Pinned
Stop manually triaging agent failures.
Let LangSmith Engine fix it.
00:00
LangChain
10.9K posts
LangChain
@LangChain
Joined November 2022
- LangSmith LLM Gateway ships with the controls enterprises told us they need first: ✅ Spend limits ✅ Spend visibility ✅ PII and secrets detection ✅ Trace continuity ✅ LangSmith Engine integration ✅ Audit logging ✅ Layered enforcement
- Replying to @LangChainAn inside look at the fastest way to ship a production Deep Agent
- The Managed Deep Agents runtime supports: ✅ Durable threads ✅ Streaming runs ✅ Checkpointing ✅ Human-in-the-loop workflows You can also use the API to create agents, update their configuration, create threads, and stream runs from your own product or platform workflow.
00:00 - LangSmith Engine goes beyond the addressing and diagnosis of problems, and actually works to fix them. A 1 minute explanation from @bentannyhill
00:00 - The @nebiusai Agent Blueprint’s open reference architecture connects proven components at each layer of the agent stack. We’re excited to have Deep Agents and LangSmith as part of it. Full announcement ⤵️Most #AIAgents don't fail because of the model. They fail because of the infrastructure around it. Introducing the Nebius Agents Blueprint: an open architecture for building, operating, and continuously improving agents in production. nebius.com/blog/posts/int…
- Getting both observability and enforcement used to mean stitching together: ✅ A separate gateway ✅ A guardrails platform ✅ An observability stack ...then correlating signals across all three when something went wrong. LLM Gateway puts both inside LangSmith.
- LangSmith Fleet template spotlight: Software Engineer Ships code from Slack, Linear, and GitHub in a sandbox A coding agent that takes issues from @linear, writes and verifies the code, and opens a PR. Triggered directly from Slack.
- Replying to @LangChainWe’re building SmithDB to solve the systems problems that come with agent observability. If that kind of infrastructure work sounds interesting, we’re hiring. Take a look at our open roles ⤵️
- How do you support full-text search JSON filtering over agent traces that span up to hundreds of MBs, while keeping a median (P50) latency of 400ms? Here’s an inside look at how we built a custom inverted index from scratch for SmithDB.
