New AI Journaling Tool Keeps You in Charge of Your Story
Finally, an AI that helps you journal without taking over your voice.
Large language models are increasingly used in reflective journaling, where articulating an experience is part of interpreting it. This raises questions about how writers retain authorship, exercise agency, and assess personalized assistance.
We present AuthScribe, an LLM-assisted reflective journaling system that combines contextual anchors, writer-steered AI support, Autobiographical Citations, and read-only Provisional Drafts that require re-expression before AI-generated suggestions enter the journal. Retrieval and LLM inference run on-device.
In a 14-day field deployment with 14 participants, grounding shifted from situating current experiences to reconnecting them with prior self-authored interpretations. Perceived agency remained stable through Week 1 and shifted during Week 2. Participants described authorship through transforming AI-generated suggestions into personally meaningful expression, and trusted personalized prompts when they could trace them to prior writing. We discuss design implications for adoption friction, longitudinal agency, and traceable personalization in AI systems for personal reflection.
- AuthScribe is an AI that helps you journal by asking questions and suggesting topics, but you do all the writing.
- It's designed to keep you in control, so your journal remains personal and authentic.
- The tool is a research prototype, so it's not yet available for public use.
Why It Matters
This could lead to AI tools that support your creativity and mental health without taking over.