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

# Introduction

> Soria is a healthcare data intelligence platform that ingests public data sources, extracts structured data with AI, and serves interactive dashboards and news intelligence.

Soria turns raw public healthcare data into queryable, structured intelligence. You connect data sources, run AI-powered extraction pipelines, and explore results through dashboards and news summaries — all accessible from a web UI and from AI assistants via the MCP server.

## Who uses Soria

<CardGroup cols={2}>
  <Card title="Data Engineers" icon="code" href="/pipeline/overview">
    Build and manage ingestion pipelines via the MCP server in Claude Code. Define scrapers, configure schemas, run extraction, and publish warehouse models.
  </Card>

  <Card title="Analysts" icon="chart-bar" href="/dashboards/overview">
    Explore structured healthcare datasets through dashboards, filter data, search across all datasets and news stories, and query the warehouse directly.
  </Card>
</CardGroup>

## Core capabilities

<CardGroup cols={2}>
  <Card title="AI Extraction" icon="brain" href="/pipeline/extraction">
    Gemini-powered detection and extraction handles PDFs, Excel, and CSVs — no manual template authoring required.
  </Card>

  <Card title="Data Warehouse" icon="database" href="/pipeline/warehouse">
    A four-layer pipeline (bronze → silver → gold → platinum) transforms raw files into dashboard-ready views.
  </Card>

  <Card title="MCP Integration" icon="robot" href="/mcp/overview">
    Connect Claude Code or any MCP-compatible AI assistant to run the full pipeline with natural language.
  </Card>

  <Card title="News Intelligence" icon="newspaper" href="/news/overview">
    An automated daily pipeline fetches, scores, clusters, and summarizes healthcare news from configured sources.
  </Card>
</CardGroup>

## Two pipeline paths

Soria handles two types of source files differently:

**PDFs and Excel** (unstructured → structured): Soria detects which pages contain relevant data, extracts it into CSVs using Gemini against your defined schema, validates accuracy, and normalizes inconsistent values.

**CSVs** (already structured): Soria maps source column headers to your canonical schema columns, handling schema drift when column names change across files or over time.

Both paths land data in the warehouse for SQL modeling and dashboarding.

## Next steps

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/quickstart">
    Connect via MCP and run your first command in minutes
  </Card>

  <Card title="Pipeline Overview" icon="pipe-section" href="/pipeline/overview">
    Understand the end-to-end data pipeline
  </Card>
</CardGroup>