signal is converted to text by automatic speech recognition (ASR). This text gets back to HiPer Gator to be processed by the Supervisor Agent. Think of this as how the AI agent “listens.”<\/p>\n RIVA also handles converting messages from the supervisor agent into audible speech. This process is essentially the reverse of the “listening” process. RIVA receives text data from the supervisor agent about what to say. This text gets run through a text to speech (TTS) engine to produce the audio output. This is sent to the supervisor agent to sync the audio with the animation before being delivered to the user.<\/p>\n [\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row _builder_version=”4.24.0″ _module_preset=”default”][et_pb_column _builder_version=”4.24.0″ _module_preset=”default” type=”4_4″][et_pb_image src=”https:\/\/education.ufl.edu\/etc\/files\/2025\/11\/25_AI-Days-Poster_SPARC-1400.jpg” _builder_version=”4.24.0″ _module_preset=”default” hover_enabled=”0″ sticky_enabled=”0″ alt=”Poster presented at AI Days for SPARC Project” title_text=”25_AI-Days-Poster_SPARC-1400″ show_in_lightbox=”on”][\/et_pb_image][et_pb_button button_text=”Download Poster” _builder_version=”4.24.0″ _module_preset=”default” button_url=”@ET-DC@eyJkeW5hbWljIjp0cnVlLCJjb250ZW50IjoicG9zdF9saW5rX3VybF9hdHRhY2htZW50Iiwic2V0dGluZ3MiOnsicG9zdF9pZCI6IjcxODAifX0=@” _dynamic_attributes=”button_url” url_new_window=”on” hover_enabled=”0″ sticky_enabled=”0″][\/et_pb_button][\/et_pb_column][\/et_pb_row][et_pb_row _builder_version=”4.24.0″ _module_preset=”default” custom_margin=”||0px||false|false” custom_padding=”||0px||false|false” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_text admin_label=”Text” _builder_version=”4.24.0″ header_2_font_size=”2rem” background_size=”initial” background_position=”top_left” background_repeat=”repeat” header_2_font_size_tablet=”1.8rem” header_2_font_size_phone=”1.8rem” header_2_font_size_last_edited=”on|tablet” global_colors_info=”{}”]<\/p>\n [\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”1_3,1_3,1_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”1_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_team_member name=”Carma Bylund, Ph.D.” position=”Co-Principal Investigator” image_url=”https:\/\/education.ufl.edu\/etc\/files\/2025\/10\/Carma-Bylund.jpeg” _builder_version=”4.24.0″ _module_preset=”default” header_level=”h3″ global_colors_info=”{}”]<\/p>\n Dr. Bylund is a\u00a0 Professor and Associate Chair of Education in the Department of Health Outcomes & Biomedical Informatics (HOBI) and the Assistant Director of the Cancer Training and Education Program at the UF Health Cancer Center (UFHCC). As an implementation scientist, her research focuses on communication interventions for clinicians, patients, and caregivers. <\/span><\/p>\n [\/et_pb_team_member][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_team_member name=”Jason Arnold, Ed.D.” position=”Co-Principal Investigator” image_url=”https:\/\/education.ufl.edu\/etc\/files\/2023\/09\/jason-reg.jpg” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n As the Director of E-Learning, Technology, and Communications\u2014and serving as the Senior Communicator for the College of Education\u2014Dr. Arnold leads a diverse team comprised of instructional designers, online student services support, web designers, software and database programmers, videographers\/editors, and graphic designers to support teaching and learning and advance the mission of the college and university.<\/p>\n <\/p>\n [\/et_pb_team_member][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_team_member name=”Stephanie Staras, Ph.D.” position=”Co-Principal Investigator” image_url=”https:\/\/education.ufl.edu\/etc\/files\/2025\/10\/stephanie-staras.jpg” _builder_version=”4.24.0″ _module_preset=”default” header_level=”h3″ global_colors_info=”{}”]<\/p>\n Stephanie A. S. Staras, M.S.P.H., Ph.D., is a professor and Associate Chair for Faculty Development in the Department of Health Outcomes and Biomedical Informatics. She is also the Associate Director of the Institute for Child Health Policy and co-lead for the UFHealth Cancer Center\u2019s Cancer Control and Population Science Program.