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

# Getting Started with Athina

### Athina IDE

Athina IDE is a collaborative editor for AI teams to prototype, experiment, and evaluate LLM-powered applications.

<CardGroup cols={2}>
  <Card title="Watch a Demo Video" icon="play" href="https://www.loom.com/share/b31b267a0ab4456887944cd3199f4422">
    View a Demo Video to learn more about Athina IDE.
  </Card>

  <Card title="Quickstart: Run Evals" icon="bolt" href="/evals/quickstart">
    A quickstart guide for running evals in the UI or programmatically.
  </Card>
</CardGroup>

### Prompts & Experimentation

<CardGroup cols={2}>
  <Card title="Athina Playground" icon="input-text" href="/prompts/overview">
    Experiment with different prompts and models
  </Card>

  <Card title="Prompt Management" icon="folder-tree" href="/prompts/organization">
    Organize prompts into folders, add versioning, and manage collaboratively
  </Card>

  <Card title="Run Prompts via API" icon="code" href="/prompts/run-prompt">
    Execute your saved prompts programmatically via API or SDK
  </Card>

  <Card title="Prototype Pipelines" icon="diagram-project" href="guides/datasets/prototype-and-evaluate-prompt-chain">
    Chain prompts and API calls to build complex pipelines
  </Card>
</CardGroup>

### Evaluations & Quality

<CardGroup cols={2}>
  <Card title="Run Evaluations" icon="bolt-lightning" href="/evals/running-evals-in-ui">
    Choose from 50+ preset evals or create custom evaluations
  </Card>

  <Card title="Continuous Evaluation" icon="rotate" href="/monitoring/continuous-eval">
    Automatically evaluate production traffic for quality and safety
  </Card>

  <Card title="CI/CD Integration" icon="code-branch" href="/evals/running-evals-ci-cd">
    Prevent regressions by running evals in your CI/CD pipeline
  </Card>

  <Card title="Custom Evaluation" icon="wrench" href="/evals/custom-evals">
    Build custom evaluation logic for your specific use case
  </Card>
</CardGroup>

### Observability & Analytics

<CardGroup cols={2}>
  <Card title="Logging Setup" icon="terminal" href="/api-reference/logging/overview">
    Start logging LLM interactions in 2 lines of code
  </Card>

  <Card title="Usage Analytics" icon="chart-line" href="/monitoring/analytics">
    Track costs and usage across models, prompts, and customers
  </Card>

  <Card title="Trace Visualization" icon="timeline" href="/monitoring/inference-trace">
    Visualize and debug complex LLM chains
  </Card>

  <Card title="Export & Query" icon="database" href="/api-reference/graphql-api/overview">
    Access your data via GraphQL API or export as CSV/JSON
  </Card>
</CardGroup>

### Datasets & Testing

<CardGroup cols={2}>
  <Card title="Create Datasets" icon="table" href="/datasets/create-dataset/create-dataset">
    Import data from logs, files, or generate synthetic datasets
  </Card>

  <Card title="Dynamic Columns" icon="code" href="/datasets/dynamic-columns/dynamic-columns">
    Add computed columns using LLM calls, code, or API requests
  </Card>

  <Card title="Compare Datasets" icon="code-compare" href="/datasets/compare-datasets">
    Compare performance across different models or prompts
  </Card>

  <Card title="Run Experiments" icon="flask" href="/datasets/run-experiment">
    Test different approaches and measure improvements
  </Card>
</CardGroup>
