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

# Examples

> Complete workflows you can copy: the graph, the code to create and run it, and a real response

Every example is one workflow, end to end. It shows the graph as JSON and as SDK code, how to upload a document and read the run, a trimmed real response, and the tips that matter for that document type. Pick the one whose shape matches your problem; the nodes it uses are named on every card.

## Read only

One [Parse](/guides/nodes/parse) node. The document comes back as markdown and layout blocks, and nothing is extracted.

<CardGroup cols={2}>
  <Card title="Parse-only workflow" icon="file-lines" href="/examples/parse-only-workflow">
    Parse a document on the Flash, Fast, Standard or Agentic tier and compare what each returns. **Nodes:** Parse.
  </Card>

  <Card title="Agentic parse to markdown" icon="wand-magic-sparkles" href="/examples/agentic-parse-to-markdown">
    Dense tables on the Agentic tier, with the effort presets and per-block confidence. **Nodes:** Parse (agentic).
  </Card>
</CardGroup>

## Read, then pull out

[Parse](/guides/nodes/parse) feeds [Extract](/guides/nodes/extract). You define the fields; every value comes back with a confidence and the evidence it came from.

<CardGroup cols={2}>
  <Card title="Invoice processing" icon="file-invoice-dollar" href="/examples/invoice-processing">
    The header and the line items of an invoice. **Nodes:** Parse, Extract.
  </Card>

  <Card title="Resume parsing" icon="user-tie" href="/examples/resume-parsing">
    Contact details, skills, education and work history from PDF and DOCX resumes. **Nodes:** Parse, Extract.
  </Card>

  <Card title="Receipt scanning" icon="receipt" href="/examples/receipt-scanning">
    Merchant, totals and payment method from receipt photos and scans. **Nodes:** Parse, Extract.
  </Card>

  <Card title="Email lead extraction" icon="envelope" href="/examples/email-lead-extraction">
    Sender, inquiry type, urgency and topics from an email body sent as text. **Nodes:** Parse, Extract.
  </Card>

  <Card title="Bank statement processing" icon="building-columns" href="/examples/bank-statement-processing">
    Statement header plus every transaction as a row, across many statements. **Nodes:** Parse, Extract.
  </Card>
</CardGroup>

## Sort first, then pull out

[Classify](/guides/nodes/classify) labels the document and routes it to the [Extract](/guides/nodes/extract) node for that category, so one workflow handles mixed input. [Split](/guides/nodes/split) does the same for one file that holds several documents.

<CardGroup cols={2}>
  <Card title="Sort invoices from receipts" icon="code-branch" href="/examples/classify-and-route">
    Parse, Classify, Extract. One inbox, two document kinds, each with its own fields.
  </Card>
</CardGroup>

## Extract, then check

[Validate](/guides/nodes/validate) runs your rules over the extracted values and records a verdict per rule; [If/Else](/guides/nodes/if-else) routes on the result.

<CardGroup cols={2}>
  <Card title="Contract analysis" icon="file-contract" href="/examples/contract-analysis">
    Key terms and clauses from a contract, then checked with validation rules. **Nodes:** Parse, Extract, Validate.
  </Card>
</CardGroup>

## Operate at scale

Scripts around the API rather than new graphs: batch the runs of a workflow, or measure it.

<CardGroup cols={2}>
  <Card title="Daily CSV export" icon="file-csv" href="/examples/daily-csv-export">
    Pull one local day of runs in parallel and flatten them into a CSV. **Nodes:** any workflow ending in Extract.
  </Card>

  <Card title="Evaluating a workflow" icon="chart-line" href="/examples/evaluating-a-workflow">
    Upload ground truth, launch an eval, and read the accuracy headline in CI. **Nodes:** any workflow ending in Extract.
  </Card>
</CardGroup>

## Before you start

* Get an API key at [app.anyformat.ai](https://app.anyformat.ai) and export it as `ANYFORMAT_API_KEY`.
* Every example uses the same three calls: [create a workflow](/api-reference-v3/workflows/create), [upload and run](/api-reference-v3/workflows/upload-and-run), and [get the run](/api-reference-v3/runs/get).
* The SDK examples need `pip install anyformat` or `npm install @anyformat/sdk`. The [Quickstart](/guides/quickstart) walks through the first workflow.
* The [Nodes overview](/guides/nodes/overview) lists every node, what it returns and what it costs.