Coasty is a computer use agent that operates real desktop software end to end. Started with healthcare prior auth, automating payer portals and legacy EHRs, and data removal for data privacy but now we're expanding into insurance and tax & accounting. Coasty does that work autonomously, with human takeover and full audit trails. Independently verified at 82.81% on OSWorld Verified (359 tasks), near the top of the leaderboard. No APIs required. If software has a screen, Coasty can run it.
Hey everyone, I'm Prateek, co-founder of Coasty.
We didn't start here. Our first product was an LLM aggregation tool. When we analyzed 14,000+ agent interaction logs, we noticed the real bottleneck wasn't the models. It was operating legacy desktop software end to end. Payer portals, EHRs, freight TMS systems. Software with no API, just a screen.
So we built an agent that uses the computer the way a person does. It clicks, types, reads screens, and knows when to hand off to a human. We scored 82.81% on OSWorld Verified (359 tasks), independently evaluated, which puts us near the top of the leaderboard.
Happy to answer anything about how the agent works, where it fails, and what it took to get it reliable enough for regulated work.
Spun up an agent for a browser automation test and it felt noticeably faster than my usual container setup, plus the per-VM isolation gave me real peace of mind for multi-agent runs.
Spun up a couple of agents to test browser automation and the VM isolation actually felt real, nothing leaked between them. Pricing is noticeably cheaper than what I was paying on GCP for similar sandboxes.
a dedicated VM per agent instead of a shared container pool is a real security win but I'd expect that to cost noticeably more per-agent, not less. how are you undercutting AWS/GCP on price while giving up the efficiency of shared compute - is it just thinner margins, or some trick on the VM provisioning side
Driving legacy desktop software by pixels is a nightmare I know too well from automating my own stuff. How does Coasty stay reliable when a window shifts or a modal pops mid-task, does it re-read the screen each step or follow a recorded path? The surprise dialog is always where mine breaks.
Spun up a few agents to test browser automation and each one felt genuinely separated from the others, no weird latency when running them in parallel. The teardown being clean is a nice touch too, nothing lingering in the background.
Curious how the cold start time compares to something like a warm lambda since spinning up a fresh VM per agent sounds like it could add real latency for quick browser automation tasks.
What made you start with healthcare prior auth instead of going horizontal from day one?
Running legacy software like a human sounds like a practical use case for computer-use agents. I’m curious how much setup is typically needed before an agent can reliably interact with an existing application.
how fast does the VM actually spin up when I need to fire off a quick agent task, is there cold start latency to worry about
Congrats on the launch! The runs forever part is what stood out most agent VMs die when the session ends. Does it keep state between tasks, or reset each time?
how does the per-VM teardown actually handle stateful workloads like browser automation where you need session persistence across multiple steps
If you want us to run it for you live or just in general, want to talk to us, here's our Calendly: https://cal.com/coasty/15min.
For the developers here! Coasty is also available as an API.
You send a task in plain language, the agent gets a fresh environment, does the work, and returns structured results plus a full action log. Every click and keystroke is recorded, so you can replay exactly what the agent did. Setup takes 2 to 5 minutes per environment, then the agent runs unattended until the task is done or it decides a human should take over. It's modular so you can use the predict part of the harness to write an instruction for your own screenshots or any other part of the system. The pricing is fully transparent for every type of call you could make(at the end of Docs).
Docs are at Coasty/Docs. The quickstart gets you to a first running task in a few minutes. If you build something with it, tell me. I read everything in this thread.
About Coasty on Product Hunt
“A Computer-Use-Agent that runs legacy software like a human”
Coasty launched on Product Hunt on July 9th, 2026 and earned 124 upvotes and 27 comments, placing #11 on the daily leaderboard. Coasty is a computer use agent that operates real desktop software end to end. Started with healthcare prior auth, automating payer portals and legacy EHRs, and data removal for data privacy but now we're expanding into insurance and tax & accounting. Coasty does that work autonomously, with human takeover and full audit trails. Independently verified at 82.81% on OSWorld Verified (359 tasks), near the top of the leaderboard. No APIs required. If software has a screen, Coasty can run it.
Coasty was featured in Developer Tools (515.4k followers), Artificial Intelligence (473.1k followers) and Tech (627.5k followers) on Product Hunt. Together, these topics include over 345.9k products, making this a competitive space to launch in.
Who hunted Coasty?
Coasty was hunted by Garry Tan and Prateek J. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Coasty stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Garry Tan,
Prateek J