Langgraph Platform And Studio
LangSmith · LangSmith
LLM Observability & Evaluation Platform — LangSmith (LangChain)
Evaluates LangSmith's LangGraph Platform & Studio across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's LLM Observability & Evaluation Platform eval coverage.
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
Website
www.langchain.com/langsmithSample tests· showing 3 of 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Operator wants to deploy a LangGraph app to LangGraph Platform so traces land in LangSmith automatically. | Define langgraph.json with the graph entry, push via the LangGraph CLI / Platform UI, and link the deployment to a LangSmith project. LangGraph runtime emits traces using the same @traceable / RunTree machinery so the LangSmith UI shows node-level spans. [REQUIRES-VERIFICATION] on exact CLI flags a… | Pass / FailAi Platformhigh |
| 02 | A graph node requires human approval before proceeding (e.g., 'send email' step). Operator uses LangGraph interrupts. | Set an interrupt_before / interrupt_after for the gated node. The graph pauses with a recoverable checkpoint. Surface the pending state to the human via Studio or an integrated app; on approval, resume by passing the thread_id. The pause is fully recorded as a span in LangSmith. | Pass / FailAi Platformcritical |
| 03 | User has a multi-day conversation. Operator wants the LangGraph thread to persist state and the LangSmith Threads view to group all turns. | Use LangGraph's thread checkpointer (Postgres or built-in) with a stable thread_id keyed on the user/conversation. Every node run inside that thread carries the same thread_id metadata so LangSmith's Threads view groups all turns. Do not generate a new thread_id per turn. | 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
- Langsmith
- Ai Platform
- Langgraph Platform And Studio
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 Langgraph Platform And Studio eval for LangSmith LangSmith test?+
Evaluates LangSmith's LangGraph Platform & Studio across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's LLM Observability & Evaluation Platform eval coverage.
How is the Langgraph Platform And Studio 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 Langgraph Platform And Studio pack for LangSmith LangSmith 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 Langgraph Platform And Studio 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.