LangSmith
LangChain provides LangSmith Harbor logs results to LangSmith LangSmith LLM Gateway SUPPORTS ScaleDown’s constrained decoding models (CDMs) LangSmith uses Jev API as a judge Open SWE -> SUPPORTS_PROVIDER -> LangSmith deepagents-cli stores all agent actions in LangSmith Nu is built on LangSmith LangSmith traces record data in LangSmith Engine, the trace analysis agent, is used in LangSmith to instrument the hill‑climbing loop More than 70% of Managed Deep Agents runs on LangSmith Managed Deep Agents v0.10 runs the browser in its own LangSmith sandbox. Managed Deep Agents v0.10 runs its browser in a LangSmith sandbox. Managed Deep Agents lets you build and deploy agents in LangSmith without running any infrastructure.· Entity summary generated by Graphiti
Relation timeline
BY VALID-FROM DATE- Managed Deep AgentsRUNS INLangSmith
Managed Deep Agents v0.10 runs the browser in its own LangSmith sandbox.
- Managed Deep AgentsBUILDS AND DEPLOYS AGENTS INLangSmith
Managed Deep Agents lets you build and deploy agents in LangSmith without running any infrastructure.
- EngineUSED INLangSmith
Engine, the trace analysis agent, is used in LangSmith to instrument the hill‑climbing loop
- Managed Deep AgentsRUNS ONLangSmith
More than 70% of Managed Deep Agents runs on LangSmith
- LangSmith tracesRECORDS INLangSmith
LangSmith traces record data in LangSmith
- NuBUILT ONLangSmith
Nu is built on LangSmith
- HarborLOGS RESULTS TOLangSmith
Harbor logs results to LangSmith
- LangChainPROVIDESLangSmith
LangChain provides LangSmith
- deepagents-cliSTORING ACTIONS INLangSmith
deepagents-cli stores all agent actions in LangSmith
- Open SWESUPPORTS PROVIDERLangSmith
Open SWE -> SUPPORTS_PROVIDER -> LangSmith
- LangSmithSUPPORTSScaleDown’s constrained decoding models (CDMs)
LangSmith LLM Gateway SUPPORTS ScaleDown’s constrained decoding models (CDMs)
- LangSmithUSESJev
LangSmith uses Jev API as a judge
- Managed Deep AgentsRUNS INLangSmith
Managed Deep Agents v0.10 runs its browser in a LangSmith sandbox.
Relations are facts Graphiti extracted from reports, not verbatim quotes. An end date means later reporting showed the relation no longer holds.
Events 7
- Managed Deep Agents v0.10: Browser Use and Async Subagents2 cited reports · 2026-10-30
- The Art of Loop Engineering1 cited report · 2026-10-29
- How to Build Proactive, Always-On Agents with the Schedules SDK in Managed Deep Agents1 cited report · 2026-10-29
- LangSmith LLM Gateway: Runtime Controls for Agents1 cited report · 2026-10-22
- How Numan Built an Eval-First AI Health Coach with LangGraph and LangSmith1 cited report · 2026-10-19
- The Most Common Questions About Agent Evals, Answered2 cited reports · 2026-10-15
- Open SWE: An Open-Source Framework for Internal Coding Agents1 cited report · 2026-10-14
Source reports 11
- Managed Deep Agents v0.10: Browser Use and Async SubagentsLangChain Blog · 2026-10-30
- Browser Use in Managed Deep AgentsLangChain Blog · 2026-10-29
- The Art of Loop EngineeringLangChain Blog · 2026-10-29
- How to Build Proactive, Always-On Agents with the Schedules SDK in Managed Deep AgentsLangChain Blog · 2026-10-29
- LangSmith LLM Gateway: Runtime Controls for AgentsLangChain Blog · 2026-10-22
- How Numan Built an Eval-First AI Health Coach with LangGraph and LangSmithLangChain Blog · 2026-10-19
- The Most Common Questions About Agent Evals, AnsweredLangChain Blog · 2026-10-15
- Improving Deep Agents with harness engineeringLangChain Blog · 2026-10-14
- Open SWE: An Open-Source Framework for Internal Coding AgentsLangChain Blog · 2026-10-14
- Building Long-Running Agents with ScaleDown and Deep AgentsLangChain Blog · 2026-10-13
- [AINews] TypeSafe/Jev at >$100M ARR, $7.5B valuation 3 weeks after launchLatent Space · 2026-10-10