> ## Documentation Index
> Fetch the complete documentation index at: https://docs.phidata.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

To run agents in production, we need to:

1. Serve them using an application like **FastApi**, **Django** or **Streamlit**.
2. Manage their sessions, memory and knowlege in a database.
3. Monitor, evaluate and improve their performance.

Phidata not only makes building Agents easy but also provides templates that can be deployed to AWS with 1 command. Here's how they work:

* Create your codebase using a template: `phi ws create`
* Run your application locally: `phi ws up`
* Run your application on AWS: `phi ws up prd:aws`

<Note>
  We strongly believe that data used by AI applications should be stored securely inside your VPC.

  We fully support BYOC (Bring Your Own Cloud) and encourage you to use your own AWS account.
</Note>

## Templates

We recommend starting with the `agent-app` template and adding your own agents.

<CardGroup cols={2}>
  <Card title="Agent App" icon="books" href="/templates/agent-app/run-local">
    Run agents using FastApi, Streamlit and store memory and knowlege in Postgres
  </Card>

  <Card title="Agent Api" icon="bolt" href="/templates/agent-api/run-local">
    Run agents using FastApi and store memory and knowlege in Postgres
  </Card>
</CardGroup>