Starting today, a @LangChain's Managed Deep Agent deploy provisions your Slack app for you 🤯
No manifest. No OAuth redirects. No bot tokens to copy around.
One command, and your agent says 👋 in Slack.
Plugged the new @shadcn chat components into @LangChain_JS Deep Agents and one-shotted a full code review agent.
One reviewer per file, local sandbox, streaming live. Wild how fast this was 😍
🧑💻 full demo: github.com/langchain-ai/s…
Agents are easy to demo locally. The hard part is shipping them inside a real app.
We published a deployment cookbook for @LangChain agents: full-stack examples with streaming UI, subagents, thread history, and production persistence notes across common JS frameworks 🚀
🧵👇
Deep Agent gives you a well tested and full featured harness with everything you need.
☝️However LangChain gives you the building blocks to re-create a smaller subset of it for specific tasks that don't need a full harness.
`createAgent` is one of these building blocks 📚
Creating custom subagent hierarchies has become super easy w/ @LangChain_JS 😊
Build a custom support harness with subagents as plain tool calls.
The supervisor decides when to delegate. The tool body invokes a named specialist agent, so your orchestration stays simple TS.
🧵👇
Do you know what your agent streams to the UI before it gets there?👀
We built stream transformers in @LangChain_JS so you can inspect and modify agent streams in-flight.
Redact sensitive data, reshape events, and emit custom channels before the frontend renders anything.
🧵👇