# How LangChain uses Baseten

As published on [baseten.co](https://www.baseten.co/resources/customers/langchain). Captured by usedby on 2026-11-07.

- Company: [LangChain](https://www.usedby.ai/companies/langchain.md)
- Tool: [Baseten](https://www.usedby.ai/tools/baseten.md)
- Industry: [DevTools & Infrastructure](https://www.usedby.ai/companies/industry/devtools-infrastructure.md)
- Teams: LangChain Labs

## The use case: how LangChain deploys Baseten

LangChain uses Baseten Loops to fine-tune custom open-weight models for LangSmith Engine, its in-platform agent that helps users debug and improve their agents. Models are trained on agent traces for tasks like diagnosing issues from a GitHub repository and categorizing traces, then deployed through Baseten's inference platform.

Summary written by usedby from the source page, in English. The figures are those of Baseten and LangChain, not ours.

> Fine-tuning a large open-weight model on agent traces specializes it for difficult tasks in LangSmith Engine, such as reading a connected GitHub repository to diagnose why an issue is happening, then drafting the prompt or code change that goes into the pull request.

> Baseten is a key partner as we develop the models behind LangSmith Engine. Loops gives us the control and iteration speed we need while training, backed by a team that works closely with us. Having training and inference on the same platform gives us a clear path from model development to production.
>
> Jake Broekhuizen, Applied Research Lead, LangChain Labs

Source: [baseten.co](https://www.baseten.co/resources/customers/langchain), captured 2026-11-07.

## Other AI tools used by LangChain

- [Hex](https://www.usedby.ai/tools/hex.md) — Confirmed
- [Daytona](https://www.usedby.ai/tools/daytona.md) — Observed
- [Pylon](https://www.usedby.ai/tools/pylon.md) — Observed
- [Rillet](https://www.usedby.ai/tools/rillet.md) — Observed
- [Tabs](https://www.usedby.ai/tools/tabs.md) — Observed

## Baseten users in DevTools & Infrastructure

- [OpenCode](https://www.usedby.ai/companies/opencode.md) — Confirmed
- [Superhuman](https://www.usedby.ai/companies/superhuman.md) — Confirmed
- [Zed](https://www.usedby.ai/companies/zed.md) — Confirmed
- [LiveKit](https://www.usedby.ai/companies/livekit.md) — Declared by the company
- [Plane](https://www.usedby.ai/companies/plane.md) — Declared by the company
- [Replit](https://www.usedby.ai/companies/replit.md) — Declared by the company

## What usedby checked

We compared the story with its live page on 2026-11-07.

- Checked: the passage quoted above is copied word for word from the page, near the name of LangChain.
- Checked: LangChain uses Baseten. Confirmed line. Latest check across sources: 2026-11-07.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/langchain-baseten · How we check: https://www.usedby.ai/methodology