> ## Documentation Index
> Fetch the complete documentation index at: https://unfold-0a6049eb.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Guides

> Recipes for hosted documents, jobs, compare, and waitForExecution.

These guides are for **hosted** `Unfold` workflows. They use the same primitives as the rest of the docs: store a document, run executions, read normalized results, delete when done.

They are application-owned patterns. Unfold does not auto-pick engines or fail over for you today.

<CardGroup cols={2}>
  <Card title="Fast preview, then full parse" icon="zap" href="/guides/fast-then-strong">
    One document, one job, two engines. Show LiteParse as soon as it finishes.
  </Card>

  <Card title="Cheap path, then escalate" icon="coins" href="/guides/cheap-path">
    Run LiteParse first. Start a heavier engine only if the cheap result looks
    weak.
  </Card>

  <Card title="Bake off engines" icon="git-compare" href="/guides/bake-off">
    Fan out with `compare` to score quality, latency, and cost on your files.
  </Card>

  <Card title="Idempotency and cleanup" icon="shield" href="/guides/durable-jobs">
    Safe retries, retention windows, and `documents.delete`.
  </Card>
</CardGroup>

## Primitives cheat sheet

| Piece | Role |
| - | - |
| `documents.create` / `release` | Store once; release source + retained results |
| `documents.delete` | Remove the document and its job history |
| `jobs.create` | Start one or more provider executions |
| `jobs.waitForExecution` | Unblock when a single execution finishes |
| `jobs.wait` | Wait until the whole job ends |
| `executions.result` | Fetch a normalized `ParseResult` |
| `parse` / `compare` | Convenience wrappers over the same resources |

See [How Unfold works](/concepts/how-it-works) for the contract, and [Documents and jobs](/api/jobs) for the HTTP shape.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.