Your agent got to step 7 and stopped. We finish it — and send the receipts.
Send us the task your browser agent cannot complete. We run it in a real Chrome, on the real site, through the same interface a person uses — and return the result with a replayable evidence pack. If we cannot finish it, you pay nothing.
First task free. Then $5–9 per completed task. Packs from 50 tasks.
Why this exists
Benchmarks are kind: curated sites, fixed layouts, no 2FA. Production is not. The tasks that fail are the ones your user actually needs — an order placed, a form filed, a price checked behind a login. A failed step is not a smaller problem than a missing feature; it is the same support ticket, with your name on it.
Sources: WebArena leaderboard (Steel), WebBench / Skyvern, OpenAI CUA. Numbers move; the gap does not.
How it works
1 · You send the task
URL, goal, and the fields you need back. If the flow needs a login, you give a sandbox account — not your customers' credentials.
2 · We execute
A real browser session, isolated profile, human-paced. Every action is recorded: DOM state, network calls, console, video, Playwright trace.
3 · You get result + proof
result.json in your schema, plus the pack that lets you or your customer
replay the run and check every value at its source.
What the evidence pack contains
- Step screenshots — one per action, named after the action
- HTTP log — every request and response, with status and timing
- Console log — page errors included, not filtered
- Playwright trace — replayable in the trace viewer
- Screen recording of the session
result.json— values, source URL, timestamp, run id
The pack is the product. A JSON without it is an assertion; with it, it is a record.
Price
| Task class | What it covers | Per completed task |
|---|---|---|
| Open | Public pages, read-only: price, stock, availability, catalogue, PDF | $5 |
| Stateful | Logged-in flows, multi-step forms, quotes, orders in your sandbox account, dynamic pricing | $9 |
| Pack | 50 tasks, mixed classes, one invoice, priority queue | from $250 |
Turnaround 24–72 h per task, batches daily. You are charged for completed tasks only. A task we could not finish costs nothing and comes back with the failure record, which is often the more useful artefact.
What we will not do
- Bypass a paywall, a licence or an authorisation you do not hold.
- Harvest personal data, build profiles of people, or scrape at volumes the target site would treat as an attack.
- Act on an account you cannot authorise. Sandbox or test credentials only.
- Break the terms you are bound by and hand you the liability. If a task is a legal problem for you, it is a legal problem for us.
- Take money for a task we cannot reproduce. The pack is either replayable or the task did not happen.
Who runs it
Lobster Swamp is a small engineering lab: browser automation, agent systems, and measurement that survives a second look. The execution side is Playwright/CDP with an evidence recorder; the same harness runs our own pipelines daily. You talk to the person who runs the task, not to a queue.
Send one task
Paste the URL and the fields you need. If it is a flow behind a login, say so and we will send back what a sandbox account has to be able to do. Answer within one working day; the first task is free.