{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/browser.check-web-app/",
    "json": "https://www.anchorterminal.com/niches/browser.check-web-app/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/browser.check-web-app/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/browser.check-web-app/index.min.md"
  },
  "markdown": "Four or more companies' docs show a full fit.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 4 | 15 | 30 | 22 | 17 |\n\n## What counts as done\n\nThe agent reports pass or fail for each named step with a screenshot or snapshot as evidence.\n\nMeasured, for our own tests: a 10-step flow takes at most 20 browser actions, and its page reads do not exceed about 50k tokens.\n\nHow agents ask for it: open the app and check the signup flow works; run the UI through the browser and tell me what breaks; test this page as a new user; take a look at the page and compare it with the design\n\n## Does the job\n\nThe docs show it meets the test above, and nothing we read says otherwise.\n\n- **agent-browser (Vercel Inc.)**: snapshot -i, -c and -d cap the tree, --max-output truncates page text, screenshot writes a path and console reads errors. acc-48 and acc-40 use it for precisely this; acc-72 reports flaky refs on dynamic pages.\n- **Browserbase (Browserbase, Inc.)**: The Browse CLI runs a managed local browser (--local) or a remote session, prints accessibility snapshots with cached refs, and the ui-test skill reports passed, failed and skipped tests with failure screenshots under .context/. Remote sessions still cannot reach localhost.\n- **Chrome DevTools MCP (Google LLC)**: take_snapshot returns a filtered tree by default (verbose false) or writes to filePath, actions default includeSnapshot to false, take_screenshot writes a file, and a local Chrome reaches localhost. acc-72 puts the tool definitions at about 17k tokens; --slim trims them.\n- **Kane CLI (TestMu AI (formerly LambdaTest))**: A plain-English objective runs in local Chrome, so localhost works, and every run seals an evidence pack with per-step screenshots, annotated copies, console and network logs and a pass or fail result card; saved test.md files replay cached steps. Runs spend account credits.\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- **Airtop (Switchboard Visual Technologies, Inc. (dba Airtop))**: A cloud browser driven by page-query, click and type calls over Puppeteer or Playwright, with recordings per window. It cannot reach localhost without a tunnel, and there is no accessibility snapshot or ref tool, so each step check is an AI call billed in credits.\n- **Anchor Browser (Anchor Forge Inc.)**: The hosted MCP's anchor_* tools give navigate, snapshot with accessibility refs, click, type, screenshot, console and network logs, and sessions record MP4 by default. The browser is in Anchor's cloud, so a localhost app needs a tunnel, and no snapshot cap or depth option is documented.\n- **Browser Use (Browser Use, Inc.)**: The cloud is a goal agent (run_session over MCP, POST /runs) whose browsers cannot reach localhost. The open-source library runs locally and can attach to the person's Chrome, but it too is an agent loop, so per-step pass or fail evidence comes from its history, not a step tool.\n- **Browserless (browserless.io, Inc.)**: browserless_agent snapshots interactive and informational elements with maxElements and returns only changes after the first, screenshot toDisk saves a file reference. The browser is in the cloud, so localhost needs a tunnel, and Free sessions end at 2 minutes with 2 concurrent.\n- **BxPlaywright (Ortus Solutions, Corp.)**: BoxLang AI agents get browser_visit, browser_snapshot (compact tree with refs, limitable to one selector), browser_click, browser_fill and browser_screenshot against a local browser that reaches localhost. Only BoxLang agents get these tools; others get Microsoft's Playwright MCP, and the in-process snapshot has no depth or size cap.\n- **Functionize MCP server (Functionize, Inc.)**: Studio runs the test in Chrome, Firefox or Edge with per-step pass or fail, screenshots and video; the coding agent reads the status rather than driving a browser. A local app needs Functionize's tunnel, a generation is green or yellow never red, and creating a test spends unpublished credits.\n- **Hyperbrowser (S2 Labs Inc.)**: A cloud Chromium driven over CDP, WebDriver or computer actions, with rrweb recording on by default and a live view. No snapshot or ref tool of its own (the MCP has run_browser_task and web_fetch), and a localhost app needs a tunnel.\n- **Kernel (Kernel Technologies, Inc.)