Extending LLM-based support for software engineers with ADHD

2026-09-30

AI Summary

This study addresses the misalignment between existing software engineering workflows and the specific needs of developers with ADHD regarding task initiation, sustained attention, and execution completion. To this end, we propose Tether 2.0, the first large language model-assisted development tool designed for neurodivergent populations. The system integrates structured interaction paradigms, activity-aware context management, and persistent memory mechanisms to support the entire workflow from planning to review. Our findings demonstrate that Tether 2.0 effectively facilitates requirements clarification and code debugging while enabling seamless resumption after interruptions and incremental task progression. Consequently, it significantly enhances development continuity and productivity for engineers with ADHD.

Abstract

Software engineering workflows are often not designed to accommodate the needs of developers with Attention Deficit Hyperactivity Disorder (ADHD), despite known challenges related to task initiation, sustained attention, and completion. At the same time, large language models (LLMs) are increasingly integrated into programming tools, but existing systems do not account for neurodiversity or support structured progression across development tasks. In this work, we present Tether 2.0, an LLM based assistant designed to support software engineers with ADHD through workflow oriented interaction across planning, coding, debugging, and review. The tool was named Tether 2.0 because it builds upon the open source code and foundations of the original Tether system. Our approach combines structured interaction modes, activity aware context, and persistent memory to support task progression and continuity. We evaluate the system through expert feedback and hands on use with a software engineer with ADHD. Our results indicate that Tether 2.0 supports requirement clarification, task decomposition, incremental implementation, debugging, and completion, while enabling users to maintain progress and resume work after interruptions. These findings suggest that LLM based assistants can support direction, sustained progress, and learning in software development when designed with workflow structure and context aware interaction.

Problem

• ADHD
• Large Language Models
• Software Engineering
• Neurodiversity
• Assistive Technology

Innovation

• Large Language Models
• ADHD
• Workflow-oriented Interaction
• Persistent Memory
• Activity-aware Context