Live data from Hacker News

Launch HN: Coasty (YC S26) – An API for computer-use agents

coasty.ai

21–30 of 32 posts

Re: Launch HN: Coasty (YC S26) – An API for computer-use agents

#21
post #4

Earlier quoted context omitted.

We don't just provide end-to-end API, we're a SOTA harness where you can bring in your own OpenAI or Claude keys and run it on and also we're the only modular API in the market - we give you the ability to control any part of CUA and charge by the type of call as you can see in https://coasty.ai/docs .

What do you think that makes your solution "SOTA"? That's quite the interesting claim, which is obviously false.

We've hit 82.8% on OSWorld Verfied(on the official page) and with our latest internal testing we're hitting 85.6% which we've posted (https://github.com/coasty-ai/coasty-osworld).

Re: Launch HN: Coasty (YC S26) – An API for computer-use agents

#22
post #20

Congrats on the launch bro. I use computer-use agents daily as an end user (browser automation, even wireless ADB to install builds on my phone), so genuine question: how does your API handle the diffrence between reversible and ireversible actions ? Clicking around a page is one thing, but submitting a form, sending a message or confirming a payment is another — is there a mechanism for the agent to pause and hand b…

Thanks!!! completely agree that this is where trust is won or lost.

We support explicit human approval gates in workflows, so you can have the agent prepare everything, then pause before steps like submitting a form, sending a message, or confirming a payment. The workflow moves to `awaiting_human`, and the caller approves or rejects it before execution continues.

Autonomous runs can also pause and hand over the live machine when the agent encounters something requiring human input. For teams that want stricter control, our lower-level API exposes each predicted action so the caller can inspect or approve actions before executing them.

Today, the irreversible boundary is primarily defined by the developer rather than us trying to universally infer what is consequential. We think explicit policy is safer because “irreversible” varies a lot by application.

Re: Launch HN: Coasty (YC S26) – An API for computer-use agents

#23
post #19
post #17

we run screen-driven agents against web forms in production and the failure mode that took us longest to find wasn't navigation, it was commits that don't commit. a react controlled select can render the right value after a click while the framework's internal state never updated, so every pixel says done and the submitted payload says null. vision-only verification passes because the screen genuinely looks correct.…

Great observation on the "commits that don't commit" failure mode. We ran into the exact same class of bug building document extraction for regulated financial workflows — turns out vision-only verification has a blind spot that shows up whether you're parsing a screen or a PDF. In tax preparation, documents have a lot of "the screen lies" equivalents: a PDF renderer can display perfectly aligned columns while the un…

Yep, this is a real failure mode, and screenshot-after-action alone does not solve it. A field can look populated while the application never commits the underlying value.

We try to define verification around the actual outcome of the task rather than the immediately preceding UI state. Depending on the workflow, that can mean checking the confirmation page, reopening the submitted record, verifying a status change elsewhere in the application, matching a generated reference ID, or confirming that a downstream artifact was created.

We can also verify against separate inputs such as a PDF, CSV, or another screen for example, confirming that the values entered into a portal match the source document and then checking the resulting record after submission.

Today, our core agent is screen-driven, so we do not claim that pixels can prove every hidden state transition. For high-consequence commits, the workflow should use explicit downstream invariants and, where those are unavailable, a human approval or review step. Longer term, we think verification should be able to consume whatever independent evidence the environment exposes, including network or application-level signals, rather than treating vision as the only source of truth but it will be quite slower.

Re: Launch HN: Coasty (YC S26) – An API for computer-use agents

#24

[flagged]

This is a great read of it, and honestly we probably did undersell that part.

The handoff works through checkpoints. The deterministic workflow defines the state it expects before resuming, and the agent’s recovery job is to get the UI back into one of those known states, not just “fix whatever happened” and keep going.

If it can reconcile back to a checkpoint, the script resumes deterministically from there. If it can’t, the run pauses rather than pretending it knows where it is.

That reconciliation layer is definitely where a lot of the hard engineering lives.

Re: Launch HN: Coasty (YC S26) – An API for computer-use agents

#25

It's so funny to see YC back tens of generic similar low quality projects

I mean we've spent a year of our life on this(ironing out infra for more than half of the time), so i wouldn't say super low quality but again YC accepted us based on how our business is growing! Thanks for the feedback though!

Re: Launch HN: Coasty (YC S26) – An API for computer-use agents

#26
post #13

The checkpoint and invariant model is a strong fit for these workflows. Having approval gates plus a replayable event log makes the agent's decisions much easier to audit than a simple end-to-end task API.

Exactly. We’ve found that for real production workflows, “did the task finish?” isn’t enough. You need to know what the agent saw, why it acted, what changed, and where a human approved something consequential.

The checkpoints and event log are really about making failures inspectable instead of mysterious.

Re: Launch HN: Coasty (YC S26) – An API for computer-use agents

#27
post #17

we run screen-driven agents against web forms in production and the failure mode that took us longest to find wasn't navigation, it was commits that don't commit. a react controlled select can render the right value after a click while the framework's internal state never updated, so every pixel says done and the submitted payload says null. vision-only verification passes because the screen genuinely looks correct.…

The invariant we use is the downstream outcome, not the visual state. For a controlled select, that can be the request payload, confirmation state, or persisted record. I’m building AnnotateQA around capturing a real browser failure and creating that failing Playwright reproduction before any code changes, with a candidate PR left for human review. If you have a recent case, I’d be glad to try one.

Re: Launch HN: Coasty (YC S26) – An API for computer-use agents

#28
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?

Re: Launch HN: Coasty (YC S26) – An API for computer-use agents

#29
post #28

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 li…

That’s exactly the failure mode we’re most worried about. A UI saying “success” is weak evidence that the underlying work is correct.

We’re using a layered approach rather than relying on the computer-use model alone. The execution agent handles navigation, but workflows can also define independent checks against source data and expected invariants,for example, matching patient IDs, totals, dates, procedure codes, or confirming that a record actually changed in the destination system. For higher-risk actions, we can pause before submission or route the completed output to human review.

We’re also trying to keep verification logically separate from execution where possible, so the same agent isn’t simply grading its own work. In some workflows that means deterministic rules; in others it may mean rereading the destination, comparing against the original document, or using a separate model/checker.

Your point about the rules handling truth is a useful way to frame it. I’d be curious how much of your checker is reusable across tax firms versus custom to each firm’s process.

Re: Launch HN: Coasty (YC S26) – An API for computer-use agents

#30

How are you all different than the other few CUA APIs in this batch and previous batches?

"Zapier to monitor email inbox and then extract the code" - I hit this exact wall, and ended up building the missing piece myself. The agent gets its own managed address on our domain, and one call blocks until the verification email arrives and it is automatically parsed for OTPs/code/magic link. Available at https://sente.run/
Post reply on HN