
Page Automation Primitives
Browserbase (cloud headless Chromium + Stagehand SDK) · Browserbase
Browser Infrastructure for AI Agents — Browserbase
Evaluates Browserbase's Page Automation Primitives across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Browser Infrastructure for AI Agents eval coverage.
About Browserbase
Browserbase provides cloud headless-browser infrastructure for AI agents — managed Chromium sessions with stealth mode, captcha handling, proxies, session persistence, live debugging, and the Stagehand SDK for act/extract/observe automation.
Sample tests· showing 3 of 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Agent calls page.goto('https://shop.example/cart') and immediately calls page.click('#checkout'). | Pass wait_until='networkidle' or 'domcontentloaded' explicitly per the target's loading pattern. SPAs may need explicit wait_for_selector on a post-mount anchor — do not rely on the default 'load' for a JS-heavy cart. | Pass / FailAi Platformhigh |
| 02 | Form has input event listeners that validate on each keystroke (e.g., card-number spacing). Agent uses page.fill() and validation never fires. | Use page.type() (per-keystroke events) when the form depends on input events. Use fill() for non-event-driven fields (faster, atomic). Decide per field by inspecting the listener model via observe() or DOM inspection. | Pass / FailAi Platformmedium |
| 03 | Operator uses page.click('button.btn-primary') on a Tailwind site where the class is shared by 12 buttons. | Prefer Playwright's role/text-based locators (getByRole('button', {name:'Checkout'})) or Stagehand act() for resilience to class refactors. Avoid brittle class selectors as the primary target. | Pass / FailAi Platformhigh |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Browserbase
- Ai Platform
- Page Automation Primitives
Recommended for
Works with
Related evals
Claude API
Evaluates Anthropic's Batch API across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Extended Thinking across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
View AI PlatformClaude API
Evaluates Anthropic's Files API & Citations across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Foundation Model & API eval coverage.
ViewFrequently asked questions
What does the Page Automation Primitives eval for Browserbase Browserbase (cloud headless Chromium + Stagehand SDK) test?+
Evaluates Browserbase's Page Automation Primitives across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Browser Infrastructure for AI Agents eval coverage.
How is the Page Automation Primitives eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
How many test cases does this eval pack include?+
The Page Automation Primitives pack for Browserbase Browserbase (cloud headless Chromium + Stagehand SDK) contains 9 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Page Automation Primitives pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.