# Tether: A Personalized Support Assistant for Software Engineers with ADHD

**Authors:** Aarsh Shah, Cleyton Magalhaes, Kiev Gama, Ronnie de Souza Santos  
**arXiv:** [2509.01946](https://arxiv.org/abs/2509.01946)  
**Date:** 2025-09-02  
**Summary page:** https://www.summarizepaper.com/en/arxiv-id/2509.01946v1/

## Key points

- Lack of tools designed to support developers with ADHD in software engineering
- Importance of equity, diversity, and inclusion in SE, particularly in relation to neurodiversity
- Introduction of Tether as an LLM-powered desktop application for adaptive, context-aware assistance
- Combination of local activity monitoring, retrieval-augmented generation (RAG), and gamification for real-time focus support and personalized dialogue
- Integration of operating system-level tracking and chatbot leveraging ADHD-specific resources for relevant responses
- Preliminary validation showing improved contextual accuracy through prompt refinements and RAG enhancements
- Differentiation of Tether from generic tools by adaptability to software-specific workflows and ADHD-related challenges
- Potential of LLMs as personalized support systems for underrepresented cognitive needs in SE
- Comparison with existing tools for focus and attention support based on design scope, interaction models, and contextual adaptability guided by common ADHD-related challenges
- Foundation laid for future neurodiversity-aware tools in SE and potential impact on addressing cognitive challenges faced by developers with ADHD

## Summary

The paper "Tether: A Personalized Support Assistant for Software Engineers with ADHD" addresses the lack of tools designed to support developers with Attention Deficit Hyperactivity Disorder (ADHD) in software engineering. The existing summary highlights the importance of equity, diversity, and inclusion in SE, particularly in relation to neurodiversity. Tether is introduced as an LLM-powered desktop application that aims to provide adaptive, context-aware assistance to software engineers with ADHD. Drawing from engineering research methodology, Tether combines local activity monitoring, retrieval-augmented generation (RAG), and gamification to offer real-time focus support and personalized dialogue. The system integrates operating system-level tracking to prompt engagement and utilizes a chatbot that leverages ADHD-specific resources to provide relevant responses. Preliminary validation through self-use revealed improved contextual accuracy following iterative prompt refinements and RAG enhancements. The paper emphasizes that Tether differentiates itself from generic tools by being adaptable and aligned with software-specific workflows and ADHD-related challenges. While not yet evaluated by target users, this work lays the foundation for future neurodiversity-aware tools in SE and highlights the potential of LLMs as personalized support systems for underrepresented cognitive needs. In addition, the preliminary evaluation compared Tether with existing tools for focus and attention support described in the literature. This comparison considered design scope, interaction models, and contextual adaptability guided by common ADHD-related challenges such as task initiation and attention regulation. No formal user study was conducted during this stage, aligning with engineering research practices that emphasize early iteration as part of artifact development. Overall,"Tether: A Personalized Support Assistant for Software Engineers with ADHD" presents a promising approach to addressing the cognitive challenges faced by developers with ADHD in software engineering environments. It sets a precedent for future research on neurodiversity-aware tools in SE and underscores the potential of personalized support systems like Tether powered by LLM technology.