In the news
New in LangSmith: Engine v2, Managed Deep Agents, Fine-Tuning, and more
LangChain · Published · 3 min read
In 30 seconds
- What happened
- LangSmith released Engine v2 with red teaming and automated fix validation, Managed Deep Agents with user-scoped memory and web search, Trajectories for readable session views, Fine-Tuning for open models, and Custom Apps for building interfaces.
- Why it matters
- Engineers building production agents need these tools to detect issues proactively, manage authentication and memory, debug long sessions, optimize model costs, and customize workflows.
- Watch out
- Self-hosted LangSmith BYOK support for Engine comes in a future release. Fine-tuning quality depends on trajectory data quality. Custom Apps require building against LangSmith APIs.
- agent
- fine-tun
- red team
Who else ran this
- Introducing LangSmith Fine-TuningLangChain
- New in LangSmith Engine: red teaming and automated testingLangChain
- Fine-tune on your LangSmith traces with Baseten LoopsBaseten
The same event, reported by other publishers we follow.
The patterns behind this
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.