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

# How EDN works

> The path from content in to governed context out.

## The pipeline

EDN turns raw content into governed context in a fixed sequence of steps.

<Steps>
  <Step title="Content enters">
    Your application sends content to EDN: a memory write, a document to ingest,
    or a correction. Each item arrives through a typed endpoint in the API.
  </Step>

  <Step title="Classification">
    EDN classifies each record with a provenance class that records its origin,
    for example whether a user stated it, a user confirmed it, a document
    verified it, or a model inferred or generated it.
  </Step>

  <Step title="Governed storage">
    Records are persisted with their type, provenance, domain, and an embedding.
    Superseded records are marked rather than silently overwritten, so history
    stays traceable.
  </Step>

  <Step title="Deterministic retrieval">
    When your application asks for context, EDN ranks stored records by cosine
    similarity to the query, applies a fixed similarity floor, and gates the
    results by provenance. No model chooses the records.
  </Step>

  <Step title="Governed context">
    The selected records are assembled into a compact package, the SIP, with a
    fixed set of sections. Inferences are marked as inferences and AI-generated
    content is confined to an uncertain section. Your application feeds this
    package to your model.
  </Step>
</Steps>

## Where the model fits

The model is only ever the consumer of the final package. EDN classifies,
stores, retrieves, and assembles. Your model reads the assembled context and
produces the answer. This separation is what lets EDN keep provenance intact
end to end.

<Note>
  Retrieval performs no generative model calls. The query is compared against
  stored embeddings with a deterministic similarity query. See
  [Core concepts](/developer/core-concepts) for detail.
</Note>