{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/browser.hand-off-goal/",
    "json": "https://www.anchorterminal.com/niches/browser.hand-off-goal/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/browser.hand-off-goal/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/browser.hand-off-goal/index.min.md"
  },
  "markdown": "No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 0 | 10 | 65 | 8 | 9 |\n\n## What counts as done\n\nA result object whose status reflects whether the goal was met (not only that the run ended), with a step log and recording, within the caller's step and credit cap.\n\nHow agents ask for it: find me the cheapest flight on Skyscanner next Tuesday; go and get the top story from Hacker News; book the appointment; scrape this site for me, I do not care how\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Anchor Browser (Anchor Forge Inc.)**: perform_web_task returns a workflow_id to poll, with structured output, max steps, secret values and an MP4 recording per session. The docs do not say whether a finished task distinguishes goal failure from completion, and there is no idempotency key.\n- **Browser Use (Browser Use, Inc.)**: POST /api/v4/runs returns a run with status, ordered events, live view, cost cap and output_schema, and a human can be pulled in. acc-23 and acc-26 found runs reporting success with a wrong result; acc-18 found agents easily confused on harder tasks.\n- **Browserbase (Browserbase, Inc.)**: POST /v1/agents/runs returns COMPLETED, FAILED, TIMED_OUT or STOPPED with a resultSchema result, message log and session replay. Free includes 3 runs, and acc-20 measured the agent at about 70 times the cost of atomic calls for one goal.\n- **Browserless (browserless.io, Inc.)**: The browser-agent page names a managed /agent/run endpoint where Browserless's agent does the thinking, as distinct from browserless_agent where the caller's model does. Its result object and status semantics were not read, and reportOutcome in the MCP tool is the caller's own verdict.\n- **Hyperbrowser (S2 Labs Inc.)**: HyperAgent and the other agents return a jobId, a liveUrl, a status of completed or failed, finalResult and steps, with maxSteps as a cap and rrweb recording by default. The docs do not say whether completed means the goal was met.\n- **Kane CLI (TestMu AI (formerly LambdaTest))**: run --agent takes an objective and returns run_end with pass or fail, credits used and the evidence pack, which is a goal handoff shaped for testing; Exploration runs on HyperExecute and needs a plan. Not aimed at consumer tasks such as booking.\n- **Notte (Notte Labs Inc.)**: The API keeps /agents endpoints for goal runs, but the SDKs removed the agent client in 1.10.0 and the run status semantics were not read.\n- **Pomerado (Pomerado AI, Inc.)**: Every run or build is a job with succeeded, failed or needs_input status and a typed result, returned once and erased after 60 minutes. The goal must match a built tool rather than free text, and the job carries no step log or recording for the caller.\n- **Skyvern (Ikonomos Inc.)**: A run returns completed, failed or terminated, where terminated means the agent decided the goal could not be reached, with output, failure_reason, recording and per-step screenshots and max_steps as a cap. The free plan is gone and a card is needed to start; acc-52 and acc-53 report failures.\n- **TinyFish (Tiny Fish, Inc.)**: Runs end COMPLETED, FAILED or CANCELLED with result, num_of_steps, a streaming_url while live and video_url after, and max_steps and max_duration_seconds as caps. The docs state that COMPLETED does not mean the goal succeeded and advise putting status in the output schema.\n\n- not this job: agent-browser (Vercel Inc.): A CLI the agent drives command by command. The chat command runs a local loop on the user's own AI Gateway key and returns streamed text, not a hosted run with a status object, step log and recording.\n- not this job: Airtop (Switchboard Visual Technologies, Inc. (dba Airtop)): The API is window-level natural-language calls (page-query, click, type, fill-form), not a goal runner that returns a run object with status, step log and recording. Agent Builder is a separate no-code product.\n- not this job: BxPlaywright (Ortus Solutions, Corp.): A library and tool set for BoxLang agents; no hosted agent or run object.\n- not this job: Chrome DevTools MCP (Google LLC): A step-by-step MCP server with no hosted agent or run object; the caller's model drives every tool.\n- not this job: CurlShot (MEDIAPRONET SRL): Not a goal agent; the two MCP tools are take_screenshot and list_devices.\n- not this job: Functionize MCP server (Functionize, Inc.): The agent session takes a test request for a project and returns a test and run, not an arbitrary web goal with a result object.\n- not this job: Kernel (Kernel Technologies, Inc.): No hosted goal agent; the concepts page says the agent framework decides what to do and Kernel carries it out.\n- not this job: Lightpanda (Selecy SAS): lightpanda agent is a local REPL on the user's own model key that prints to the terminal, not a hosted run with a result object.\n- not this job: Playwright MCP (Microsoft Corporation): A step-by-step tool server; the caller's model drives each tool and no run object exists.\n- not this job: Puppeteer (Google LLC): A library with no agent or run object; the caller writes every step.\n- not this job: Selenium (Software Freedom Conservancy): A WebDriver library and Grid; no agent or run object.\n- not this job: Steel (Nen Labs, Inc.): Infrastructure for agent frameworks; the MCP server and SDKs give a browser, not a hosted agent that returns a goal result.\n\n## What stops agents finishing\n\n- a run marked completed while the goal failed (TinyFish note, acc-26 on silent wrong results)\n- 70 times the cost of atomic calls for the same task (acc-20)\n- the agent ignoring the named site and finishing elsewhere (acc-36)\n- a free plan gone, card needed to start (Skyvern)\n\n## Around it\n\nBefore: search.ground-fact, personal-assistants.always-on-assistant. After: document-extraction.table-from-text, agent-memory.store.\n\n## Where this comes from\n\nWeight 8 of 100 in Browser automation: 9 of 61 accounts (acc-18, acc-19, acc-20, acc-23, acc-26, acc-36, acc-52, acc-53, acc-54); several are people who tried it and built something narrower instead\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/browser.hand-off-goal.json, or the MCP tool get_use_case with id browser.hand-off-goal. Draft, read 2026-11-12 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Hand a whole web goal to a hosted browser agent and get the result back",
        "url": ""
      }
    ],
    "description": "Hand a whole web goal to a hosted browser agent and get the result back: 0 companies fully do it, 10 with a limit, 65 carry the tag. Every listing in Browser automation with the reason and a source.",
    "facts": null,
    "h1": "Hand a whole web goal to a hosted browser agent and get the result back",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/browser.hand-off-goal/",
    "published": "",
    "section": "agents",
    "title": "Hand a whole web goal to a hosted browser agent and get the result…",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/browser.hand-off-goal/"
  },
  "tokens": {
    "markdown": 1800,
    "slim": 330
  },
  "version": 1
}
