Quentin Brosse

Building @LangChain

[David Duong @__dqbd]

Trace AI SDK 7 operations with LangSmith!

[LangChain @LangChain]

Introducing LangSmith Fleet: an enterprise workspace for creating, using, and managing your fleet of agents.

Fleet agents have their own memory, access to a collection of tools and skills, and can be exposed through the communication channels your team uses every day.

Fleet includes:
→ Agent identity and credential management with “Claws” and “Assistants”
→ Sharing and permissions to control who can run, clone, and edit (just like Google Docs)
→ Custom Slack bots so each agent has its own identity in Slack

Try Fleet: https://t.co/yhv7mZUV92
Read the announcement: https://t.co/5P0KXV9C7y

[Harrison Chase @hwchase17]

a lot of engineering orgs (Stripe, Ramp, Coinbase) are building internal cloud coding agents

we're releasing a fully OSS one today - every company should have the power of cloud agents at their fingertips

[LangChain @LangChain]

Introducing `langgraph deploy`

Deploy an agent to LangSmith Deployment with a single command.

$ uvx --from langgraph-cli@latest langgraph deploy

Go from prototype → production in minutes.

Try it today: https://t.co/wxXQ9TXORe

[Quentin Brosse @QuentinBrosse]

Agents will love LangSmith

[LangChain @LangChain]

🚀 Announcing LangSmith Skills + CLI 🚀

Agent improvements are increasingly driven by coding agents themselves.

We're releasing LangSmith Skills alongside the LangSmith CLI to make coding agents experts at the agent engineering lifecycle.

LangSmith Skills enable agents to debug traces, create datasets, and run experiments - and thanks to the CLI, agents are able to do it all natively through the terminal, where they're most comfortable.

Try out LangSmith Skills and the CLI with your own coding agents!

➡️ Skills: https://t.co/YTvRIA4jM3
➡️ CLI: https://t.co/7ouew7HQXF

[Quentin Brosse @QuentinBrosse]

new bird!

[LangChain @LangChain]

What? LangChain is evolving!

Meet our final form ➡️ https://t.co/f6eGVFchtB

[Harrison Chase @hwchase17]

https://t.co/3P7AZBO2XR

[Quentin Brosse @QuentinBrosse]

Shipped native tracing for Google ADK. Send feedback!

[LangChain @LangChain]

🔎 We shipped native tracing for Google ADK! See how easy it is to get started observing your ADK agents in LangSmith with just a few clicks.

LangSmith works natively with over 25 frameworks and providers, and not to mention OpenTelemetry! 🔥

Docs 👉 https://t.co/0dxpq8CFEr

[Quentin Brosse @QuentinBrosse]

LamgSmith is agnostic

[LangChain @LangChain]

👌 Tracing in LangSmith is as easy as copy/paste 📊

Get started in seconds with Claude Agent SDK, OpenAI, LangChain, Vercel AI SDK, and 20+ other frameworks. Pick your stack, copy the code, start debugging.

Docs: https://t.co/V1Xq96oaiP
Sign up for LangSmith: https://t.co/ufxGs8BdGv

[LangChain @LangChain]

LangSmith Agent Builder is generally available 🎉

It’s surprisingly easy to build agents now. Even a VC can do it…👇

Try it free: https://t.co/LbggOitARY
Read the announcement: https://t.co/Xn9d0jIG0d

[LangChain @LangChain]

🔥 New LangChain Academy Course: LangChain Essentials (Python & TypeScript) 🔥

Learn the basics of LangChain – our open source framework that makes it easy to start building agents with any model provider.

Last week, we released LangChain 1.0. We’ve completely rewritten LangChain to be opinionated, focused, and powered by LangGraph’s runtime. It includes a new `create_agent` abstraction to build agents quickly, middleware for flexibility, and standard content blocks that work across any model provider.

In this quickstart course, you'll learn how to:
- Build an agent with the `create_agent` abstraction
- Use LangChain’s core building blocks: Models, Messages, Memory, and Tools
- Customize your agent with middleware
- Debug and test your agent with LangSmith Observability & Evaluation

Enroll for free ➡️ https://t.co/Umv2VamSIw

[LangChain @LangChain]

We’ve heard your feedback loud and clear. Today, we’re launching 1.0 versions (in both Python and Typescript) of LangChain and LangGraph, the two most popular agent frameworks, based on what the community has been asking for.

• LangGraph: Low-level agent orchestration with built-in durable execution, memory, streaming, and human in the loop
• LangChain: Revamped to be more flexible — with a new `create_agent` template to build agents quickly, middleware for customizing behavior, and standard content blocks that work across any model provider

We’ve also unified all our docs (Python and TypeScript languages, as well as `langchain`, `langgraph`, and LangSmith) at https://t.co/cxRVTx6VbN. We know this has been a long time coming!

Read the full breakdown in this blog: https://t.co/tao4Nafpfs

[Quentin Brosse @QuentinBrosse]

@hwchase17 So proud to be part of this team! The next chapter will be wild, and the future of agent engineering bright. 🔥

[Quentin Brosse @QuentinBrosse]

brace yourself for the next chapter 🫡

[Quentin Brosse @QuentinBrosse]

@ZeroNocturn @0xBechilled 🌝

[Skribz @t_skribbles]

WHITELIST #Giveaway for a project I’ve been eagerly waiting for 👀 🪂🪙

How to win:

☑️ Follow @Airdrp_official 🚶🚶‍♀️

☑️ Retweet this post 🔄

☑️ Tag 2 friends 👥

DYOR https://t.co/ADANgsM315

⏰Winner will be announced on Thursday 📣

[Quentin Brosse @QuentinBrosse]

@cryptochampi0ns @0xBechilled @ZeroNocturn @soootaleb

[Quentin Brosse @QuentinBrosse]

@AfricanZoe Terraform for provisioning, Ansible for configuring

[Shreyas Doshi @shreyas]

3 types of product leaders:

1) The Operator

2) The Craftsperson

3) The Visionary

It is important for you as a startup founder or CEO, product manager, or a product leader to deeply understand these types, as you make decisions on whom to hire or whom to work for.

Thread👇🏾

[Alex Garcia 🔍 @alexgarcia_atx]

I’ve created a ton of marketing strategies.

I’ve studied thousands of marketing strategies.

And the common denominator in very successful marketing strategies is the use of the SAVE framework.

Squarespace has made a killin' using it.

Create a successful marketing strategy 🧵

[Quentin Brosse @QuentinBrosse]

@babbel I agree with her. Your app is great but has a new user, the Babbel keyboard generates a lot of friction. :/ Is it possible to let the user choose between native and Babbel keyboards in the app settings?

[Miss C-W @miss_scw]

@babbel I understand how to submit an answer. I don’t think you read the message properly. The keyboard is hard to type on because it’s not the same size as the iPhone keyboard and makes it too easy to make typos meaning I get answers wrong that I know.