TeamWise: Exploring Virtually Embodied AI Facilitation for Video-Based Team Onboarding

Obilisetty, V., Elleby, M., Tang, A., and Wang, A. (2026). TeamWise: Exploring Virtually Embodied AI Facilitation for Video-Based Team Onboarding. In Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems (CHI EA '26).

Abstract

AI-mediated facilitation has emerged as a scalable approach to supporting onboarding and coordination in newly formed remote teams, yet existing systems are predominantly text-based. To explore how video-based, virtually embodied AI facilitators shape team experiences, we present TeamWise, which joins video-based onboarding meetings as an on-screen avatar. TeamWise guides teams through a structured facilitation flow of low-stakes activities to foster rapport, mutual awareness, and shared identity. While the overall sequence of activities and facilitation goals is predefined, the facilitator's turn-by-turn utterances are generated dynamically by an LLM in response to participant input. We conducted a formative study of TeamWise to refine the facilitator's design and interaction flow. We outline the design and protocol of a planned full-scale study comparing visual and voice-based AI onboarding that focuses on how and when embodiment influences early team interactions.

Materials

URL (https://doi.org/10.1145/3772363.3798791)
DOI (https://doi.org/10.1145/3772363.3798791)

BibTeX

@inproceedings{obilisetty2026teamwise,
  abstract = {AI-mediated facilitation has emerged as a scalable approach to supporting onboarding and coordination in newly formed remote teams, yet existing systems are predominantly text-based. To explore how video-based, virtually embodied AI facilitators shape team experiences, we present TeamWise, which joins video-based onboarding meetings as an on-screen avatar. TeamWise guides teams through a structured facilitation flow of low-stakes activities to foster rapport, mutual awareness, and shared identity. While the overall sequence of activities and facilitation goals is predefined, the facilitator's turn-by-turn utterances are generated dynamically by an LLM in response to participant input. We conducted a formative study of TeamWise to refine the facilitator's design and interaction flow. We outline the design and protocol of a planned full-scale study comparing visual and voice-based AI onboarding that focuses on how and when embodiment influences early team interactions.},
  type = {poster},
  url = {https://doi.org/10.1145/3772363.3798791},
  doi = {10.1145/3772363.3798791},
  publisher = {ACM},
  address = {Barcelona, Spain},
  year = {2026},
  booktitle = {Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems (CHI EA '26)},
  title = {TeamWise: Exploring Virtually Embodied AI Facilitation for Video-Based Team Onboarding},
  author = {Obilisetty, Venkata Akhila Rani and Elleby, Mikkeline and Tang, Anthony and Wang, April Yi},
}