> For the complete documentation index, see [llms.txt](https://docs.docbits.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.docbits.com/administration-and-setup/settings/document-processing/e-documents/notification-routing.md).

# Notification Routing

<figure><img src="https://578966019-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FT2n2w4uDCJvv7CJ5zrdk%2Fuploads%2Fgit-blob-5d819fb673d1dc3b2990b49cf8edcd87f53ac8c0%2Feinvoice-notification-routing.png?alt=media" alt="Notification routes"><figcaption><p>Mapping validation findings to agents</p></figcaption></figure>

The **Notification Routing** page (**E-Documents → Actions**) maps validation findings to **AI Workforce agents**. Each blocking finding triggers exactly one agent — the one whose code-prefix matches the longest. Anything with no match falls back to the default supplier-notification agent.

## Notification Routes

Choose who handles each kind of invoice problem. Anything not listed goes to the default agent:

| Route                          | Findings it covers                                      |
| ------------------------------ | ------------------------------------------------------- |
| **Colombian business rules**   | Colombia-specific business-rule findings.               |
| **German business rules**      | Germany-specific business-rule findings.                |
| **IBAN / bank-account checks** | Payment-data findings (IBAN checksum, length, country). |
| **VAT-ID checks**              | VAT/tax-ID format findings.                             |
| **Everything else**            | The default fallback for anything not matched above.    |

For each route, pick the handling agent from the dropdown. **Advanced (custom code rules)** lets you route by an exact finding code when you need finer control.

## Available Agents

<figure><img src="https://578966019-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FT2n2w4uDCJvv7CJ5zrdk%2Fuploads%2Fgit-blob-3c4712f21cee79b43db0ca82c884140da397e823%2Feinvoice-notification-agents.png?alt=media" alt="Available agents registry"><figcaption><p>Read-only registry of AI Workforce agents</p></figcaption></figure>

The **Available Agents** section is a read-only registry of the AI Workforce agents shipped with your deployment, for example:

| Agent                             | Purpose                                                                                 |
| --------------------------------- | --------------------------------------------------------------------------------------- |
| **Default supplier notification** | Generic supplier-notification email; the catch-all when no more specific agent matches. |
| **Banking Bot**                   | Specialised template for payment-data findings (IBAN/BIC corrections).                  |
| **Tax Bot**                       | VAT/tax-ID specific supplier notification.                                              |
| **Compliance Bot**                | Handles compliance findings.                                                            |

Each agent shows its Celery task and the finding-code prefixes it handles by default.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.docbits.com/administration-and-setup/settings/document-processing/e-documents/notification-routing.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
