Waiting months for API access? Give Claude a computer instead. Use E2B with Claude's new computer and browser use toolset, and Claude gets an isolated cloud machine where every action becomes a click or keystroke. Use it to automate the work an API can't reach, like testing your own... UI end to end or entering data into a legacy app. Docs: Cookbook Example:show more

@claudeai 有些活儿确实不是 API 接得住的

@claudeai the legacy-app example is the one i'd stress test. replacing an API with clicks works until a form submission times out and the agent can't tell whether it actually committed. i'd want checkpoints and retry rules around irreversible UI actions before letting this run unattended

The legacy-app use case is where this gets really interesting. Once an agent can actually operate a UI, the execution itself becomes valuable data: what it saw, what it changed, and what happened afterward. The challenge is making that history reusable, not just replayable. That’s a layer we’re exploring with @ekosproject.

@claudeai Giving Claude a full computer unlocks a whole new class of automation use cases