> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/getting-started/core-ai-concepts.md).

# Core AI Concepts

These concepts help you build better workflows in StackAI. Start with prompting, then add retrieval and orchestration patterns.

{% hint style="info" %}
If you are new to LLM workflows, start with prompts and embeddings first.
{% endhint %}

### Start with the fundamentals

<table data-view="cards"><thead><tr><th>Concept</th><th data-card-target data-type="content-ref">Page</th></tr></thead><tbody><tr><td><strong>Prompt Engineering</strong><br>Write clearer instructions, structure prompts, and improve output reliability.</td><td><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/YyniJ9zfpaxKz2jmc8cn">/spaces/FSlso1Kjob5CLDrh0dVn/pages/YyniJ9zfpaxKz2jmc8cn</a></td></tr><tr><td><strong>Instruction vs Prompt</strong><br>Separate stable system behavior from task-specific user input.</td><td><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/IYDJEUNZKKCxmVYpq6C3">/spaces/FSlso1Kjob5CLDrh0dVn/pages/IYDJEUNZKKCxmVYpq6C3</a></td></tr><tr><td><strong>Embeddings</strong><br>Understand how text becomes vectors for semantic search and retrieval.</td><td><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/rHbvl2f6ab0YxwchTFBK">/spaces/FSlso1Kjob5CLDrh0dVn/pages/rHbvl2f6ab0YxwchTFBK</a></td></tr></tbody></table>

### Go deeper into retrieval and orchestration

<table data-view="cards"><thead><tr><th>Concept</th><th data-card-target data-type="content-ref">Page</th></tr></thead><tbody><tr><td><strong>Chunking</strong><br>Split content into useful units for stronger retrieval quality.</td><td><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/S8FXtl5a8zIJdsycEJP2">/spaces/FSlso1Kjob5CLDrh0dVn/pages/S8FXtl5a8zIJdsycEJP2</a></td></tr><tr><td><strong>Using Multiple LLMs</strong><br>Design workflows that route, compare, or chain multiple models.</td><td><a href="/spaces/FSlso1Kjob5CLDrh0dVn/pages/yLyBw6HoH9gCE2UUOy6v">/spaces/FSlso1Kjob5CLDrh0dVn/pages/yLyBw6HoH9gCE2UUOy6v</a></td></tr></tbody></table>

### Recommended order

1. Learn [Prompt Engineering](/getting-started/core-ai-concepts/prompt-engineering.md).
2. Learn [Instruction vs Prompt](/getting-started/core-ai-concepts/instruction-vs-prompt.md).
3. Learn [Embeddings](/getting-started/core-ai-concepts/embeddings.md) and [Chunking](/getting-started/core-ai-concepts/chunking.md).
4. Apply them in [Using Multiple LLMs](/getting-started/core-ai-concepts/using-multiple-llms.md).

### Next step

When you are ready to build, move into [Get Started with Workflow Builder](/getting-started/start-here/get-started-with-workflow-builder.md) or follow the [Stack AI Curriculum](/getting-started/learning/stackai-curriculum.md).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.stackai.com/getting-started/core-ai-concepts.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.