> For the complete documentation index, see [llms.txt](https://docs.supervisely.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.supervisely.com/agents/connect-your-computer/ami.md).
# AMI AWS
If, for some reason, your computer doesn't meet the requirements, hardware (no GPU) or software (no CUDA or nvidia-docker), there is a quick way to try training & inference with Supervisely on Amazon EC2.
If you have an account on EC2, deploying Supervisely agent is easy as one-two-three:
### Step 1: Login into Amazon EC2 Console
[Sign in](https://console.aws.amazon.com/console/home) into your account. We suppose you already have an account on AWS. If not, [signup](https://portal.aws.amazon.com/billing/signup).
### Step 2: Select AMI
Select EC2, open "Instances" section and click "Launch Instance" button.
Search for "Deep Learning AMI". You will see a bunch of out-of-the-box images that have Docker and CUDA installed - exactly what we are looking for. We suggest to use "Deep Learning AMI". Click "Select" button.
### Step 3: Run the GPU instance
On a next step select "GPU compute" filter and select "p3.\*" instance type. We suggest using "p3.2xlarge".
Different AMIs need different storage - i.e. "Deep Learning AMI (Ubuntu)" comes with Anaconda and multiple versions of CUDA so it's 100 Gb of already taken space. We suggest to configure at least 200 Gb volume size, because agent will download pretty large docker images. You can also attach additional EBS volume and create a symlink to `~/.supervisely-agent` - this is where your model weights and images will be stored.
Click "Review and Launch" to start your instance.
### Step 4: Copy-paste command in the instance terminal
Connect to your new instance using ssh. Follow [those steps](/agents/add_delete_node.md) to generate the agent deployment command and run it on your Amazon instance.
You can always stop your instance when you don't need your GPU resources to save money and start it again later. Supervisely agent should run automatically on instance startup.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## 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, and the optional `goal` query parameter:
```
GET https://docs.supervisely.com/agents/connect-your-computer/ami.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.