> For the complete documentation index, see [llms.txt](https://examind.gitbook.io/v1/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://examind.gitbook.io/v1/feedback-machines/build-a-feedback-machine/content-dependencies.md).

# Content Dependencies

Some evaluation questions rely on material outside the student's submission — for example, a case study the assignment is built around, a template the work must follow, or a transcript the student responds to. Feedback Machines calls these **content dependencies**.

When you build a machine, the system scans your questions and flags any dependencies it detects.

## Why they matter

If a question depends on material the machine doesn't have, it can't evaluate that question as accurately. Providing the material lets the AI judge the work against the real source.

## Resolving dependencies

On the machine review page, each detected dependency is in one of three states:

* **Unresolved** — detected but not yet handled. You can resolve or dismiss it.
* **Resolved** — you've provided the material. You can update it anytime.
* **Dismissed** — you've acknowledged it but chosen not to provide it. You can restore it later.

To resolve a dependency, either **paste the text** or **upload a document** (`.docx`).

## Adding a dependency yourself

If the system didn't detect a dependency it should have, add one through the [Modify panel](/v1/feedback-machines/build-a-feedback-machine/modifying-a-feedback-machine.md) — for example, "please add a dependency for a case study and link it to all the analysis questions." You can remove dependencies there too.

{% hint style="info" %}
Dependencies aren't required to publish a machine — but resolving them improves the accuracy of the evaluation questions that rely on them.
{% endhint %}