"Just automate it through the UI" sounds simple until you're the one maintaining that integration. When an API is missing, incomplete, or unsuitable for a task, an agent can often operate through the visible interface instead, the same DOM, accessibility tree, or screen pixels a person would use...
Source: [Dev.to](https://dev.to/nataiden/ai-agents-and-apps-with-no-api-the-real-engineering-tradeoffs-20ho)