# Channel Configuration — Document Processing

In the **Document Processing** area, you define **what Workist does with an incoming document** once it has arrived in the channel — which fields are extracted, the confidence level above which processing happens automatically, which master data is consulted, and how documents that do not belong in the channel are handled.

This page gives an overview of the entries in the navigation under **Document Processing**, in their order:

1. **[Document](/en/docs/channel-configuration/document-processing/document.md)** — general processing settings per channel (localization, automation, user assignment, date format, validation, …).
2. **[Header Fields](/en/docs/channel-configuration/document-processing/header-fields.md)** — which header data is extracted and with which options.
3. **[Line Item Fields](/en/docs/channel-configuration/document-processing/line-item-fields.md)** — which fields are extracted per line item.
4. **[Agentic Extraction](/en/docs/channel-configuration/document-processing/agentic-extraction.md)** — optional LLM-based extraction of additional fields. In the navigation it appears as two entries, **Agentic Header Extraction** and **Agentic Line Item Extraction**; both are described in a shared guide.
5. **Master Data** — which master data (lookups) is used for articles, customers, addresses, … (see Step 5).
6. **Discard** — what happens to discarded documents (see Step 6).

Two reference pages complement these guides:

- **[Validation Checks and Assistance Reasons](/en/docs/channel-configuration/document-processing/validation-checks.md)** — when Workist automates, all checks, and the assistance reasons in Analytics.
- **[Matching with Order and Quote Data](/en/docs/channel-configuration/document-processing/matching.md)** — offer and order matching, prefilling empty documents.

## Prerequisites

- Access to the channel configuration (see [Users and roles](/en/docs/administration/users-and-roles.md)).
- For **Master Data**: master data set up in advance in the [Master Data Hub](/en/docs/master-data/master-data-hub.md).
- For **Agentic Extraction**: an understanding of which additional fields the AI should extract and which data sources are available to it for this purpose.

## Step 1 — Document: central processing settings

In the navigation under **Document Processing**, select the **Document** entry. This page is organized by topic. Each topic block has a **Save** button; each of them saves all changes on the page.

| Topic block | Key settings |
| --- | --- |
| **Localization** | **Time zone** and **Holiday calendar** of the channel. Overrides the customer-level settings for this channel. |
| **Automation** | **Automation enabled** as a global switch. **Header data / Position lines confidence threshold (%)**: every field must reach this value on its own for the document to be handed over without assistance. Without a saved value, 100 % applies. |
| **User assignment** | Automatically assigns documents to the responsible person from your master data. |
| **Data formatting** | **Date format**, **Address format** (street name first / street number first), and **Decimal separator** of the output file. |
| **Unit conversion** | **Conversion style** (none / round up / 30% rule), options for overriding the original fields, for best effort conversion, and for customer-specific conversion. |
| **Validation** | **Validation checks** — multi-select from the business checks (total amount, line item sum, position number, …), rules for min quantity and article status, and **Keywords to assistance**. All checks: [Validation checks](/en/docs/channel-configuration/document-processing/validation-checks.md). |
| **Document type specific** | Settings that only affect the respective document type (e.g. **Support order forms**, **Remove freight cost line items**, Factur-X for invoices). |
| **Backfilling** | **Backfill with email data** and **Document formats for backfilling** — Workist fills missing header fields from the email body if **Backfilling enabled** is on for the field. |
| **Document Filtering** | **Sort Out Document Types** and **Filtering Sensitivity** — for emails with several attachments, Workist decides which attachments become a document. |

:::warning Automation is set up together with Workist
Automation (the global switch and confidence thresholds) is normally set up and configured together with your contact at Workist. Making your own changes here is **not recommended** and is done at your own risk.
:::

You can find the complete step-by-step guide to all topic blocks under **[Document](/en/docs/channel-configuration/document-processing/document.md)**.

## Step 2 — Header Fields

In the navigation under **Document Processing**, select the **Header Fields** entry. Here you define which header data fields (e.g. order type, order number, customer contact) Workist extracts from the document and which properties each field has.

The layout has two columns: on the left, the list of **configured fields**; on the right, the **configuration options** for the currently selected field. In day-to-day use, you mainly define here **which** standard fields are extracted, whether a field is **required**, and in which **order** the fields appear in assistance. Many fields also have options of their own, e.g. address fallbacks, delivery date rules, or a replacement for a missing document number.

Complete guide: **[Header Fields](/en/docs/channel-configuration/document-processing/header-fields.md)**.

## Step 3 — Line Item Fields

In the navigation under **Document Processing**, select the **Line Item Fields** entry. The operating logic is identical to the Header Fields; compared to the Header Fields, a few line-item-specific options are added.

