Harrison Chase
@hwchase17
Followers
76K
Following
13K
Media
520
Statuses
13K
@LangChainAI, previously @robusthq @kensho MLOps ∪ Generative AI ∪ sports analytics
Joined July 2014
OpenAI recently released a guide on building agents which contains some misguided takes. There's a lot of FUD, confusion, hype, and noise around agents. I wrote a blog on how to think about agent frameworks. Includes:. Background Info.- What is an agent?.- What is hard about
90
124
913
RT @modal_labs: This is happening tomorrow in NYC with @LangChainAI! 600+ people interested in coding agents 🤯.
0
3
0
RT @LangChainAI: 🤖📊 DataFrame Analyzer. Streamline your Pandas workflow with this LangChain solution using ChatOllama for local, private Da….
0
45
0
RT @LangChainAI: 🎛️ LangConnect: RAG Made Easy. A complete RAG management solution with Streamlit dashboard for document processing and vec….
0
89
0
RT @BraceSproul: The process of building an AI agent:. 1. Idea.2. Look for inspiration (open source examples, blogs).3. Build an MVP (empha….
0
7
0
RT @LangChainAI: 🎉 100K+ Students on LangChain Academy! 🎉. We're excited to celebrate this major milestone with all of you. Whether you're….
0
17
0
RT @diptanu: Event Driven systems are great for scalability. I have seen them get hard to maintain over time as more events are added to ad….
0
2
0
RT @LangChainAI: 🤓 Learn the basics of LangSmith 🤓. LangSmith is our unified observability & evals platform where teams can debug, test, an….
0
8
0
RT @LangChainAI: We’re honored to be named to the InfraRed 100 by @Redpoint, recognizing the top 100 companies transforming cloud infrastru….
0
4
0
RT @Hacubu: Fantastic reading for the long weekend if you want a conceptual breakdown of context engineering patterns!.
0
5
0
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?.
In my mind LLM "agents" are just event-driven programs (or as @karpathy would say "Software 3.0" programs). 1) They can receive new events (e.g. a "user message").2) Some events trigger a "computation" (i.e. an LLM request).3) This produces additional events (e.g. an "assistant.
27
16
132
RT @LangChainAI: LangChain now supports Claude Sonnet 4's citable search results - bringing proper source attribution to your RAG apps. ✨….
0
43
0
RT @zhanghaili0610: 🦜🔗 Just finished @LangChainAI's Building Ambient Agents with LangGraph Course! Check it out here: .
0
2
0
RT @QodoAI: Qodo Gen CLI automates the entire SDLC from the command line. @LangChainAI's LangGraph made it possible to trigger, inspect,….
0
4
0
RT @realshcallaway: Fresh from my talk at @arizeai Observe last week: We're at an inflection point in software engineering. AI is completel….
0
15
0
RT @latentspacepod: 🆕Information Theory for Language Models. Learning = Compression: @IlyaSut is known for taking….
0
12
0
RT @LangChainAI: We're hosting an AI Meetup in Amsterdam 🇳🇱that's all about multi-agent orchestration with special guest @nfcampos. rsvp:….
0
5
0
RT @LangChainAI: Context Engineering. "Context engineering" is a key part of agent building. We review a few popular patterns for context….
0
207
0
RT @LangChainAI: Define your agent logic once, then configure and deploy specialized versions on the fly with LangGraph Assistants. In thi….
0
34
0
RT @lgesuelli_p: With @TryArcade + @LangChainAI , that’s all possible. Users don’t need to deploy servers or deal with configs. No hardcod….
0
4
0