---
title: "Validate a document package"
slug: "verifying-a-document-package"
updated: 2025-12-10T15:24:30Z
published: 2025-12-10T15:24:30Z
canonical: "knowledge.lightico.com/verifying-a-document-package"
---

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

# Validate a document package

This article explains how to access and validate the AI-generated analysis for each document in the Document Analyzer.

You'll learn how to review the details of individual documents, and approve or correct the AI's classification, extracted data, and rule evaluation, ensuring the analysis meets your standards before submission.

The explanations in this article, in general, are relevant to document analysis run in both **HITL**(Human In The Loop) and **STP**(Straight-Through Processing) mode. However, some of the UI options apply only to HITL mode. See [below](/v1/docs/verifying-a-document-package#validating-or-editing-an-analysis-package-in-stp-mode)to understand the differences in validating an analysis package in STP mode.

---

## Validating or editing an analysis package in STP mode

When the document analysis runs in **STP (straight-through processing) mode**, the analysis is automatically submitted as soon as it completes. The [Document analysis completed](https://developers.lightico.com/docs/api-reference/lcsk7yvan13da-document-analyzer-events#document-analysis-completed) event is already sent, and there is **no approval step** required from an agent or admin. Opening the analysis in this mode serves one purpose: **to correct the results when necessary.**

### How STP validation differs from HITL validation

**1. No approval controls** In HITL mode, agents explicitly confirm analysis results using approval actions. In STP, these controls are removed because the analysis has already been finalized and reported. There is **nothing to approve**.

**2. Reject-and-correct only** In STP, the available action is to **reject** an item and provide a corrected value. This is used when the automated results caused downstream issues—for example, a rule evaluation failed but the agent determines the extracted value should be adjusted.

**3. Edits trigger a new event** After making corrections, the agent resubmits the updated results. This triggers the [Document analysis modified](https://developers.lightico.com/docs/api-reference/lcsk7yvan13da-document-analyzer-events#document-analysis-modified) event, allowing downstream systems to react to the updated outcome.

### Typical use case

A document analyzed in STP mode fails a rule. An agent reviews the failure reason, determines that a specific extracted value should be corrected, updates it, and resubmits. No approval is required—only correction where appropriate.

---

## Validate the AI analysis of each document class

Validation requires a co-pilot user to approve or correct different aspects of the AI analysis. There are three aspects of the AI analysis that require validation for each document class:

- **Classification**- Type of document, for example: pay slip, utility bill, or bank statement. Every analysis package has defined documents types on which the AI model was trained.
- **Extracted data** - Individual data points extracted and identified by the AI model. Each data point is assigned to a Lightico Attribute.
- **Rules**- Business rules defined in the analysis package. Extracted data is marked as **Pass**or **Fail**based on whether it meets the requirements.

**To validate the AI analysis of a document class:**

1. On the [document package overview page](https://knowledge.lightico.com/docs/overview-a-document-analysis-package#document-package-overview-page), click a document class. ![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/2025-05-11_10-10-20(1).png) The selected classification opens.
2. Validate each of the following aspects of the analysis:
  - [Classification](/v1/docs/verifying-a-document-package#classification)
  - [Extracted data](/v1/docs/verifying-a-document-package#extracted-data)
  - [Rules](/v1/docs/verifying-a-document-package#rules)

---

## Classification

The AI model analyzes each page of an uploaded PDF file and decides to what class each page belongs. It then groups all pages of the same class and presents them as one document class in the Document Analyzer UI.

### Validating the classification

**To review and validate a document classification:**

1. On the [document package overview page](https://knowledge.lightico.com/docs/overview-a-document-analysis-package#document-package-overview-page), click a classification. ![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/2025-05-11_10-10-20(1).png)

The classification opens.
2. Complete the classification validation by doing the following in the right pane:
  - If the classification is correct for this page, click the thumbs up.
  - To change the classification for this page, see [below](/v1/docs/verifying-a-document-package#change-the-document-classification).
  - If there are multiple pages of this document, make sure to either approve or change the classification for all pages.
  - To approve the classification for all pages, click **Confirm all pages**. ![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/2025-05-08_17-52-04(1).png)

### Change the page classification

If the AI classification is incorrect, you can manually assign a different classification. Some available classifications may not have been trained on the AI model, but using them improves accuracy and can help to train the model for future use.

> [!NOTE]
> Note
> 
> If you reclassify a page that included extracted data, you will need to resubmit the package for AI analysis. See [below](/v1/docs/verifying-a-document-package#reanalyzing-the-package).

**To change the page classification:**

1. Click the thumbs down. ![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/2025-05-21_10-22-00(1).png)

The **Select classification** dialog opens.
2. Select a new classification and click **Save**.

> [!TIP]
> Tip
> 
> Classifications that have been trained on the AI model show an icon, as illustrated below.

![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/image(333).png)

> [!TIP]
> - If the page does not fit into any of the classifications, click **Mark as unclassified**.
> 
> The page is moved to the **Unclassified**documents list.
> - To restore the original classification assigned by the AI model, click the thumbs up.

### Validating unclassified documents

The package may contain documents that the AI model could not associate with any of the known document types in this package.

**To validate an unclassified document:**

1. Click the document to open it. ![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/image(226).png)
2. Click the thumbs down and select a document type -OR- submit the package with the unclassified status.

