---
title: "LangSmith | Skills We Assign For | Azendo"
description: "LangSmith for LLM observability — tracing, datasets, evaluation, plus the Azendo roles assigned for it."
url: "https://azendo.co/skills/langsmith/"
---

[Skills](https://azendo.co/skills/) AI and machine learning 

# LangSmith.

LangSmith is an observability and evaluation platform for language model applications, capturing traces of every call, storing datasets, running evaluations and collecting feedback against production traffic.

## Where LangSmith fits on a long engagement.

Tracing is what makes a non-deterministic system debuggable. Seeing the exact prompt sent, the retrieved documents, the tokens consumed and the response returned for a specific failing request is the difference between diagnosing a problem and speculating about it.

Building datasets from production traces is the most valuable workflow it enables. Real failures become test cases directly, which means the evaluation suite reflects what actually goes wrong rather than what someone imagined might.

## What an assigned team does with LangSmith.

Traces contain user input, which means they contain personal data. Retention, access control and redaction need designing rather than accepting defaults, particularly under GDPR.

Treating observability data with the same care as any other personal data is a standard held by the assigned specialists, as set out in [how an assignment runs](https://azendo.co/how-it-works/).

## What we use LangSmith for.

* Failures diagnosed from the trace The exact prompt, context and response for a specific request, rather than a reproduction attempt.
* Test sets built from production Real failures captured as cases, so evaluation reflects reality.
* Trace data handled as personal data Retention and redaction designed, because user input is in every trace.

## How LangSmith capacity is assigned.

LLM observability is assigned inside AI capacity, with data protection for trace content designed rather than defaulted.

## Service lines it sits in

* [AI engineering](https://azendo.co/services/ai-engineering/)

Capacity is agreed as a committed monthly capacity across a discipline, not per skill.

## Related in ai and machine learning

* [PyTorch — skill we assign for](https://azendo.co/skills/pytorch/)
* [TensorFlow — skill we assign for](https://azendo.co/skills/tensorflow/)
* [scikit-learn — skill we assign for](https://azendo.co/skills/scikit-learn/)
* [Pandas — skill we assign for](https://azendo.co/skills/pandas/)
* [NumPy — skill we assign for](https://azendo.co/skills/numpy/)
* [embeddings — skill we assign for](https://azendo.co/skills/embeddings/)
* [function calling — skill we assign for](https://azendo.co/skills/function-calling/)
* [vLLM — skill we assign for](https://azendo.co/skills/vllm/)

## Tell us what your roadmap needs LangSmith for.

A service delivery manager replies with the disciplines we would assign, the monthly capacity and what the first month looks like.

[All skills we assign for](https://azendo.co/skills/)