Content-Driven Local Response:

Supporting Sentence-Level and Message-Level Mobile Email Replies With and Without AI

Abstract: Mobile emailing demands efficiency in diverse situations, which motivates the use of AI. However, generated text does not always reflect how people want to respond. This challenges users with AI involvement tradeoffs not yet considered in email UIs. We address this with a new UI concept called Content-Driven Local Response (CDLR), inspired by microtasking. This allows users to insert responses into the email by selecting sentences, which additionally serves to guide AI suggestions. The concept supports combining AI for local suggestions and message-level improvements. Our user study (N=126) compared CDLR with manual typing and full reply generation. We found that CDLR supports flexible workflows with varying degrees of AI involvement, while retaining the benefits of reduced typing and errors. This work contributes a new approach to integrating AI capabilities: By redesigning the UI for workflows with and without AI, we can empower users to dynamically adjust AI involvement.


Replying to an email with Content-Driven Local Response: (1) In the local response view, users can insert responses (A) directly while reading the email. (B) Tapping on a sentence opens a response widget, (C) with a text box where users enter a response or a prompt that affects (D) the sentence suggestions below. (2) After adding local responses, users go to the draft view, to turn their responses into a full reply email. They can do so manually and/or with the help of (E) an AI improvement pass feature, which generates (F) a message-level suggestion, displayed with highlighted changes. These AI features are flexible and optional: Users can add local responses without using suggestions. They can also skip directly to the draft view, optionally enter a prompt there, and use the improvement feature to generate a full reply directly. This supports flexible workflows.

Demo: