# Bespoke Visual Assistance: What and How do Blind and Low-Vision People Create with Agentic Programming?

arXiv: https://arxiv.org/abs/2607.21760 · HTML: https://mlsanity.com/paper/2607.21760/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- Builds on 32 of its 116 references that are in the map.
- First posted on arXiv 23 Jul 2026.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Builds on (most cited first, 30 of 32)

- [SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents](https://mlsanity.com/paper/2504.08703/) (2025)
- [Vibe Coding in Practice: Motivations, Challenges, and a Future Outlook -- a Grey Literature Review](https://mlsanity.com/paper/2510.00328/) (2025)
- [Misfitting With AI: How Blind People Verify and Contest AI Errors](https://mlsanity.com/paper/2408.06546/) (2024)
- [Programming by Chat: A Large-Scale Behavioral Analysis of 11,579 Real-World AI-Assisted IDE Sessions](https://mlsanity.com/paper/2604.00436/) (2026)
- [Improving Automated Code Reviews: Learning from Experience](https://mlsanity.com/paper/2402.03777/) (2024)
- [Beyond Visual Perception: Insights from Smartphone Interaction of Visually Impaired Users with Large Multimodal Models](https://mlsanity.com/paper/2502.16098/) (2025)
- [Vid2Coach: Transforming How-To Videos into Task Assistants](https://mlsanity.com/paper/2506.00717/) (2025)
- [Conversational AI as a Coding Assistant: Understanding Programmers' Interactions with and Expectations from Large Language Models for Coding](https://mlsanity.com/paper/2503.16508/) (2025)
- [Understanding Visual Arts Experiences of Blind People](https://mlsanity.com/paper/2301.12687/) (2023)
- [CodeA11y: Making AI Coding Assistants Useful for Accessible Web Development](https://mlsanity.com/paper/2502.10884/) (2025)
- [DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models](https://mlsanity.com/paper/2601.11895/) (2026)
- [Non-Visual Cooking: Exploring Practices and Challenges of Meal Preparation by People with Visual Impairments](https://mlsanity.com/paper/2107.05783/) (2021)
- [ProgramAlly: Creating Custom Visual Access Programs via Multi-Modal End-User Programming](https://mlsanity.com/paper/2408.10499/) (2024)
- [What do Blind and Low-Vision People Really Want from Assistive Smart Devices? Comparison of the Literature with a Focus Study](https://mlsanity.com/paper/2505.19325/) (2025)
- ["Before, I Asked My Mom, Now I Ask ChatGPT": Visual Privacy Management with Generative AI for Blind and Low-Vision People](https://mlsanity.com/paper/2507.00286/) (2025)
- [Not Everyone Wins with LLMs: Behavioral Patterns and Pedagogical Implications for AI Literacy in Programmatic Data Science](https://mlsanity.com/paper/2509.21890/) (2025)
- [Understanding Dominant Themes in Reviewing Agentic AI-authored Code](https://mlsanity.com/paper/2601.19287/) (2026)
- [Mini-Giants: "Small" Language Models and Open Source Win-Win](https://mlsanity.com/paper/2307.08189/) (2023)
- [One Does Not Simply 'Mm-hmm': Exploring Backchanneling in the AAC Micro-Culture](https://mlsanity.com/paper/2506.17890/) (2025)
- [Why So Serious? Exploring Timely Humorous Comments in AAC Through AI-Powered Interfaces](https://mlsanity.com/paper/2410.16634/) (2024)
- [ChartA11y: Designing Accessible Touch Experiences of Visualizations with Blind Smartphone Users](https://mlsanity.com/paper/2410.20545/) (2024)
- [Optimizing AI-Assisted Code Generation](https://mlsanity.com/paper/2412.10953/) (2024)
- [The Dilemma of Building Do-It-Yourself (DIY) Solutions for Workplace Accessibility](https://mlsanity.com/paper/2501.18148/) (2025)
- [More than One Step at a Time: Designing Procedural Feedback for Non-visual Makeup Routines](https://mlsanity.com/paper/2507.03942/) (2025)
- [I, Robot? Exploring Ultra-Personalized AI-Powered AAC; an Autoethnographic Account](https://mlsanity.com/paper/2509.13671/) (2025)
- [Smart Glasses for CVI: Co-Designing Extended Reality Solutions to Support Environmental Perception by People with Cerebral Visual Impairment](https://mlsanity.com/paper/2506.19210/) (2025)
- [Helping or Homogenizing? GenAI as a Design Partner to Pre-Service SLPs for Just-in-Time Programming of AAC](https://mlsanity.com/paper/2507.21811/) (2025)
- [SonoCraftAR: Towards Supporting Personalized Authoring of Sound-Reactive AR Interfaces by Deaf and Hard of Hearing Users](https://mlsanity.com/paper/2508.17597/) (2025)
- [How Far I'll Go: Imagining Futures of Conversational AI with People with Visual Impairments Through Design Fiction](https://mlsanity.com/paper/2510.12268/) (2025)
- [(R)evolution of Programming: Vibe Coding as a Post-Coding Paradigm](https://mlsanity.com/paper/2510.12364/) (2025)

## Abstract (arXiv)

AI-powered assistive technologies have long supported blind and low vision (BLV) people in everyday tasks, but they are general-purpose and often fall short of meeting complex, individualized, in-situ accessibility needs. Though agentic programming tools, like GitHub Copilot, have the potential to bridge this gap by lowering the technical barriers to building personal AT using natural language, the practical applicability of this creation paradigm has been unknown. We address this knowledge gap through a two-phase longitudinal co-design study with five tech-savvy BLV users using ProgramAT, an agentic programming tool that supports the creation, iteration, and testing of camera-based AT. Overall, co-designers created over 37 tools, with some addressing needs unmet by any existing commercial AT such as identifying Uber rides or interpreting hand gestures. Qualitative feedback from our co-designers and analysis of development logs surface BLV strategies for tool creation, along with key challenges including model capability limits, specification conflicts, and barriers to successful creation. We discuss recommendations to provide appropriate conversational scaffolding, community tool sharing capabilities, and support for specialized models and personal datasets for future agentic programming environments to empower BLV users to create bespoke visual assistance for themselves.