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

# Choose your path

> Choose between the two Flint AI Platform quickstarts, Discover and Runtime

There are two ways into Flint AI Platform, and they answer different questions. Start with Discover if you want to know what agents you have. Start with Runtime if you already know and want to see what they do in production.

Most teams do Discover first — it needs no changes to running code.

<CardGroup cols={2}>
  <Card title="Discover your agents" icon="radar" href="/flintai/platform/getting-started/discover">
    Add a GitHub Action to build an inventory of the agents in your repositories, along with the models, tools, and MCP servers behind them.
  </Card>

  <Card title="Monitor your agents at runtime" icon="shield-halved" href="/flintai/platform/getting-started/runtime">
    Wrap your LLM client with the Python SDK to capture live sessions and enforce guardrails.
  </Card>
</CardGroup>

## What each one needs

|                 | **Discover**                                 | **Runtime**                         |
| --------------- | -------------------------------------------- | ----------------------------------- |
| **You provide** | A GitHub repository with Python agent code   | A running agent you can change      |
| **You install** | A GitHub Action                              | The Flint AI Python SDK             |
| **You get**     | An agent inventory and the issues to address | Live traces and enforced guardrails |

Both need a Flint AI API key. Discovery also needs an API key from your own LLM provider — the scan uses a model to analyze your code, so that inference is billed to you. [Google Gemini's free tier](https://aistudio.google.com/apikey) is enough to try it.