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

# Process your first document in ABBYY Vantage Cloud

> Process your first document in ABBYY Vantage Cloud, the SaaS platform hosted by ABBYY, using the REST API or the web UI. See how AI skills extract data.

ABBYY Vantage Cloud is the multi-tenant SaaS platform hosted and operated by ABBYY. This quickstart takes you from a raw document to structured data in about 10 minutes.

You upload a real document, apply an AI-powered skill, and get structured data back.

<Info>
  These pages document **Vantage Cloud**. To run Vantage on your own Kubernetes infrastructure instead, see [ABBYY Vantage 3.0 self-hosted](/vantage/self-hosted/v3.0/introduction).
</Info>

Choose your path depending on how you want to work with Vantage Cloud:

<CardGroup cols={2}>
  <Card title="Process via API" icon="code" href="/vantage/getting-started/api">
    Authenticate, upload a document, and extract data using the REST API. Best for developers integrating Vantage into applications. \~10 minutes.
  </Card>

  <Card title="Process via UI" icon="browser" href="/vantage/getting-started/ui">
    Upload a document and review extracted data in the Vantage web interface. Best for business users and evaluation. \~10 minutes.
  </Card>
</CardGroup>

## How Vantage processes a document

Whether you use the API or the web UI, every document goes through the same pipeline:

<Steps>
  <Step title="Authenticate or sign in">
    Connect to your Vantage tenant using API credentials or the web login.
  </Step>

  <Step title="Select a skill">
    A **skill** is an AI model trained to extract data from a specific document type. Vantage has [100+ pre-trained skills](/vantage/documentation/skill-catalog/skill-catalog), or you can build your own.
  </Step>

  <Step title="Submit your document">
    Upload a PDF, image, or Office document. Vantage creates a **transaction**, a processing job that tracks the document through extraction.
  </Step>

  <Step title="Extract structured data">
    The skill reads the document and extracts field values (e.g., invoice number, vendor name, total amount). Each field gets a **confidence score** from 0 to 100 indicating how certain Vantage is about the extraction.
  </Step>

  <Step title="Review and export results">
    Download the extracted data as JSON or XML, or verify it in **Manual Review**, a built-in interface where operators can check and correct fields before the data moves downstream.
  </Step>
</Steps>

## What you'll need

* An ABBYY Vantage account ([contact ABBYY](https://www.abbyy.com/vantage-contact-us/) to request a tenant)
* A sample document (invoice, receipt, purchase order, or any supported type)
* About 10 minutes

## Key concepts

| Concept | What it means |
| - | - |
| **Skill** | An AI model trained to extract data from a specific document type. There are [100+ pre-trained skills](/vantage/documentation/skill-catalog/skill-catalog), or you can [create your own](/vantage/documentation/skill-catalog/create-skill). |
| **Document Skill** | The most common skill type. Extracts named fields such as `InvoiceNumber` or `VendorName` from a single document type. |
| **Transaction** | A processing job. Each time you submit a document to a skill, Vantage creates a transaction to track it. |
| **Confidence Score** | A number from 0 to 100 indicating how certain Vantage is about an extracted value. Fields below configured thresholds are flagged for review. |
| **Manual Review** | A built-in interface where human operators verify and correct extracted data before it moves to downstream systems. |

<Tip>
  After processing your first document, see [Understanding your results](/vantage/getting-started/results) to learn how to read the extracted data, and [What to learn next](/vantage/getting-started/next-steps) for guidance on where to go based on your goals.
</Tip>