Harrison Chase
@hwchase17
Followers
83K
Following
14K
Media
561
Statuses
14K
@LangChainAI, previously @robusthq @kensho MLOps ∪ Generative AI ∪ sports analytics
Joined July 2014
🔥Today we’re excited to announce new funding for LangChain (at a $1.25B valuation) to allow us to build the platform for agent engineering. LangChain started as a single Python package 3 years ago. Since then, we’ve evolved into a comprehensive platform for agent engineering
169
129
888
In case you haven't been following.... LangGraph.js just passed 1,000,000 downloads a week! This is double the weekly downloads from just 40 days ago! The team has been working insanely hard on making LangGraph the best agent orchestration framework out there, and the download
0
3
4
Come watch us yap about voice agents!
Voice agents are hard to build. We see two architectures dominate: 1. STT → LLM → TTS (the "sandwich") 2. Speech-to-speech (realtime) Both have trade-offs. The sandwich is model-agnostic, and you can extend existing text agents without rewiring it. But stitching together
0
1
4
For everyone out there in the trenches building voice agents… 🗣️ for everyone fighting to get that last 20% right… for everyone who still wonders how to do observability + evals the right way… 📈 @huntlovell just dropped a fantastic primer on building production-ready voice
Come watch us yap about voice agents!
0
1
5
When you spend enough time watching agents break in the weirdest, least predictable ways… you start to design differently. That’s why we built createAgent and middleware the way we did — to make the actual agent-engineering loop (ship → observe → refine) less painful and more
Agent engineering: A new discipline Traditional software assumes known inputs and predictable behavior. Agents give you neither. That’s why teams shipping reliable agents are adopting a new discipline: agent engineering. Agent engineering is driven by a few core ideas: 🔹
2
2
7
Deep Agents represent a shift in how AI systems operate – unlike simple chatbots or basic RAG applications, these agents run for extended periods, execute multiple sub-tasks, and make complex decisions autonomously. In this webinar, we'll dive into practical approaches for
luma.com
Join us for an online webinar exploring the unique challenges of observing and evaluating Deep Agents in production. Deep Agents represent a shift in how AI…
2
2
39
Dexter is now 73% faster. What changed: • simpler task planning • cached tool outputs • shorter summaries LLM calls dropped by more than half. Costs dropped too. Next: smarter model selection so each task uses the right LLM.
11
31
243
Want to see AI-first at scale? Check out Thomas Menard and the rockstar team at @LOrealParisUSA showing us how it’s done. Embracing AI to drive “idea to impact” in less than 90 days for a 100,000 person enterprise is impressive. To do it in May 2024 is outrageous. My man
0
2
4
In case you haven't been following.... LangGraph.js just passed 1,000,000 downloads a week! This is double the weekly downloads from just 40 days ago! The team has been working insanely hard on making LangGraph the best agent orchestration framework out there, and the download
1
2
11
Let’s go!!!! 🚀🎉
In case you haven't been following.... LangGraph.js just passed 1,000,000 downloads a week! This is double the weekly downloads from just 40 days ago! The team has been working insanely hard on making LangGraph the best agent orchestration framework out there, and the download
0
2
4
i wrote this post after a great discussion w/ @peakji abt context engineering in @ManusAI. Peak’s slides + video link below! https://t.co/88c1ooe82h
This is a very good post on agent design https://t.co/pEbNUJsOme
5
25
226
Join Harrison Chase and Nick Huang in a deep dive into practical approaches for gaining visibility into Deep Agent behavior and measuring their effectiveness using LangSmith. RSVP: https://t.co/cKzWg0fn82
5
10
61
Voice agents are hard to build. We see two architectures dominate: 1. STT → LLM → TTS (the "sandwich") 2. Speech-to-speech (realtime) Both have trade-offs. The sandwich is model-agnostic, and you can extend existing text agents without rewiring it. But stitching together
8
40
361
Agent engineering: A new discipline Traditional software assumes known inputs and predictable behavior. Agents give you neither. That’s why teams shipping reliable agents are adopting a new discipline: agent engineering. Agent engineering is driven by a few core ideas: 🔹
11
63
395
Reminds me of: Agents should be more opinionated by @Vtrivedy10
https://t.co/evb6D39hJm
vtrivedy.com
The best agent products aren't the most flexible, they're the most opinionated. Learn why agents need fewer knobs, not more, and how to design around model intelligence spikes.
1
1
20
🔌 LangChain MCP Adapters 0.2.0 is out! This new release features: 🖼️ Multimodal tool support using LangChain’s standard content blocks ❓Elicitation support via callbacks 🏗️ Structured content for tools, stored as an artifact on tool results 🛠️ Tool name prefixes, preventing
docs.langchain.com
5
16
110
❓How are evals and observability different from AI agents compared to simpler LLM applications? Come join me and Nick this Thursday as we discuss patterns we are seeing in the wild Will be a combo of presentation with a chunk of Q&A at the end! https://t.co/XfOq4d2VPu
6
10
66
Introducing Dexter 2.0 Open source. Built for financial research. Like Claude Code, but for stocks. What Dexter does: • plans tasks • runs on its own • validates its work • researches stocks It uses OSS tools like @LangChainAI, with a fresh stack of typescript, react,
95
316
3K
Join Jason Ginsberg (Head of Engineering, Product at @cursor_ai) and Harrison Chase (Co-founder and CEO, LangChain) as they discuss coding agent UX, building with Cursor, and trends heading into 2026. This will be an in-person event in San Francisco! RSVP:
2
4
51
Understanding how agents behave and how to improve their quality isn’t straightforward. Our "Getting Started with LangSmith" video series shows you can use LangSmith for: • Observability to understand what your agent is doing • Evaluation to track quality and catch regressions
6
11
86