---
title: "Anthropic | Skills We Assign For | Azendo"
description: "Building on Claude models — long context, tool use, and multi-provider strategy, plus the Azendo roles assigned for it."
url: "https://azendo.co/skills/anthropic/"
---

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

# Anthropic.

Anthropic provides the Claude family of language models through an API, with long context windows, tool use and strong instruction-following. It is commonly used alongside another provider rather than exclusively.

## Where Anthropic fits on a long engagement.

Long context changes what architectures are worth building. Where a shorter window forces aggressive retrieval and chunking, a long one allows whole documents or extended histories to be passed directly, which removes a substantial amount of machinery and a substantial number of failure modes with it.

Models differ in ways that only become visible on real workloads. One handles a structured extraction task more reliably, another follows a long instruction set more faithfully, and the difference is task-specific rather than general. Benchmarks are a weak guide; evaluation against your own data is the only reliable comparison.

## What an assigned team does with Anthropic.

Running more than one provider is increasingly the sensible default. It provides failover when one has an outage, negotiating position, and the ability to route different tasks to whichever model handles them best.

That only works if the application was built with a provider boundary, which is why the architecture matters more than the initial choice. How that is decided at scoping is described in [how an assignment runs](https://azendo.co/how-it-works/).

## What we use Anthropic for.

* Whole documents without chunking Long context removing retrieval machinery where the source fits directly.
* Tool use for real actions Models calling defined functions, with the boundaries of what they may do enforced in code.
* Routing tasks to the better model Per-task comparison on your own data rather than a single provider by default.

## How Anthropic capacity is assigned.

Model selection work is assigned under [managed ai services](https://azendo.co/services/ai-engineering/), with evaluation run against your data rather than decided from published benchmarks.

## Roles we assign Anthropic for

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

## 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 Anthropic 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/)