Eval Library
L
For LangSmithAI Platform

Workspaces Rbac Billing

LangSmith · LangSmith

LLM observability and evaluation — LangSmith

LangSmith evals — Workspaces, RBAC & Billing (relift v3)

About LangSmith

LangSmith is LangChain's LLM observability and evaluation platform: tracing, datasets, evaluators (LLM-as-judge, code, and human), experiments, prompt management, and online monitoring used by AI teams to measure and improve LLM apps in production.

Employees

~200

Industry

LLM Observability

Headquarters

San Francisco, CA

Sample tests· showing 3 of 9

#InputExpected behaviorCheck
01

Key must write traces/experiments but not delete datasets.

Create key in Settings → API Keys scoped to workspace; store in CI secret; rotate; never commit langsmith key to repo.

Pass / FailAi Platformcritical
02

Rotation scheduled; dual-key period needed for CI and prod workers.

Provision new key; dual-write period; update secrets; revoke old after drain; monitor 401 on ingestion.

Pass / FailAi Platformhigh
03

Procurement needs exact retention days for contract appendix.

State exact Plus plan retention days vary by marketing vs contract and are [REQUIRES-VERIFICATION]; point to FAQ/trust docs; do not invent 30/90 day numbers without source.

Pass / FailAi Platformmedium

How this eval is graded

Grade against expected.ideal_behavior and expected.rubric. Penalize failure_modes.

Rubric criteria

  • Langsmith
  • Ai Platform
  • Workspaces Rbac Billing

Recommended for

LangSmithLangSmith customers

Works with

Related evals

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.