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.