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

# How Stratta works

> Why Stratta gives you exact, verifiable citations instead of plausible-sounding guesses.

Stratta is designed around one goal: **every answer must be traceable to the source norm.**
For engineering work, an answer you can't verify is worse than no answer. This page explains
the approach in plain terms.

## The problem with ordinary AI search

Most AI document tools chop a document into thousands of small fragments, turn each into a
numeric vector ("embedding"), and retrieve the fragments that look mathematically similar to
your question. This works for casual Q\&A, but it has two failure modes that matter for norms:

* **Fuzzy provenance.** A retrieved fragment may not map cleanly to a section number or page,
  so the citation is approximate — or invented.
* **Lost structure.** Norms are deeply hierarchical and cross-referenced. Flat fragments lose
  the chapter → section → clause structure that tells you *where a rule actually lives*.

## Stratta's approach: TreeRAG

Instead of embeddings, Stratta stores each norm as its **real table of contents** — a tree of
chapters, sections, sub-sections, and annexes. Claude navigates that tree the way an engineer
flips through the printed norm:

<Steps>
  <Step title="See what's available">
    Claude lists the norms in your workspace.
  </Step>

  <Step title="Open the table of contents">
    It reads the chapter structure, then drills into the relevant section.
  </Step>

  <Step title="Read the exact section">
    It opens the section's full content — text, formulas (in LaTeX), tables, and figures.
  </Step>

  <Step title="Follow the cross-references">
    SIA splits a rule across norms (the action in SIA 261, the safety factors in SIA 260, the
    material rules in the domain norm). Claude follows those links before concluding.
  </Step>
</Steps>

Because each section keeps its **exact path and page range**, every citation Claude produces —
`[SIA 261, 8.2, p. 44]` — points to a real, openable location. This is what we mean by
*deterministic citations*.

<Info>
  TreeRAG is inspired by the [PageIndex](https://github.com/VectifyAI/PageIndex) approach to
  document reasoning. Read the deeper rationale in [Concepts → TreeRAG](/en/concepts/treerag).
</Info>

## The two halves of Stratta

<CardGroup cols={2}>
  <Card title="stratta.ch — the platform" icon="globe">
    Where you sign up, create API keys, manage your organization, and (later) handle billing.
  </Card>

  <Card title="@stratta/mcp — the connector" icon="plug">
    The MCP server you install in Claude. It authenticates with your API key and gives Claude
    the tools to read and ingest norms.
  </Card>
</CardGroup>

There is no separate chat interface to learn. You use the Claude client you already have;
Stratta simply adds the norms.

## Your norms are yours

Norms are **scoped to your organization**. You ingest the documents you are licensed for, and
they are visible only to your workspace — never a shared public corpus. This keeps you in
control of licensing and confidentiality. See
[Concepts → Multi-tenant norms](/en/concepts/multi-tenant-norms).

## Next

<CardGroup cols={2}>
  <Card title="TreeRAG in depth" icon="tree" href="/en/concepts/treerag">
    The reasoning model behind deterministic citations.
  </Card>

  <Card title="Architecture" icon="sitemap" href="/en/concepts/architecture">
    How the platform and the MCP connector fit together.
  </Card>
</CardGroup>