> ## Documentation Index > Fetch the complete documentation index at: https://predev.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Agents: start with https://docs.pre.dev/agents.md, which has complete recipes, plan access, polling rules, errors and limits. > Authenticate with the workspace API key (pdk_…) from Integrations → Built-in, sent as Authorization: Bearer . > REST API: https://api.pre.dev (OpenAPI: https://docs.pre.dev/api-reference/openapi.json). AI Gateway: https://api.pre.dev/v1, OpenAI-compatible (OpenAPI: https://docs.pre.dev/api-reference/ai-gateway.openapi.json). > pre.dev MCP server: npx -y @predotdev/mcp setup adds it to every local coding agent with every pre.dev tool plus the user's own Chrome; the hosted server is https://api.pre.dev/mcp. Search these docs over MCP at https://docs.pre.dev/mcp. # Browser Agents > Run browser workflows and extract structured data through REST, SDKs, or MCP, or let your coding agent use your own Chrome. Give Browser Agents a starting URL and a task. It navigates pages, interacts with forms and controls, and returns task outcomes with data and an optional execution timeline. Browser Agents comes in two editions. **Cloud**, covered on this page, runs tasks on pre.dev's browsers: send a task by REST, the SDKs, or the `browser_agent` MCP tool and get structured data back, with many tasks in parallel and nothing to set up. **Local** lets your coding agent drive the Chrome you already have open, with your profiles and the accounts you are signed in to. Both come in the free, open-source pre.dev MCP server, set up with `npx -y @predotdev/mcp setup`. In the [pre.dev CLI](https://predev.mintlify.site/cli/overview.md), type `/chrome` for Local. See [Browser Agents Local](https://predev.mintlify.site/browser-agents/local.md). > **[Run your first task](https://predev.mintlify.site/browser-agents/quickstart.md)** > > Extract a page heading with curl, Python, or TypeScript. > **[Use an MCP tool](https://predev.mintlify.site/mcp/tools.md#browser_agent)** > > Give your assistant browser automation and structured results. > **[Use your own Chrome](https://predev.mintlify.site/browser-agents/local.md)** > > Let a local coding agent work in your profiles, logins, and tabs. > **[Switch from Claude in Chrome](https://predev.mintlify.site/browser-agents/switch-from-claude-in-chrome.md)** > > Two steps. Your Chrome profiles, tabs, and logins carry over. ## Choose how the task runs | Mode | Use it for | Supply | | - | - | - | | `extract` | Read page content into a known shape | An `output` JSON Schema, optionally an instruction | | `agent` | Navigate, search, fill forms, or perform several steps | A clear instruction and success condition; optionally an output schema | | `auto` | Let the service choose the execution path | A URL and your goal or schema | Provide an explicit `output` when downstream code expects a particular structure. If it is omitted, the service may infer an output schema; do not assume a specific data shape or that every task returns text. ## Request lifecycle 1. **Submit tasks.** Send URLs, instructions, and the output shape you need. 2. **Save the run ID.** After credit and queue checks, tasks can start or wait. 3. **Follow the run.** Poll the saved ID or stream available progress events. 4. **Read each outcome.** Check every task's status before consuming its data. A completed run can include failed tasks. A rejected submission returns an error; inspect its code and next action before retrying. One request creates one **run**, also called a **batch** in response types. A run contains one or more tasks. Use its `id` to retrieve progress and results; each task has its own status and credit usage. The [status guide](https://predev.mintlify.site/browser-agents/api/task-status.md#batch-and-task-states) shows each task state and what it costs. ## Choose how to receive results | Interface | Behavior | | - | - | | [Synchronous request](https://predev.mintlify.site/browser-agents/api/run-task.md) | Wait for the run and return JSON | | [Async request](https://predev.mintlify.site/browser-agents/api/run-task.md#async) | Return the run ID, then poll or attach a stream | | [Submission stream](https://predev.mintlify.site/browser-agents/api/run-task.md#streaming) | Live SSE events and a full final result | | [Existing-run stream](https://predev.mintlify.site/browser-agents/api/stream-task.md) | Initial snapshot, live events, and terminal status | | [Live browser](https://predev.mintlify.site/browser-agents/api/live-browser.md) | View available browser frames over WebSocket | Task counts, account in-flight limits, and per-run concurrency are different controls. Check [queue status](https://predev.mintlify.site/browser-agents/api/queue-status.md) when submitting larger workloads. ## Credits Every browser task is charged a **0.1-credit floor** when you submit it, so you need available credits to start. When the task finishes, it is charged any usage above the floor, whether it succeeded or not. Only an `ERROR` or `EXHAUSTED` task keeps the floor and nothing more. Read [billing and limits](https://predev.mintlify.site/browser-agents/api/run-task.md#billing-and-limits) for details. ## Benchmarks Our runs on two public benchmarks of tasks on live websites, next to the numbers TinyFish publishes for its own runs: | Benchmark | Browser Agents | TinyFish, published | | - | - | - | | WebVoyager, 641 tasks | 93.9% | 91.1% | | Online-Mind2Web, 300 tasks | 78.3% | 89.9% | The Browser Agents figures are the mean of two full runs of each benchmark: 93.1% and 94.7% on WebVoyager, 80.3% and 76.3% on Online-Mind2Web. Under a stricter WebVoyager rule that needs a screenshot showing each claim, the mean is 91.4%. TinyFish's numbers come from its own runs, with a different harness, patch set, and grader, and we did not re-run them. On Online-Mind2Web, Browser Agents trails TinyFish's published number. The [benchmark report](https://pre.dev/browser-agents-benchmark.html) covers the protocol, results by site and level, the patched tasks and why, and a CSV of every task result from both runs. Cloud browser tasks do not expose persistent login profiles, reusable cookie sessions, or a recurring-schedule API. Schedule submissions in your own application and provide the inputs each task needs. For work behind a login, use [Browser Agents Local](https://predev.mintlify.site/browser-agents/local.md): your coding agent works in the Chrome you are already signed in to. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.