### Reanalyzing the package

When you reclassify a page from which data was extracted, all extracted data and rule decisions are removed from all pages in the original class. This is because extraction and rules are based on the class of the pages. In this case you need to resubmit the package for AI analysis.

On the package overview page, a status of **Analysis required** shows for classes that need reanalysis.

![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/2025-05-19_10-28-45.png)

**To reanalyze the package**:

1. Click **Reanalyze**in the top right corner of the package overview page. ![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/2025-05-19_10-35-21.png)
2. Confirm the action. ![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/2025-05-19_10-42-07.png)

The package is sent for AI analysis.

---

## Extracted data

The reviewer is required to approve or reject each piece of extracted data before submitting the document for review.

**To validate extracted data:**

1. Select a piece of data. The data is highlighted in the document view. ![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/image-1738852808838.png)
2. Review each piece of data and either:

Click the thumbs down to reject and correct the extracted information (see [below](/v1/docs/co-piloting-a-package#correcting-extracted-information)) -OR_

click the thumbs up to approve the information. ![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/image(222).png)

### Correcting extracted information

If you see that a piece of data was extracted incorrectly, you can reject it and change it to the correct information.

> [!NOTE]
> Note
> 
> When you correct extracted data, rules are recalculated. A **Pass**status for a rule may change to **Fail**and vice versa.

**To correct extracted information:**

1. Click the thumbs down icon. ![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/image-1737971710342.png)
2. Enter the correct version of the data in the box and click **Done**. ![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/2025-01-27_11-41-54(1).png)

The information is recorded in this document as you corrected it and it is marked as **Edited**. ![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/image(218).png)

---

## Signatures

The **Signatures** tab shows analysis results relating to signatures in this document class. Document Analyzer finds areas that are expected to be signed and displays one of the following statuses:

- **Signed**- A signature was found
- **Missing**- No signature was found

**To validate document signatures:**

1. Click the **Signatures** tab in the right pane.
2. Either approve (thumbs up) or reject (thumbs down) each of the signature result. ![Signatures tab with identified signature](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/2025-09-18_16-50-10.png)

---

## Rules

Use the **Rules**tab to verify whether the extracted data met the defined analysis requirements. You may want to review the reason for a failure or confirm that a pass status is accurate.

Even if a document fails one or more rules, it can still be validated and submitted. The final analysis report will indicate that the document did not comply with specific rules.

### Reviewing rule results

- Click the **Rules**tab in the right pane.
- If the document status is **Fail**, the pane will display the reason for the failure.

![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/2025-02-06_17-53-43(1).png)

### Overriding a rule decision

In some cases, a rule may be met, but Document Analyzer fails to recognize it correctly. To ensure accuracy, you can override the decision when necessary. For example, the AI might not identify a close name match, such as **Bill**vs. **William**or **Bob**vs. **Robert**, or it may fail to recognize an abbreviation, like **Mn St** instead of **Main Street.**

**To override a rule decision:**

1. In the Rules panel, next to the **Fail**status, click the options menu and select **Switch to Pass**. ![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/image(329).png)
2. Confirm the change. ![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/image(330).png)

The status is changed to **Pass**with an indication next to it that the status was manually edited. ![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/image(331).png)

> [!TIP]
> **To change the status to *Fail*:**
> 
> Click the options menu and select **Switch to Fail**. ![](https://cdn.document360.io/473bb8c5-ff1b-4930-8109-2321ac6ab967/Images/Documentation/image(332).png)

## Q & A

****If I upload multiple instances of the same class of document, for example, pay slips or bank statements for three different months, will they be grouped together into one document?****

Yes. However, you can separate the pages by manually reclassifying them. See [above](/v1/docs/verifying-a-document-package#change-the-page-classification).

****Can I submit a document package if some documents fail one or more rules?****

Yes. Even if a document fails some rule checks, you can still validate and submit it. The final analysis report will clearly indicate which rules were not met.

****What happens if I change the classification of a document that already had extracted data?****

When you reclassify such a document, all extracted data and rule results associated with that classification are cleared. You’ll need to **resubmit the package for AI analysis** to regenerate the data.

****Do I need to validate every page of a multi-page document individually?****

Yes. Each page must be approved or manually classified to complete the validation. You can use **Confirm all pages** to approve the same classification for all pages in a document.

****If****I click Confirm all, what happens to the items that I rejected****?****

**Confirm all** preserves any rejected (thumbs down) feedback and corrections made to the page classifications, extracted data or signatures.

****Can I override a rule that was incorrectly marked as failed?****

Yes. You can manually switch a rule status from **Fail**to **Pass**(or vice versa) if you determine that the rule was not interpreted correctly by the AI.

****What does "Unclassified documents" mean?****

These are pages the AI could not confidently associate with any known document class. You can either manually assign a classification or submit them as unclassified.

****Can I undo a manual classification change and restore the original AI classification?****

Yes. To restore the original AI classification, simply click the **thumbs up** icon after a manual change.

A module in the Lightico platform that performs an AI-based analysis of uploaded documents to extract structured data, classify document types, and evaluate business rules. The interface enables agent review, feedback, and corrections.

An identifying label that you bind to data in a session that enables you to organize and make use of the data during the session.