Botender: Supporting Communities in Collaboratively Designing AI Agents through Case-Based Provocations
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914317226475520 |
|---|---|
| author | Kuo, Tzu-Sheng Liu, Sophia Chen, Quan Ze Seering, Joseph Zhang, Amy X. Zhu, Haiyi Holstein, Kenneth |
| author_facet | Kuo, Tzu-Sheng Liu, Sophia Chen, Quan Ze Seering, Joseph Zhang, Amy X. Zhu, Haiyi Holstein, Kenneth |
| contents | AI agents, or bots, serve important roles in online communities. However, they are often designed by outsiders or a few tech-savvy members, leading to bots that may not align with the broader community's needs. How might communities collectively shape the behavior of community bots? We present Botender, a system that enables communities to collaboratively design LLM-powered bots without coding. With Botender, community members can directly propose, iterate on, and deploy custom bot behaviors tailored to community needs. Botender facilitates testing and iteration on bot behavior through case-based provocations: interaction scenarios generated to spark user reflection and discussion around desirable bot behavior. A validation study found these provocations more useful than standard test cases for revealing improvement opportunities and surfacing disagreements. During a five-day deployment across six Discord servers, Botender supported communities in tailoring bot behavior to their specific needs, showcasing the usefulness of case-based provocations in facilitating collaborative bot design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25492 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Botender: Supporting Communities in Collaboratively Designing AI Agents through Case-Based Provocations Kuo, Tzu-Sheng Liu, Sophia Chen, Quan Ze Seering, Joseph Zhang, Amy X. Zhu, Haiyi Holstein, Kenneth Human-Computer Interaction AI agents, or bots, serve important roles in online communities. However, they are often designed by outsiders or a few tech-savvy members, leading to bots that may not align with the broader community's needs. How might communities collectively shape the behavior of community bots? We present Botender, a system that enables communities to collaboratively design LLM-powered bots without coding. With Botender, community members can directly propose, iterate on, and deploy custom bot behaviors tailored to community needs. Botender facilitates testing and iteration on bot behavior through case-based provocations: interaction scenarios generated to spark user reflection and discussion around desirable bot behavior. A validation study found these provocations more useful than standard test cases for revealing improvement opportunities and surfacing disagreements. During a five-day deployment across six Discord servers, Botender supported communities in tailoring bot behavior to their specific needs, showcasing the usefulness of case-based provocations in facilitating collaborative bot design. |
| title | Botender: Supporting Communities in Collaboratively Designing AI Agents through Case-Based Provocations |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2509.25492 |