Letting the Agent Touch the Browser Changed My Task List

Description and use

<p>For the first month I kept the agent inside the terminal. Files, git, commands - all fine. The browser was off limits because I assumed it would be flaky, and every GUI automation story I had heard ended in a pile of brittle coordinates.</p> <p>Then a task forced the issue: a weekly report that only exists behind a login, with no export button. Either the agent learns the browser or I keep doing it by hand forever.</p> <h2> What was actually hard </h2> <p>Not clicking. Clicking was fine. The hard parts were, in order:</p> <ol> <li> <strong>Knowing when the page was ready.</strong> Sleeps ar

Problem

<p>For the first month I kept the agent inside the terminal. Files, git, commands - all fine. The browser was off limits because I assumed it would be flaky, and every GUI automation story I had heard ended in a pile of brittle coordinates.</p> <p>Then a task forced the issue: a weekly report that only exists behind a login, with no export button. Either the agent learns the browser or I keep doing it by hand forever.</p> <h2> What was actually hard </h2> <p>Not clicking. Clicking was fine. The hard parts were, in order:</p> <ol> <li> <strong>Knowing when the page was ready.</strong> Sleeps ar

Outcome

<p>For the first month I kept the agent inside the terminal. Files, git, commands - all fine. The browser was off limits because I assumed it would be flaky, and every GUI automation story I had heard ended in a pile of brittle coordinates.</p> <p>Then a task forced the issue: a weekly report that only exists behind a login, with no export button. Either the agent learns the browser or I keep doing it by hand forever.</p> <h2> What was actually hard </h2> <p>Not clicking. Clicking was fine. The hard parts were, in order:</p> <ol> <li> <strong>Knowing when the page was ready.</strong> Sleeps ar

Evidence

Letting the Agent Touch the Browser Changed My Task List

Source