Here you find, among others, **Perform lookups**, **Allow invalid IDs**, **Keep external article number**, and **Reset imperfect article matches** on the article number, and **Allow decimal quantities**, **Allow zero quantities**, and **Max value** on the quantity. **Max field length** exists on all text fields, header fields included.

Complete guide: **[Line Item Fields](/en/docs/channel-configuration/document-processing/line-item-fields.md)**.

## Step 4 — Agentic Extraction

In the navigation under **Document Processing**, you will find two entries: **Agentic Header Extraction** (per document) and **Agentic Line Item Extraction** (per line item). Here you set up **LLM-based extractors** that work in addition to the regular field extraction — typically for fields that are difficult to capture with classic extraction (e.g. free-text instructions, document-specific clauses).

:::tip When agentic extraction is worthwhile
When a field is not always in the same place, is embedded in free text, or requires combined logic (e.g. "derive order type from brand + shipping address"). For tightly structured fields, the regular extraction in *Header Fields* / *Line Item Fields* is sufficient.
:::

Both variants are described in a shared guide: **[Agentic Extraction](/en/docs/channel-configuration/document-processing/agentic-extraction.md)**.

## Step 5 — Master Data

In the navigation under **Document Processing**, select the **Master Data** entry. Here you define which master data the channel uses for matching.

The page has three blocks:

| Block | Entries (selection) |
| --- | --- |
| **Master Data Lookups** | **Client Lookup ID** (customers), **Contact Lookup ID**, **Invoice Address Lookup ID**, **Delivery Address Lookup ID**, **Article Lookup ID**, **Debtor Article Lookup ID** (customer-specific articles), **Conversion Factor Lookup ID**, **Framework Contract Lookup ID** |
| **Master Data Mappings** | Mappings stored from assistance, e.g. **Article Mapping Lookup ID** |
| **Master Data Matching** | **Order Matching Lookup ID** and **Offer Matching Lookup ID** for [matching](/en/docs/channel-configuration/document-processing/matching.md) |

For each entry, you select the matching master data of your company from a list; only master data of the right type is offered. The **gear icon** next to it opens this master data in the [Master Data Hub](/en/docs/master-data/master-data-hub.md) in a new tab. There you upload files and set up the import. Only users who may manage master data see the icon.

:::note What happens if no article master data is set?
Matching does not take place. For the article number this means: if **Allow invalid IDs** is off on the line item field *Article number* (default), the article number stays empty unless Workist knows it from learned mappings. If the option is on, Workist takes over the number from the document unchanged.
:::

After making changes, click **Save**.

## Step 6 — Discard

In the navigation under **Document Processing**, select the **Discard** entry. Here you define who is notified when a document in the channel is discarded (e.g. because a user discards it manually).

| Field | Meaning |
| --- | --- |
| **Recipient e-mail addresses** | Addresses to which discarded documents are forwarded with reason, channel and link — typically an internal mailbox for manual review. Confirm each address separately. |
| **Return e-mail to original sender** | When enabled and the sender of the document is a Workbench user of your company, the notification goes to that user **instead of** the recipients above. External senders receive nothing. |

:::tip Recommendation
Always set at least one forwarding address. Otherwise nobody is notified when a document is discarded; the documents are only visible as discarded in the Workbench. Attachments sorted out by [document filtering](/en/docs/channel-configuration/document-processing/document.md#step-9--document-filtering) do not become a document and trigger no notification.
:::

## Frequently Asked Questions

**In which order do the configurations run?**
Per incoming email: document filtering (which attachments become documents) → classic field extraction (header fields / line item fields) including master data matching for customer, contact, addresses and articles; agentic line item extraction runs per line item after the article lookup → agentic header extraction → validation checks and matching → decision between automation and assistance. The rule for that is described under [When is a document automated?](/en/docs/channel-configuration/document-processing/validation-checks.md#when-is-a-document-automated).

**What is the difference between data label name and field label name?**
Both exist for custom fields. The **data label name** is the technical name in the output file and is fixed after the first save. The **field label name** is only the label that appears in the Workbench (assistance, forms) and can be changed at any time. For standard fields, you change the label with **Display name**.

## Help and Support

If you encounter problems with processing, have the following information ready:

- the **channel name** and the area (Document, Header Fields, …),
- the ID or name of a specific **example document** that was not processed as expected,
- for master data topics: the affected **master data** and ideally the most recently imported file,
- for agentic extraction: the **configuration name**, the prompt if applicable, and the most recent successful / failed examples.