In the news
New in LangSmith Engine: red teaming and automated testing
LangChain · Published · 3 min read
In 30 seconds
- What happened
- LangSmith Engine v2 adds red teaming to proactively find agent bugs, detects inefficiencies and performance trends, and auto-validates fixes before deployment.
- Why it matters
- Matters for engineers building LLM agents who want to catch issues before production and accelerate the fix-and-deploy cycle.
- Watch out
- Red teaming and auto-validation are in private beta for LangSmith Deployment users only; self-hosted support coming later.
- agent
- red team
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.