Brace (@bracesproul) 's Twitter Profile
Brace

@bracesproul

AI at @LangChainAI ~ Interested in agents, drones and rockets.

ID: 797465269

linkhttps://github.com/bracesproul calendar_today02-09-2012 04:03:16

1,1K Tweet

3,3K Followers

561 Following

LangChain (@langchainai) 's Twitter Profile Photo

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks.

Brace (@bracesproul) 's Twitter Profile Photo

In this edition of Agent Activities, I'll be discussing how to handle "agent rabbit-holing". More specifically, how I designed my coding agent to handle repeated errors from the tool calls it generates. The problem: When building a coding agent, you obviously need to give it

Brace (@bracesproul) 's Twitter Profile Photo

The new way Google shows ads is actually insane The *entire* first page view is sponsored results, with no ad indication next to the individual links

The new way Google shows ads is actually insane

The *entire* first page view is sponsored results, with no ad indication next to the individual links
LangChain (@langchainai) 's Twitter Profile Photo

🎥New Video: How to Build an Agent with Auth and Payments AI Services often track LLM requests via credits. We just released a video showing how to build a LangGraph.js app that does exactly this! It has: - 💰Stripe for payments - 🔐Supabase for auth & credits - 💬LangGraph

🎥New Video: How to Build an Agent with Auth and Payments

AI Services often track LLM requests via credits. We just released a video showing how to build a LangGraph.js app that does exactly this!

It has:
- 💰Stripe for payments
- 🔐Supabase for auth & credits
- 💬LangGraph
Brace (@bracesproul) 's Twitter Profile Photo

I'm super excited to see this video & repo get released!! Anyone who's building an AI app, and wants to monetize it should 100% checkout this video & template. There aren't really any good fully open source examples showing how to build an app like this, so we wanted to release

Harrison Chase (@hwchase17) 's Twitter Profile Photo

🔒How to Build an Agent with Auth and Payments Fullstack agent application! Not only can LangGraph + LangGraph Platform help you build agents, it can also help you deploy them and supports custom auth and middleware for usage tracking Video: youtube.com/watch?v=4Z2uBt…

🔒How to Build an Agent with Auth and Payments

Fullstack agent application!

Not only can LangGraph + LangGraph Platform help you build agents, it can also help you deploy them and supports custom auth and middleware for usage tracking

Video: youtube.com/watch?v=4Z2uBt…
Harrison Chase (@hwchase17) 's Twitter Profile Photo

Deep research is becoming a pretty common use case for gen AI agents Read how Exa built and launched one with LangGraph/LangSmith!

Harrison Chase (@hwchase17) 's Twitter Profile Photo

This is langgraph Most people think of langgraph as agent abstractions, but it’s powered by a low level event driven framework under the hood If we exposed that - would people be interested? Or focus more on agent abstractions?

Brace (@bracesproul) 's Twitter Profile Photo

Something interesting I see sonnet 4 do a lot is create *.backup files during codegen. For whatever reason it often worries about losing a file, or needing to revert after making a change (although I never see it use the backup file after creating it)

LangChain (@langchainai) 's Twitter Profile Photo

🎉 100K+ Students on LangChain Academy! 🎉 We're excited to celebrate this major milestone with all of you. Whether you're building your first LLM-powered app or scaling your production agent, thank you for learning with us 🤓 Our new Ambient Agents course teaches you how to

🎉 100K+ Students on LangChain Academy! 🎉

We're excited to celebrate this major milestone with all of you. Whether you're building your first LLM-powered app or scaling your production agent, thank you for learning with us 🤓 

Our new Ambient Agents course teaches you how to
LangChain (@langchainai) 's Twitter Profile Photo

🎛️ LangConnect: RAG Made Easy A complete RAG management solution with Streamlit dashboard for document processing and vector search. Built with PostgreSQL/pgvector, it offers real-time processing, multi-type search, and secure authentication. Check it out here 🚀

🎛️ LangConnect: RAG Made Easy

A complete RAG management solution with Streamlit dashboard for document processing and vector search. Built with PostgreSQL/pgvector, it offers real-time processing, multi-type search, and secure authentication.

Check it out here 🚀
Brace (@bracesproul) 's Twitter Profile Photo

The process of building an AI agent: 1. Idea 2. Look for inspiration (open source examples, blogs) 3. Build an MVP (emphasis on minimum) 4. Write evals & look at your data!!! 5. Based on the MVP & eval results, build it out to be much more involved to improve results (will

Brace (@bracesproul) 's Twitter Profile Photo

So this is definitely a bad thing since it means the authors aren’t reading over their papers. But do people think using LLMs to write papers in general is a bad thing? If you do the research, but use an LLM to compile it all into a paper, and re-read to ensure it didn’t

Brace (@bracesproul) 's Twitter Profile Photo

Why is YouTube’s “Jump ahead” feature for skipping in video ads only available when watching online? When I download videos & watch offline it doesn’t appear. I can’t imagine they’re determining what part of the video is an ad on the fly… so why doesn’t it work offline?