A software developer reports spending a week auditing 15 popular Android apps to determine whether an AI agent can identify and interact with core buttons using the app’s UI tree. The developer says the agent worked reliably in several major “global” apps—including WhatsApp, Google Messages, Gmail, Google Maps, and others—because those apps provide rich accessibility-related UI labels. In contrast, the developer reports that several “local” apps, including banking and government service applications, largely expose no usable UI tree labels, making the agent unable to find or tap key interface elements. The developer describes testing by extracting and reviewing UI hierarchy information (such as content descriptions) for each app and recording whether the agent can automate each one. The findings lead the developer to frame the results as evidence of an “accessibility divide,” attributing it to differences in engineering teams, priorities, and investment in accessibility. The developer says the project will include an A–F accessibility score, expand the audit to more apps, and publish an initial list and outreach efforts to app developers.
Developer audits 15 Android apps’ accessibility, finding local apps lack UI labels
A software developer reports spending a week auditing 15 popular Android apps to determine whether an AI agent can identify and interact with core buttons using the app’s UI tree. The developer says t...
- The developer audits 15 Android apps by checking whether the AI agent can find and tap core buttons using the UI tree.
- WhatsApp and several Google apps are reported to have rich UI/accessibility labels and are fully automatable.
- Multiple banking and government service apps are reported to provide no usable UI labels, making them completely invisible to the agent.
- Other apps like Spotify and Slack are reported as only mostly automatable, with partial labeling.
- The developer plans to expand the audit, publish an A–F accessibility scoring list, and add results to the project documentation.
Project Log #12: I Spent a Week Auditing Apps. The Results Changed This Project. Okeke Chukwudubem Okeke Chukwudubem Okeke Chukwudubem Follow Jul 4 Project Log #12: I Spent a Week Auditing Apps. The Results Changed This Project. #ai #webdev #programming #productivity Add Comment 3 min read
3 hours agoDay 12. I tested 15 popular Android apps for accessibility. What I found revealed who gets left behind. I took a week off from coding. Not because I was stuck. Not because I was tired. But because I needed to understand something that had been nagging at me since Day 10. Why does my AI agent work flawlessly on WhatsApp but completely fail on my banking app? The answer took a week of testing, documenting, and thinking. And what I found changed the direction of this entire project. The Week-Long Audit I tested 15 popular Android apps. For each one, I asked the same question: "Can my agent find and tap a core button using the UI tree?" I spent hours opening apps, dumping UI hierarchies, parsing XML, and documenting every content description I could find. I wasn't coding. I was investigating. App UI Tree Labels Agent Can Automate? WhatsApp Excellent ✅ Fully Google Messages Excellent ✅ Fully Gmail Excellent ✅ Fully Google Maps Excellent ✅ Fully Spotify Good ✅ Mostly Slack Good ✅ Mostly Banking App A None ❌ Completely blind Banking App B None ❌ Completely blind Banking App C None ❌ Completely blind Local Food Delivery App Minimal ❌ Mostly blind Government Service App None ❌ Completely blind Telecom App Minimal ❌ Mostly blind The pattern was impossible to ignore. Global apps had rich accessibility labels. Local apps had nothing. What This Actually Means Here's the truth I wasn't ready for. Accessibility labels exist so that screen readers can tell blind and visually impaired users what's on their screen. When a developer adds content-desc="Send message" to a button, they're helping a blind person use WhatsApp. WhatsApp invested in accessibility. Google invested in accessibility. Their apps are usable by millions of people with disabilities—and, accidentally, by my AI agent. The local apps that skipped accessibility didn't just lock out my agent. They locked out every blind and visually impaired person who needs to use that banking app, that government service, that telecom platform. My AI agent is not the victim here. It's a canary in a coal mine. The Accessibility Divide This divide follows a clear pattern. Global tech companies with large engineering teams and legal departments prioritise accessibility. They have dedicated accessibility engineers. They test with screen readers. They follow WCAG guidelines. Local apps, often built by smaller teams with tighter budgets, deprioritise accessibility. It's seen as a "nice to have" rather than a core requirement. The result is an entire class of applications that are unusable by people with disabilities—and by AI agents. What I'm Doing About It I'm adding an accessibility score to every app my agent supports. A simple A-F rating. A — Fully automatable. Rich labels everywhere. (WhatsApp, Google apps) B — Mostly automatable. Good labels with some gaps. (Spotify, Slack) C — Partially automatable. Some labels, mostly generic. D — Mostly blind. Few labels. Heavy reliance on OCR fallback. F — Completely inaccessible. No labels. Unusable by both AI and screen readers. This score isn't just for my agent. It's a public signal. If your app scores an F, you're not just failing my project. You're failing every visually impaired person who tries to use your service. What's Next (Day 13) Expand the audit to 30+ apps Publish the first version of the accessibility score list Start reaching out to local app developers about their accessibility gaps The Repo 👉 github.com/Dexter2344/phone-agent The audit results are being added to the README. The scoring system is documented. This is Day 12. I spent a week not writing code. And it was the most productive week of this entire project.
3 hours ago
Storms prompt evacuation at Washington’s National Mall ahead of Trump July 4 speech
Ahead of US President Donald Trump’s scheduled July 4, 2026 speech commemorating America’s 250th anniversary of independ...
AI coding speeds software output but keeps humans reviewing, with production risks and delays
Multiple outlets describe a shift in how software is built with “agentic” AI tools, but they agree that faster code gene...
OpenAI considers offering the U.S. government a 5% stake, report says
OpenAI is reportedly in early discussions about giving the U.S. government a 5% equity stake in the company that develop...