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

# Welcome to Switchport

> Prompt management and A/B testing platform for production LLM applications

## What is Switchport?

Switchport is a platform that helps you manage, test, and optimize LLM prompts in production. Execute prompts, run A/B tests, and track metrics to continuously improve your AI applications.

## Key Features

<Columns cols={2}>
  <Card title="Prompt Management" icon="code">
    Store and version your prompts in one place. Update prompts without deploying code.
  </Card>

  <Card title="A/B Testing" icon="flask">
    Test multiple prompt versions simultaneously with deterministic routing based on subject identification.
  </Card>

  <Card title="Metrics Tracking" icon="chart-line">
    Track performance metrics and aggregate results per prompt version automatically.
  </Card>

  <Card title="Multi-Model Support" icon="layer-group">
    Support for OpenAI, Anthropic, Google Gemini, and more.
  </Card>
</Columns>

## Get Started

Choose your language to begin:

<Columns cols={3}>
  <Card title="Python SDK" icon="python" href="/sdk/python/quickstart">
    Get started with the Python SDK in 5 minutes.
  </Card>

  <Card title="Go SDK" icon="code" href="/sdk/go/quickstart">
    Get started with the Go SDK in 5 minutes.
  </Card>

  <Card title="TypeScript SDK" icon="js" href="/sdk/typescript/coming-soon">
    Coming soon - TypeScript/JavaScript SDK.
  </Card>
</Columns>

## How it Works

<Steps>
  <Step title="Create a prompt config">
    Define your prompt in the Switchport dashboard with variables and multiple versions.
  </Step>

  <Step title="Execute from your code">
    Use the SDK to execute prompts with dynamic variables and subject identification for A/B testing.
  </Step>

  <Step title="Track metrics">
    Record user feedback, conversion rates, or any custom metrics linked to prompt versions.
  </Step>

  <Step title="Analyze results">
    View aggregated metrics per version in the dashboard to identify the best-performing prompts.
  </Step>
</Steps>

## Quick Example

```python theme={null}
from switchport import Switchport

client = Switchport()

# Execute a prompt
response = client.prompts.execute(
    prompt_key="welcome-message",
    subject={"user_id": "user_123"},
    variables={"name": "Alice"}
)

print(response.text)

# Track user feedback
client.metrics.record(
    metric_key="satisfaction",
    value=4.5,
    subject={"user_id": "user_123"}
)
```

## Resources

<Columns cols={3}>
  <Card title="GitHub" icon="github" href="https://github.com/switchport-ai">
    Explore our open-source SDKs
  </Card>

  <Card title="Dashboard" icon="chart-line" href="https://switchport.ai">
    Access the Switchport platform
  </Card>

  <Card title="Discord" icon="discord" href="https://discord.gg/switchport">
    Join our community
  </Card>
</Columns>