# Command Line Interface

Prism offers a simple, yet powerful CLI to help users create, manage and run their projects. 

{% hint style="info" %}
**Good to know:** we recommend building your project in a code editor, like VSCode, Atom, or Sublime Text, and running the project from the command line.
{% endhint %}

```
Usage: prism [OPTIONS] COMMAND [ARGS]...                                                                                            
                                                                                                                                     
╭─ Options ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ --help      Show this message and exit.                                                                                           │
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
╭─ Commands ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ agent         Execute your Prism using third-party agents, (e.g., Docker containers, EC2 instances, etc.).                        │
│ compile       Parse the tasks.ref(...) calls, construct the DAG, and generate the manifest.                                       │
│ connect       Connect your Prism project to third-party adapters (e.g., Snowflake, BigQuery, PySpark, etc.).                      │
│ create        Create and/or update project components (e.g., tasks, triggers, agents).                                            │
│ graph         Visualize your Prism project as a DAG in an interactive UI.                                                         │
│ init          Initialize a Prism project.                                                                                         │
│ run           Execute your Prism project.                                                                                         │
│ spark-submit  Execute your Prism project as a PySpark job.                                                                        │
╰───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
```

Here are the list of commands available through the CLI:

* [agent](https://docs.runprism.com/v0.2.0/cli/agent)
  * [apply](https://docs.runprism.com/v0.2.0/cli/agent/apply)
  * [run](https://docs.runprism.com/v0.2.0/cli/agent/run)
  * [build](https://docs.runprism.com/v0.2.0/cli/agent/build)
* [compile](https://docs.runprism.com/v0.2.0/cli/compile)
* [connect](https://docs.runprism.com/v0.2.0/cli/connect)
* [create](https://docs.runprism.com/v0.2.0/cli/create)
  * [agent](https://docs.runprism.com/v0.2.0/cli/create/agent)
  * [task](https://docs.runprism.com/v0.2.0/cli/create/task)
  * [trigger](https://docs.runprism.com/v0.2.0/cli/create/trigger)
* [graph](https://docs.runprism.com/v0.2.0/cli/graph)
* [init](https://docs.runprism.com/v0.2.0/cli/init)
* [run](https://docs.runprism.com/v0.2.0/cli/run)
* [spark-submit](https://docs.runprism.com/v0.2.0/cli/spark-submit)


---

# 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/v0.2.0/cli/command-line-interface.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.