Typical chatbots force co-writers to leave shared docs. Our #CHI2026 paper explores collaborative AI use in shared docs via 3 features:
🤖 Shared agent profiles
☑️ Repeatable tasks, triggered by users or system
💬 Agents respond in shared comments
Preprint in 🧵
w @florianlehmann.bsky.social

CHI’26 Preprint Collection Looking for current research on HCI + AI? Here’s a list.

📢 Looking for current research on #HCI + #AI? Here's a categorised collection of 300+ #CHI2026 preprints, collected via arXiv:
dbuschek.medium.com/chi26-prepri...

Don’t Review with an LLM (Laundry List Method) The problem of asking AI for problems

Finalising your #CHI2026 revision? Or suffering from not being allowed to do so? I've "reviewed-to-reject" one of our papers with ChatGPT, to show how this leads to bad reviews - and give ideas for responding to this: dbuschek.medium.com/dont-review-...

StudyAlign: A Software System for Conducting Web-Based User Studies with Functional Interactive Prototypes | Proceedings of the ACM on Human-Computer Interaction Interactive systems are commonly prototyped as web applications. This approach enables studies with functional prototypes on a large scale. However, setting up these studies can be complex due to impl...

The paper is now available on the ACM Digital Library.: dl.acm.org/doi/10.1145/...

You can find our repositories here: studyalign.com

StudyAlign: A Software System for Conducting Web-Based User Studies with Functional Interactive Prototypes Interactive systems are commonly prototyped as web applications. This approach enables studies with functional prototypes on a large scale. However, setting up these studies can be complex due to impl...

Excited to share StudyAlign, our new open-source project for conducting web-based user studies. I'll be presenting our work at #EICS2025 today. StudyAlign supports HCI researchers to streamline study setup and execution. Find our paper here: arxiv.org/abs/2505.13046

We’ve redesigned #mobile #email replies - with & without #AI. Tap sentences while reading to enter local responses (or get suggestions). Then connect them on a usual draft screen (or let AI do just that). Result: Flexible workflows with varying speed and control. #CHI2025 #preprint in comments.