←
Sam Crowder545 posts
Sam Crowder avatar

Sam Crowder

@samecrowder

Head of Product, LangSmith at @LangChain 🚀 | prev: @Harvard MS/MBA, @RocksetCloud (acq. OpenAI), @BainCapVC, @ContraryCapital

◷ Joined September 2017▧ 48 Photos and videos
Sam Crowder avatar
Sam Crowder@samecrowder·5h

I remember when @hwchase17 built deepagents as a weekend project fall of last year. Fast forward one year later and it's the industry standard for building intelligent agents with full model agnosticism! Awesome to see this milestone.

deepagents just hit 50M downloads!!! we started it a bit over a year ago, back before "harness" was an industry term we bet on a provider agnostic, open source harness for production agents that can take on long running, complex work in any domain github.com/langchain-ai/deep…

0:08
LangChain avatar
⟳ Sam Crowder retweeted
LangChain@LangChain·Nov 16

Meet the new LangSmith Agent Platform: a single place to build, run, improve, and govern every agent across your org. Head of Product @samecrowder on: 1️⃣ Why we reorganized it 2️⃣ How the agent model works 3️⃣ What it unlocks 4️⃣ Where it’s going next langchain.com/blog/we-rebuil…

Sam Crowder avatar
Sam Crowder@samecrowder·Nov 13

Our mission is to enable every company to own its intelligence. We're excited to announce $300m more raised in order to make that dream a reality!

Today we announced that LangChain raised $300M at a $3B valuation. We think agents will transform the economy, and the companies that own their intelligence will build lasting competitive advantages. That's why we're building LangSmith, the framework-agnostic platform to run, improve, and govern agents. Still so much left to build! More on what’s next: langchain.com/blog/series-c

1:57
Caspar avatar
⟳ Sam Crowder retweeted
Caspar@caspar_br·Oct 22

How do you build an adaptive company harness? If you've built a company megazoid agent, every team will end up wanting something different from it. E.g. finance needs billing skills while the platform team needs incident MCP server. You will inevitably face a context bloat problem when your agent loads hundreds of tools/skills/resources that have nothing to do with the request Solution is to use a factory! In Managed Deep Agents you can build your agent from a function instead of a fixed definition. That function runs at the start of every run with all relevant context, so you can load a different model/skills/tools/sandbox/memory/etc. to suit each team's needs

Post attachment
Sam Crowder avatar
Sam Crowder@samecrowder·Oct 8

This was a fun conversation with @jaminball and @palak_go from Altimeter about System One models! We're very excited about this new class of model at LangChain and are seeing all kinds of applications for them from model routing at the harness level to scoring traces for online evaluation.

Next up on First Pass: a conversation with @samecrowder from @LangChain on decision models. Jev from @typesafeai took the world by storm. Then OpenAI and Databricks released producs (Decisions API and ai_decide function) So what are Decision Models? We dig in!

11:12
Harrison Chase avatar
⟳ Sam Crowder retweeted
Harrison Chase@hwchase17·Sep 29

No

it's crazy how far out the labs are building at the application layer on the one hand it makes sense, on the other hand do you really want all of your company knowledge, docs, workflows built so locked in to a single model?

Sam Crowder avatar
Sam Crowder@samecrowder·Aug 18

Online evals are difficult to set up correctly. Even if you know what you want to look for, it's an optimization question of which model to choose, how to tune the prompt, and how to think about the cost trade off of adding more LLM spend on top of each agent run. LangSmith Tuned Evaluators makes this much easier!

Introducing LangSmith Tuned Evaluators They automatically score agent behavior in production, starting with Perceived Error. Perceived Error is one of the clearest signals that your agent is giving users a helpful experience. In our benchmark, our specialized model outperformed every frontier model we tested and reduced evaluation cost by 82%. Learn more: langchain.com/blog/introduci…

Harrison Chase avatar
⟳ Sam Crowder retweeted
Harrison Chase@hwchase17·Aug 14

some great new LangSmith docs on traces vs threads vs trajectories (new concept) observability data is no longer just for observability - its also for memory & learning having a really clear mental model of this data is incredibly helpful! docs.langchain.com/langsmith…

Post attachment
Julia Schottenstein avatar
⟳ Sam Crowder retweeted
Julia Schottenstein@j_schottenstein·Jun 29

the most common FUD our competitors throw against LangSmith is that it only works if you use our open source. but actually as of this month, a MAJORITY of our active self-serve customers build without a LangChain open source framework / harness. LangSmith is model, framework, and cloud neutral, and we have the numbers to show it!

David Duong avatar
⟳ Sam Crowder retweeted
David Duong@__dqbd·Jun 26

Trace AI SDK 7 operations with LangSmith!

Post attachment
AI SDK@aisdkJun 25

Trace AI SDK operations across your app by registering telemetry once and sending traces to your observability provider.

Post attachment
Sam Crowder avatar
Sam Crowder@samecrowder·Jun 16

a great thread about online evals and why everyone should be running them!

Importantly, this lets us monitor the agent's live performance (akin to observability), see trends over time, and get alerted when a metric drops below a threshold. Combining heuristic functions and LLM-as-a-judge implementations lets us capture both hard and fuzzy metrics from live usage that may not surface in a controlled, offline experiment.

Post attachment
Sam Crowder avatar
Sam Crowder@samecrowder·Jun 2

increasingly a company's ability to scale AI systems is limited by willingness to pay for tokens at the high end but you can use langsmith tracing and experiments to optimize costs and get the right balance. our team enjoyed collaborating with @harvey on this one!

LangChain @LangChain Jun 2 Article Designing Efficient Verifiers for Legal Agents with Harvey A LangChain Labs x Harvey study measuring and designing efficient verifiers for legal agents. Read on the LangChain blog. Authors: @Vtrivedy10 (LangChain), @jakebroekhuizen (LangChain), @hwchase17

swyx avatar
⟳ Sam Crowder retweeted
swyx@swyx·Jun 1

Langsmith Engine is the "Full Self-Driving" moment for AI Engineering

Sam Crowder avatar
Sam Crowder@samecrowder·May 29

LLMs clearly make for an amazing business today, but they are also the fastest depreciating asset in history. And open models have a lot to do with that. This is why the labs are moving more into the application and deployment layers. At LangChain, we love working with teams building on both closed and open models!

The latest finding in the LangSmith Signal: Open Models are having a moment. 1 in 3 AI teams ran an open-weights model in April 2026, up from 1 in 5 nine months ago. The overall number of teams using open weights grew 3x. We’re seeing newer users choose open models at a higher rate than those who came before.

Post attachmentPost attachmentPost attachmentPost attachment
Adam Łucek avatar
⟳ Sam Crowder retweeted
Adam Łucek@AdamRLucek·May 26

Trace data is literally worth its weight in gold these days, if you know what to do with it! As has been established, creating effective agents requires shipping early, observing behavior, and iterating quickly. At the core of this are your agent traces capturing exact inputs, outputs, steps, and metadata along the way. Analyzing traces helps surface inefficiencies and areas for improvement, but they can also be used in more sophisticated ways to set up robust evaluations. Here's two of the ways we use traces to build evals for production agents 👇

Post attachment