**: Cloud Chromium driven by Playwright, CDP or computer controls with replays recorded by browser id; the MCP server launches browsers and runs Playwright code rather than snapshots. A localhost app needs a tunnel, and acc-36 measured 0.94 s to create a browser.\n- **Lightpanda (Selecy SAS)**: A local MCP server with goto, tree, interactiveElements, click, fill, consoleLogs and a screenshot tool reaches localhost cheaply. There is no graphical rendering, iframes, workers and stylesheets are off by default, and acc-64's agent task failed on a link click.\n- **Notte (Notte Labs Inc.)**: The MCP gives browser_observe (element IDs), browser_action, browser_scrape and browser_screenshot over a cloud session, and every session records an MP4. The browser is remote, so a localhost app needs the CLI tunnel command, which was not read.\n- **Playwright MCP (Microsoft Corporation)**: browser_snapshot takes depth, target and filename, browser_find returns matches instead of a tree, --snapshot-mode none stops action responses carrying one, and screenshots land in --output-dir. acc-01, acc-08, acc-09 and acc-10 use it for UI checks; acc-04 spent over 1M tokens on a 20-step test and acc-03 found it slow.\n- **Puppeteer (Google LLC)**: A Node library: the agent writes a script that opens localhost, acts through locators and saves screenshots, so evidence per step is whatever the script prints. No snapshot or ref tool; page.accessibility.snapshot is the compact read. acc-58 let an agent troubleshoot web code this way in Docker.\n- **Selenium (Software Freedom Conservancy)**: The agent writes WebDriver scripts in one of five languages and attaches screenshots on failure; there is no accessibility snapshot or ref tool, so page reads are page source or element queries. acc-59 had Claude write JUnit and Selenium tests with no result reported.\n- **Skyvern (Ikonomos Inc.)**: An agent run records video, a screenshot and reasoning per step and Browser Address lets Skyvern drive your own browser over CDP, so localhost is reachable. Each action costs 30 credits, acc-54 waited 4 to 5 minutes for a six-field form, and a new account needs a card.\n- **Steel (Nen Labs, Inc.)**: The steel CLI drives a session with snapshot refs (@e3), waits for downloads and screenshots, and every session has replay, console and network tabs plus Agent Traces. The browser is in Steel's cloud, so localhost needs a tunnel, and Launch sessions end after 15 minutes.\n- **TinyFish (Tiny Fish, Inc.)**: A how-to runs a numbered user flow against a preview deploy or tunnelled localhost in Strict mode and returns passed as JSON, telling you to check passed rather than run status. Strict mode and max_steps are beta-gated, and steps cost $0.016 each.\n\n- not this job: CurlShot (MEDIAPRONET SRL): One capture per call of a public URL; the MCP tool has no click, type or snapshot and cannot reach localhost. The REST click and wait_for_selector parameters stage one render, not a flow.\n- not this job: Pomerado (Pomerado AI, Inc.): Builds tools for public consumer sites and portals from a site_url origin; nothing drives a localhost or preview app step by step, and no screenshot or snapshot tool exists.\n\n## What stops agents finishing\n\n- a 20-step test that spends over a million tokens on snapshots (acc-04)\n- refs that go stale after navigation so the agent retries blindly (acc-15)\n- canvas and custom widgets outside the accessibility tree\n- a tool that reports a saved screenshot that was never written (acc-62)\n\n## Around it\n\nBefore: agent-harnesses.spec-to-build-loop, agent-harnesses.fix-failing-ci. After: agent-harnesses.spec-to-build-loop, browser.capture-evidence.\n\n## Where this comes from\n\nWeight 22 of 100 in Browser automation: 15 of 61 accounts, the most common job on Hacker News among coding-agent users (acc-01, acc-03, acc-04, acc-08 to acc-11, acc-13, acc-16, acc-37, acc-39, acc-40, acc-48, acc-59, acc-61)\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/browser.check-web-app.json, or the MCP tool get_use_case with id browser.check-web-app. 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": "Check a web app the agent is building in a real browser",
        "url": ""
      }
    ],
    "description": "Check a web app the agent is building in a real browser: 4 companies fully do it, 15 with a limit, 30 carry the tag. Every listing in Browser automation with the reason and a source.",
    "facts": null,
    "h1": "Check a web app the agent is building in a real browser",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/browser.check-web-app/",
    "published": "",
    "section": "agents",
    "title": "Check a web app the agent is building in a real browser | Anchor…",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/browser.check-web-app/"
  },
  "tokens": {
    "markdown": 2350,
    "slim": 380
  },
  "version": 1
}
