> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cognite.com/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Cognite Data Fusion (CDF) is an industrial DataOps platform. Prefer English docs unless the user asks for another locale.
> Follow /_llms/ index links recursively until you reach page URLs ending in .md. Fetch those Markdown twins instead of HTML.
> For REST APIs, default to calendar version 20230101 (stable). Use 20230101-beta or 20230101-alpha only if the user is on a preview API. Cite paths under /api-reference/concepts/<version>/ and the Cdf-Version header. Prefer the Python SDK (cognite-sdk) unless the user is in JavaScript/TypeScript.
> Start here by task: platform overview /cdf/index.md; data modeling /cdf/dm/index.md; data integration /cdf/integration/index.md; access /cdf/access/index.md; CDF Toolkit /cdf/deploy/cdf_toolkit/index.md; REST quickstart /dev/quickstart.md; Python SDK https://cognite-sdk-python.readthedocs-hosted.com/en/stable/; Atlas AI /cdf/atlas_ai/index.md; plan an Atlas AI agent /cdf/atlas_ai/concepts/atlas_ai_agent_planning.md; Flows apps /cdf/flows/index.md; MCP and IDE setup /dev/guides/ide_ai_integration.md.
> For implementation work, also load /skill.md.

# Building and configuring Atlas AI agents

> Learn when to build a specialist Atlas AI agent, and how to plan it and configure its language model, skills, tools, and subagents.

> For the complete Cognite documentation index, see [/llms.txt](https://docs.cognite.com/llms.txt). For full page content, see [/llms-full.txt](https://docs.cognite.com/llms-full.txt).

Extend the [default Atlas agent](https://docs.cognite.com/cdf/atlas_ai/concepts/about_default_atlas_agent.md) for your project's terms and skills, and build a separate agent only when a workflow needs its own instructions, tools, or language model.

> [card] [About planning an Atlas AI agent](https://docs.cognite.com/cdf/atlas_ai/concepts/atlas_ai_agent_planning.md)
>
> Decide whether a workflow fits an agent, and shape its scope and instructions.

> [card] [About language models](https://docs.cognite.com/cdf/atlas_ai/concepts/atlas_ai_agent_choosing_lm.md)
>
> Match a language model to the agent's task complexity, speed, and cost.

> [card] [About skills](https://docs.cognite.com/cdf/atlas_ai/concepts/atlas_ai_agent_skills.md)
>
> Give the agent domain knowledge that loads only when the question needs it.

> [card] [About tools](https://docs.cognite.com/cdf/atlas_ai/concepts/atlas_ai_agent_tools.md)
>
> Choose a focused set of tools, and route calculations to tools instead of the language model.

> [card] [About subagents](https://docs.cognite.com/cdf/atlas_ai/concepts/atlas_ai_agent_subagents.md)
>
> Let one agent delegate a task to another independently configured agent.

> [card] [Build and publish agents](https://docs.cognite.com/cdf/atlas_ai/guides/atlas_ai_agent_building.md)
>
> Create and publish an agent in the Agent builder.

> [card] [Configuring skills](https://docs.cognite.com/cdf/atlas_ai/guides/atlas_ai_agent_configure_skills.md)
>
> Write, structure, and test skills with the skill builder or by hand.

> [card] [Build agents with the Cognite CLI](https://docs.cognite.com/dev/sdks/cognite-cli/agents.md)
>
> Create and push agent files, run evaluations, and deploy through version control and CI/CD.