<\/span><\/p>\n [\/et_pb_team_member][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”1_3,1_3,1_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”1_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_team_member name=”Macy Geiger, Ed.D.” position=”Learning Experience Designer” image_url=”https:\/\/education.ufl.edu\/etc\/files\/2025\/01\/macy-reg.jpg” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_team_member][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_team_member name=”Jay Rosen” position=”AI Engineer and Lead Developer” image_url=”https:\/\/education.ufl.edu\/etc\/files\/2024\/08\/jay-reg.png” _builder_version=”4.24.0″ _module_preset=”default” header_level=”h3″ global_colors_info=”{}”][\/et_pb_team_member][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_team_member name=”Kennan DeGruccio, LSW” position=”Learning Experience Designer” image_url=”https:\/\/education.ufl.edu\/etc\/files\/2025\/11\/kennan-DeGruccio.jpg” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_team_member][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”1_3,1_3,1_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”1_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_team_member name=”Kayla Sharp, MSM” position=”Project Manager” image_url=”https:\/\/education.ufl.edu\/etc\/files\/2024\/08\/kayla-reg.jpg” _builder_version=”4.24.0″ _module_preset=”default” header_level=”h3″ global_colors_info=”{}”][\/et_pb_team_member][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_team_member name=”Rachel West” position=”3D Modeling” image_url=”https:\/\/education.ufl.edu\/etc\/files\/2024\/08\/rachel-reg.png” _builder_version=”4.24.0″ _module_preset=”default” header_level=”h3″ global_colors_info=”{}”][\/et_pb_team_member][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_team_member name=”Eve Kung” position=”Front End Web Development” image_url=”https:\/\/education.ufl.edu\/etc\/files\/2024\/08\/eve-reg.png” _builder_version=”4.24.0″ _module_preset=”default” header_level=”h3″ global_colors_info=”{}”][\/et_pb_team_member][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”1_3,1_3,1_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_column type=”1_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][et_pb_team_member name=”Jonathan Walker” position=”Web Development” image_url=”https:\/\/education.ufl.edu\/etc\/files\/2025\/02\/jon-reg.png” _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n <\/p>\n <\/p>\n [\/et_pb_team_member][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”4.24.0″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_column][\/et_pb_row][\/et_pb_section]<\/p>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":77,"featured_media":0,"comment_status":"open","ping_status":"closed","template":"","meta":{"_et_pb_use_builder":"on","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"project_category":[],"project_tag":[],"class_list":["post-7131","project","type-project","status-publish","hentry"],"yoast_head":"\nProject Timeline<\/h2>\n
Stage 1: Planning & Onboarding (Complete)<\/b><\/h3>\n
\n
<\/span><\/span><\/li>\n
<\/span><\/span><\/li>\n\n
<\/span><\/span><\/li>\n
<\/span><\/span><\/li>\n
<\/span><\/span><\/li>\nStage 3: Alpha Build Development<\/b><\/h3>\n
\n
<\/span><\/span><\/li>\n
<\/span><\/span><\/li>\n
<\/span><\/span><\/li>\nStage 4: Internal Testing & Risk Review<\/b><\/h3>\n
\n
<\/span><\/span><\/li>\n
<\/span><\/span><\/li>\n
<\/span><\/span><\/li>\nStage 5: Refinement & User Simulation<\/b>
<\/span><\/span><\/h3>\n\n
<\/span><\/span><\/li>\n
<\/span><\/span><\/li>\n
<\/span><\/span><\/li>\nStage 6: Finalization & Reporting<\/b>
<\/span><\/span><\/h3>\n\n
<\/span><\/span><\/li>\n
<\/span><\/span><\/li>\n
<\/span><\/li>\n
<\/span><\/span><\/li>\n
<\/span><\/li>\n<\/ul>\nTechnical Details<\/h2>\n
Multi-Agent AI<\/h3>\n
Processing the Training Documents<\/h3>\n
Create a Specialized Index<\/h3>\n
Combine Vector Database with an Open Source LLM<\/h3>\n
Creating the Avatar<\/h3>\n
User Interactions With the AI Avatar<\/h3>\n
HiPer Gator Processes Incoming and Outgoing Data<\/h3>\n
Processing AI Avatar Audio<\/h3>\n
Meet the Team<\/h2>\n