Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.pre.dev/llms.txt

Use this file to discover all available pages before exploring further.

Browser Agents for humans + AI. Give the agent a URL and an instruction — it drives a real browser, follows the flow, and returns structured JSON validated against your schema. No Playwright plumbing, no selector maintenance.

Quickstart

Copy-paste examples in curl, TypeScript, Python, and MCP. Your first task in under a minute.

Get an API key

Grab a key from the pre.dev playground and set it as PREDEV_API_KEY.

​
What Browser Agents can do

Pull data off any site

  • Scrape pricing, listings, and contacts into JSON
  • Enrich CSVs with fresh web data
  • Read authed dashboards (Linear, Notion, Stripe)

Automate anything clickable

  • Log in, navigate, fill forms
  • Submit bulk forms from a CSV
  • Step through multi-page flows end-to-end

Catch regressions before users do

  • Run critical flows on a schedule
  • Verify checkout across plans
  • Flag pricing, UI, or copy drift

Give your agent a real browser

  • Drop-in MCP for Claude Code & Cursor
  • URL + instruction → typed JSON
  • Replaces flaky Playwright code

​
Benchmark

pre.dev Browser Agents passes 100 / 100 tasks in our public suite vs Browser Use Cloud’s 97 / 100 — and it’s 2.9× cheaper AND 2.8× faster.
ProviderPass rate$ / taskTotal $Avg time / task
pre.dev Browser Agents100 / 100$0.0129$1.2912.7 s
Browser Use Cloud97 / 100$0.0372$3.7235.7 s
Same 100 tasks. Same JSON output schemas. Same uniform pass predicate.

​
Two ways to call it

REST API

POST https://api.pre.dev/browser-agent with a tasks array. Sync, async, or live SSE streams. Up to 1,000 tasks per request.

MCP Tool

One-click install into Cursor, Claude Code, VS Code, or Windsurf. Your agent gets browser_agent as a tool — no orchestration code.

​
Next