# Creating your first project

The primary interface for creating, manipulating, and executing Prism projects is the command line. The full list of commands are described in detail in the [CLI](/v0.2.3/cli/command-line-interface.md) section.

To create your first Prism project, navigate to your folder of choice and run the following command:

<pre><code><strong>$ prism init --project-name my_first_project
</strong>--------------------------------------------------------------------------------
&#x3C;HH:MM:SS> | INFO  | Running with prism v0.2.3...

&#x3C;HH:MM:SS> | INFO  | Creating project directory...
 
      ______
   ____  __ \_____(_)________ _______
 _____  /_/ / ___/ / ___/ __ `__ \ ____
____ / ____/ /  / (__  ) / / / / / _____
 ___/_/   /_/  /_/____/_/ /_/ /_/  ___

Welcome to Prism, the easiest way to create clean, modular data pipelines
using Python!

To get started, navigate to your newly created project "my_first_project" and try
running the following commands:
    prism compile
    prism run

Consult the documentation here for more information on how to get started.
    docs.runprism.com

Happy building!
--------------------------------------------------------------------------------
$
</code></pre>

Again, the [CLI](/v0.2.3/cli/command-line-interface.md) section gives a much more comprehensive overview of how to use the command line to manipulate projects. But, if you're itching to get started and you want to execute this project right away, then navigate to that directory and use `prism run`:

```
$ cd my_first_project
$ prism run
--------------------------------------------------------------------------------
<HH:MM:SS> | INFO  | Running with prism v0.2.3...
<HH:MM:SS> | INFO  | Found project directory at /my_first_project
 
<HH:MM:SS> | INFO  | RUNNING 'parsing prism_project.py'.............................................. [RUN]
<HH:MM:SS> | INFO  | FINISHED 'parsing prism_project.py'............................................. [DONE in 0.03s]
<HH:MM:SS> | INFO  | RUNNING 'task DAG'.............................................................. [RUN]
<HH:MM:SS> | INFO  | FINISHED 'task DAG'............................................................. [DONE in 0.01s]
<HH:MM:SS> | INFO  | RUNNING 'creating pipeline, DAG executor'....................................... [RUN]
<HH:MM:SS> | INFO  | FINISHED 'creating pipeline, DAG executor'...................................... [DONE in 0.01s]
 
<HH:MM:SS> | INFO  | ===================== tasks (vermilion-hornet-Gyycw4kRWG) =====================
<HH:MM:SS> | INFO  | 1 of 2 RUNNING EVENT 'decorated_task.example_task'.............................. [RUN]
<HH:MM:SS> | INFO  | 1 of 2 FINISHED EVENT 'decorated_task.example_task'............................. [DONE in 0.02s]
<HH:MM:SS> | INFO  | 2 of 2 RUNNING EVENT 'class_task.ExampleTask'................................... [RUN]
<HH:MM:SS> | INFO  | 2 of 2 FINISHED EVENT 'class_task.ExampleTask'.................................. [DONE in 0.01s]
 
<HH:MM:SS> | INFO  | Done!
--------------------------------------------------------------------------------
```

:tada: Congratulations! You just ran your first Prism project!

The project itself doesn't do much. It only has one task, and this task simply creates a `.txt` file in the `output` folder containing the string `Hello, World!`.&#x20;

Here's what the Prism graph looks like:

<figure><img src="/files/gHt2uVJ35aMZ9Mfz3BCH" alt=""><figcaption><p>The Prism project visualizer UI, generated via the <a href="/pages/wFuiQqfLRezSpPCefNWX"><code>prism graph</code></a> command</p></figcaption></figure>

In the next section, we'll add some complexity and learn about tasks and targets.


---

# 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.runprism.com/v0.2.3/getting-started/creating-your-first-project.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.