# Define phase requirements

## What are requirements?

Requirements are specific objectives that need to be met to complete a project phase. They act as clear, actionable goals for your team.

### Why define requirements?

* **Clarity:** Provides team members with a clear understanding of expectations.
* **Focus:** Helps teams concentrate on essential goals, boosting efficiency.
* **Progress Tracking:** Allows for monitoring of achievements against set objectives.

## Create requirements

To create requirements, select <img src="/files/ck3unLiQ0Xa0OmayoN5Q" alt="" data-size="line"> and enter the name and description.

**Best Practice:**

* Be concise and clear in your descriptions.
* Make these requirements specific, measurable, achievable, relevant, and time-bound (SMART).
* Clearly communicate these requirements to your team. Ensure everyone understands what is expected and why it's important.

<figure><img src="/files/P7hmFEtm5rXEkxHe47ot" alt=""><figcaption></figcaption></figure>

## Use requirements to structure future iterations

The 'Use requirements to structure future iterations' setting allows you to use those requirements as a way to structure your iteration work in your notebook.

It is an advanced feature, so to learn more about iterations and sections, view our [Iterations introduction guide](/glossary/concepts/iterations.md).

### How to enable this setting

1. Go to the requirements settings by clicking the <img src="/files/I46fPGZzK6eUPzabVHex" alt="" data-size="line">.
2. Enable the "Use requirements to structure future iterations" option.

<figure><img src="/files/Q4W5iAOedOtNmpBvoBO2" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: 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:

```
GET https://docs.vectice.com/manage-ai-ml-projects/define-phase-requirements.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.