Llm assistant improves software work for engineers with ADHD

Extending LLM-based support for software engineers with ADHD

Software Engineering

Summary

People with ADHD often find it hard to start, focus on, and finish software projects because typical workflows don't fit their needs. The authors made a new tool called Tether 2.0 that uses a language AI to help these developers plan, write, debug, and review code in a way that supports staying on track and picking up work after breaks. They tested it with experts and a software engineer with ADHD and found it helps break down tasks and keep progress steady. This shows AI assistants can be helpful when designed for real work stages and personal focus challenges.

What this means in practice

  • For software engineering teams: Enable developers with ADHD to better manage coding workflows by using AI assistance tailored to their workflow challenges and attention needs.
  • For productivity tool designers: Build development tools that integrate task-focused AI interactions supporting sustained progress and task resumption for neurodiverse users.

Authors

Aarsh Shah, Ronnie de Souza Santos, Italo Santos, Cleyton Magalhaes, Kiev Gama

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.