Session Persistence And Recovery
Browserbase (cloud headless Chromium + Stagehand SDK) · Browserbase
Browser Infrastructure for AI Agents — Browserbase
Evaluates Browserbase's Session Persistence & Recovery 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 | Operator wants the next session to start already-logged-in to a SaaS dashboard. | Create a Context via the documented Contexts API (or SDK). Pass contextId on POST /v1/sessions to attach. The session boots with the prior cookies + localStorage. Persist contextId per tenant in operator storage. | Pass / FailAi Platformhigh |
| 02 | Two tenants share an operator backend. Operator looks up contextId by user email but key collisions cause tenant A to resume tenant B's session. | Key context storage by (tenant_id, user_id, target_domain). Never key only by email. Validate the resumed session against the expected tenant identity before exposing the browser back to the user. Treat any mismatch as a security incident. | Pass / FailAi Platformcritical |
| 03 | Saved contextId has not been used for the documented retention window [REQUIRES-VERIFICATION on exact TTL]. POST /v1/sessions with that contextId errors. | Detect retention-expiry error specifically, fall back to fresh login flow, and create a new Context on success. Do not retry the same expired contextId — that burns concurrency slots. | 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
- Session Persistence And Recovery
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 Session Persistence And Recovery eval for Browserbase Browserbase (cloud headless Chromium + Stagehand SDK) test?+
Evaluates Browserbase's Session Persistence & Recovery 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 Session Persistence And Recovery 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 Session Persistence And Recovery 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 Session Persistence And Recovery 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.