Clark
An AI coworker with its own cloud computer
783 followers
An AI coworker with its own cloud computer
783 followers
Clark is an AI coworker with its own cloud computer - browser, terminal, files, and code. Hand it a real task, close the tab, and come back to finished work: wide, sourced research; websites; spreadsheets; decks; audits; or tested code. It can fan work out to parallel specialists, run on a schedule, and return artifacts with the evidence behind them. Use Clark on web or mobile, work in real repositories with Clark Code, or embed the agent through an OpenAI-compatible API.
Free Options
Launch Team / Built With
How does the fan out to parallel specialists actually work, does Clark decide on its own how to split a task or do you have to define the sub agents ahead of time?
Clark
@talhakhalidmtk it decides on its own
@stanislav_kirdey great
the scheduled monitoring use case is the interesting one - when a monitor job runs repeatedly, does it diff against the last run so you only get pinged on what changed, or does it hand back the full state fresh each time and you compare yourself?
Clark
@sabber_ahamed it diffs against last run so it is continous information, not same thing every day
the scheduled monitoring runs are the part I'd worry about most - if a recurring job silently starts failing (site changed, credentials expired) does it flag that as a failure or just quietly hand back a stale/empty artifact next run?
Clark
@sabber_ahamed there is a flag it will stop wasting tokens if it fails
Congrats on the launch — #2 on the day is well earned. The under-discussed part IMO is the OpenAI-compatible API: an embeddable agent means other agents can delegate to Clark, and agent-to-agent work is where a lot of this space is heading. How does the API handle long-running tasks — does a caller get a job handle to poll, streamed progress, or a webhook when the artifact is ready?
Clark
@nitish_garg4 it is very similar to claude managed agents - Clark managed agent can be started / restarted or continued over long horizon task.
Congrats on the launch. I like that it's async, you send a task and leave instead of babysitting the agent the whole way. My one nervous question before handing an agent a real repo: when Clark Code patches something while I'm gone, is it scoped to a branch or PR I get to review, or can it land straight on main? Trying to picture the blast radius before I point it at anything that matters.
Clark
@vollos clark code could work on main, but optimized for worktrees
would love your feedback on what would work best by default
@stanislav_kirdey For me the default has to be the safe one: worktrees or a branch, never straight to main. A default is what everyone who skips the docs ends up running, and async is exactly when nobody's watching. If the one time it goes sideways it's already on main, there was no gate to catch it. I'd make branch-or-PR the default and let people opt into main once they trust it on their own repo.
Clark
@vollos good point! designing this as feature as we speak
@stanislav_kirdey Nice, glad it's on the roadmap. Good luck with the launch!
AISA AI Skills Test
the async model is the right call. most AI tools force you to babysit the process in real-time which defeats the purpose. curious how you handle the verification step though — when Clark finishes a research task, how does the user know the sources are solid without re-doing the work themselves?
Clark
@ozandag user will see browser recordings and extact sources links
todai
Clark
@umar_saleem clark code
www.clarkchat.com/clark-code should be able to navigate them with ease!