LangChain ships LangSmith Engine v2 with pre-production red teaming for agents
hwchase17 · x · 2026-09-25
Announced at Interrupt, LangSmith Engine v2 adds:
- Red teaming: the engine surfaces agent issues before they hit production
- Validated fixes: proposed fixes are tested by the engine itself before being shown to users
- Better issue detection: flags inefficient agent work and trends in metrics like cost and latency
The pitch: proactive agent QA instead of debugging traces after users complain.
Related event: LangChain Unveils LangSmith Engine v2 and Suite of Agent Updates(3 posts)→
More from coding & agent
- Where to draw the determinism boundary in LLM pipelines — aronchick · 2026-09-26
- The only pipeline shape that survives production: LLM proposes, rules dispose — aronchick · 2026-09-26
- 100-slot Terminal-Bench 2.1 rerun shows Luna 6 far behind Luna 5.6 — s1lverkin · 2026-09-26
- Qwen3.8-Omni-Flash: natively multimodal agent model with 1M-token context — dair_ai · 2026-09-26
- Que: open-source app queues all your waiting AI agent sessions in one place — Glad_Raspberry_6795 · 2026-09-26
- Zero-dependency LLM SDK lm15 1.0 hits PyPI, supports 10+ providers and already used by dspy — lateinteraction · 2026-09-26