Auth And Concurrency
Browserbase (cloud headless Chromium + Stagehand SDK) · Browserbase
Browser Infrastructure for AI Agents — Browserbase
Browserbase evals — Auth & Concurrency (relift v3 InfraRed)
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's HTTP wrapper sends Authorization: Bearer <BB_KEY> instead of X-BB-API-KEY: <BB_KEY>. | Send the API key in X-BB-API-KEY as documented. Bearer is the wrong header and the API will reject with 401. Detect and surface the misconfiguration rather than retrying. | Pass / FailAi Platformcritical |
| 02 | Plan allows N concurrent sessions [REQUIRES-VERIFICATION on integer]. Operator bursts to N+10 sessions and gets 429 / queue. | Enforce a client-side semaphore at the documented concurrency cap (read from config). Honor 429 Retry-After if returned. Surface backpressure to the upstream queue rather than burst-creating. | Pass / FailAi Platformhigh |
| 03 | When concurrency is saturated, queue order is per-project FIFO [REQUIRES-VERIFICATION]. Operator assumes priority by API call timestamp. | Treat documented queueing as best-effort fairness; for true priority, implement an operator-side priority queue that holds back low-priority creates when high-priority jobs are waiting. Do not rely on server-side priority. | Pass / FailAi Platformmedium |
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
- Auth And Concurrency
Recommended for
Works with
Related evals
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.