> ## 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.

# Soria Documentation

> Healthcare data intelligence — ingest public data sources, build structured dashboards, and surface news intelligence through AI-powered pipelines.

Soria transforms raw public healthcare data into structured, queryable intelligence. Connect data sources, run AI-powered extraction pipelines, and serve interactive dashboards — all from a unified platform with deep AI assistant integration via MCP.

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/quickstart">
    Get up and running with Soria in minutes
  </Card>

  <Card title="MCP Integration" icon="robot" href="/mcp/overview">
    Connect Claude Code or any AI assistant to Soria
  </Card>

  <Card title="Data Pipeline" icon="pipe-section" href="/pipeline/overview">
    Ingest, extract, and warehouse healthcare data
  </Card>

  <Card title="Dashboards" icon="chart-bar" href="/dashboards/overview">
    Build and explore data visualizations
  </Card>
</CardGroup>

## How Soria works

<Steps>
  <Step title="Connect a data source">
    Define a scraper that discovers and downloads files from a public URL — PDFs, Excel files, or CSVs. Soria handles scheduling, deduplication, and storage automatically.
  </Step>

  <Step title="Run the extraction pipeline">
    Soria's AI pipeline detects relevant pages, extracts tabular data into structured CSVs, validates accuracy, and normalizes values to canonical forms.
  </Step>

  <Step title="Build warehouse models">
    Raw files land in bronze warehouse tables. Write SQL models to clean (silver), join (gold), and aggregate (platinum) your data into dashboard-ready views.
  </Step>

  <Step title="Explore and share">
    Browse dashboards in the web UI, query data through the MCP tools in your AI assistant, or search across all datasets and news events in one place.
  </Step>
</Steps>

## Key capabilities

<CardGroup cols={2}>
  <Card title="AI-Powered Extraction" icon="brain" href="/pipeline/extraction">
    Gemini-powered detection and extraction handles PDFs, Excel, and CSVs without manual template authoring
  </Card>

  <Card title="Workspaces" icon="layer-group" href="/workspaces/overview">
    Isolate data changes in workspace branches before promoting to production
  </Card>

  <Card title="News Intelligence" icon="newspaper" href="/news/overview">
    Automated pipeline fetches, scores, clusters, and summarizes healthcare news daily
  </Card>

  <Card title="Search" icon="magnifying-glass" href="/dashboards/search">
    Full-text search across all dashboards and news stories with synonym support
  </Card>
</CardGroup>