What are people using for browser automation / validation? I’m surprised not to see more selenium/puppeteer wrappers.

> A typical debugging session illustrates the pattern: I describe the bug by voice (Wispr Flow), Claude searches memory (claude-mem) for prior context on that area of the code, creates a task in Beads, and spawns a debug team (Agent Teams) with competing hypotheses. [...]

So at the end of this process, you've spent anywhere from $1 to $5 to fix a bug, and you don't have any of the knowledge you would have gained from being directly involved in the fix. It seems like this approach would keep a developer easily replaceable over time, regardless of how long they've been working with a codebase, because they build very little internal knowledge on it.