Pinned
Stop manually triaging agent failures.
Let LangSmith Engine fix it.
00:00
LangChain
11K posts
Joined November 2022
- LangChain repostedEvery agent will need a sandbox by the end of the year (trust me bro). @jakebroekhuizen and I break down why they're necessary and what you'd use them for in the latest edition of spill da 🫖!00:00
- 00:00
- LangChain repostedwe've been running this on our own on-call for weeks. it triages alerts, handles tickets, sends us weekly analytics, and gets sharper every week. try it today in Fleet and make it yours!Introducing On-Call Copilot - a new agent template in LangSmith Fleet → Triages every alert and investigates root cause across your code and traces → Manages tickets and routes every incident to the right channels → Continuously learns from your runbooks, escalation rules,00:00
- LangChain repostedMore integrations with LangChain coming soon!LangSmith sandboxes are now a first-class environment in @harborframework 🚀 Install: pip install “harbor[langsmith]” Authenticate: export LANGSMITH_API_KEY= “<LANGSMITH_API_KEY>” That's it. Your evals are now ready to run in LangSmith production sandboxes, alongside Daytona,
- LangSmith sandboxes are now a first-class environment in @harborframework 🚀 Install: pip install “harbor[langsmith]” Authenticate: export LANGSMITH_API_KEY= “<LANGSMITH_API_KEY>” That's it. Your evals are now ready to run in LangSmith production sandboxes, alongside Daytona,A few things that went into this: → Full Dockerfile snapshot support: point Harbor at your task's environment/Dockerfile and it builds, caches, and reuses snapshots automatically → SDK profile support: you can target different environments without config changes → Entire
- Fine-tuning open models can exceed or match frontier models. 📦Base @Alibaba_Qwen out of the box w/ good prompting: Strong for perceived error classification, trailed frontier model performance. 🔧With a LoRA SFT job: Both models came close to or above frontier performance.We teamed up with @FireworksAI_HQ to answer the following question… How can we cost-effectively mine important signals from every single trace, while maintaining frontier performance? Read our LangChain Labs study ⤵️
- Deep Agents deep dive part 3 | Delegation TLDR: A planning tool that allows the model to organize work for challenging tasks. Equipped with subagent support out of the box. A 90 second explanation from @sydneyrunkle00:00
- We have 3 LangChain meetups coming up in the next month! Find one in your city and register here 👉 luma.com/langchain 📍 6/22: Chicago with @focused_dot_io and @united 📍 6/24: SF with @usehercules 📍 7/16: Berlin with @Zalando
- .@benchling Head of AI @nlarusstone on why understanding LLMs is closer to biology than software engineering.00:00Watch the full conversation with @nlarusstone and @hwchase17 on the latest episode of Max Agency. ⏯️ YouTube: youtube.com/watch?v=RjpTrf… 🎧 Apple Podcasts: podcasts.apple.com/us/podcast/the… 🎧 Spotify: open.spotify.com/episode/2bFEj2…
- LangChain repostedWhen Box transitioned Box AI into a multi-step agentic system, we chose @LangChain's LangGraph over building a custom execution engine from scratch. Our full architectural breakdown covers how agents are defined and compiled at runtime, how the Global Agent spawns sub-agents
- LangChain repostedAn on call agent, pre-built and ready to go in Fleet! Try out our newest template:Introducing On-Call Copilot - a new agent template in LangSmith Fleet → Triages every alert and investigates root cause across your code and traces → Manages tickets and routes every incident to the right channels → Continuously learns from your runbooks, escalation rules,00:00
- Introducing On-Call Copilot - a new agent template in LangSmith Fleet → Triages every alert and investigates root cause across your code and traces → Manages tickets and routes every incident to the right channels → Continuously learns from your runbooks, escalation rules,00:00Try it today: fleet.langchain.com
