Coasty Launches API for Computer-Use Agents Despite Server Timeout
Launch HN: Coasty (YC S26) – An API for computer-use agents
I am launching Coasty, a new YC S26 startup offering an API designed for computer-use agents. Although the site currently shows a 504 Gateway Timeout error via Cloudflare, the platform aims to empower developers to build intelligent systems that can interact with computers directly. We are working to resolve the temporary access issues so you can explore our documentation and start integrating our tools.
The web server reported a gateway time-out error.
- madikz
Founder building document-automation tools for tax firms here — the hardest part is definitely the verification step. For us it's not whether the agent can navigate a UI, but whether the output it produced (a reconciliation report, a tax form) is actually correct when every screen says "success."
We ended up building a secondary rule-based checker that runs independently over the agent's output — it catches things like missing schedules, transposed account numbers, and date mismatches with prior-year filings. The agents handle the execution path, the rules handle the truth.
Curious how you're thinking about this for workflows where a wrong but "successful" action has real downstream cost — do you rely on human review, or do you have a layered verification approach built-in?
- throw03172019
How are you all different than the other few CUA APIs in this batch and previous batches?
- teknokeras
The invariants feature is the most interesting part to me. Are invariants like "patient name must match the source document" enforced deterministically outside the model (a separate checker that gates actions), or does the agent itself evaluate them as part of its loop? Asking because if the same model that decides actions also verifies invariants, a misread screenshot could fail both at once — the check inherits the perception errors it's meant to catch. Curious how you split trusted checks from model judgment.