> ## 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 semi-structured documents in Advanced Designer
> Advanced Designer scenarios for semi-structured documents — Deep Learning + Fast Learning, classification with rule fallback, or Classify + Extraction Rules.
Use Advanced Designer for [semi-structured document sets](/vantage/documentation/advanced-designer/use-cases/extracting-from-docs#semi-structured-documents) that are too complex for the cloud [Skill Designer](/vantage/documentation/skill-designer/skill-designer) alone — for example, sets with many varying layouts, outliers that need rule-based extraction, or insufficient training data for machine learning.
## Pick a scenario
| Scenario | When to use | Key activities |
| :----------------------------- | :----------------------------------------------- | :----------------------------------------------- |
| Many varying document variants | New templates keep appearing | Deep Learning + Fast Learning |
| Outliers needing rules | Most variants work with ML, but a few need rules | Classify + IF + Deep Learning + Extraction Rules |
| Limited training data | Not enough documents to train Deep Learning | Classify + Extraction Rules per variant |
Each scenario below follows the same pattern; only the activities you add to the processing flow differ.
## Common workflow
Open Advanced Designer and click **Create Document Skill** on the start page.
On the **Documents** tab, upload the documents you'll use to set up the skill. For scenarios that include classification, add a roughly equal number of documents for each variant so the classifier has balanced training data.
On the **Fields** tab, create and configure the fields the skill will extract. Label documents in the **Reference** section.
On the **Activities** tab, add the activities for your scenario (described below). Open each activity in the **Activity Editor** to configure and train it.
Click **Test Skill Using Selected Documents** to evaluate results. When the results are good enough, [publish the skill](/vantage/documentation/advanced-designer/document-skills/publish).
## Many varying document variants
Use this scenario when documents share a type but layouts vary widely — for example, invoices from many suppliers where new templates will keep appearing.
Pair a [Deep Learning activity](/vantage/documentation/advanced-designer/activities/deep-learning-semi-structured) with a [Fast Learning activity](/vantage/documentation/advanced-designer/activities/fast-learning):
* **Deep Learning** generalizes to unforeseen variants. Training requires at least 100 labeled documents.
* **Fast Learning** sharpens accuracy on the specific templates you've seen. It can also be trained continuously via the [Online Learning](/vantage/documentation/runtime/online-learning/online-learning) feedback loop from manual review.
## Outliers that need rule-based extraction
Use this scenario when most variants work with Deep Learning + Fast Learning, but a few documents have nested tables or other features that machine learning won't capture cleanly.
Separate the outliers with a Classify activity, then branch the flow with an IF activity:
* Use [Classify By Company](/vantage/documentation/advanced-designer/activities/classify-by-company) when the variants come from different companies whose name or address appears on the document — for example, bank statements from multiple banks.
* Use [Classify By Text and Image](/vantage/documentation/advanced-designer/activities/classify-by-text-and-image) in all other cases. This multimodal classifier uses text, layout, and image patterns to distinguish variants.
After branching, send outlier documents through an [Extraction Rules activity](/vantage/documentation/advanced-designer/activities/extraction-rules/extraction-rules) tailored to those documents.
## Limited training data
Use this scenario when you don't have enough documents to train a Deep Learning activity, but you have enough domain knowledge to describe the extraction rules — for example, tax forms that vary by year.
Split the documents with a Classify activity ([Classify By Company](/vantage/documentation/advanced-designer/activities/classify-by-company) or [Classify By Text and Image](/vantage/documentation/advanced-designer/activities/classify-by-text-and-image)), then route each variant through its own [Extraction Rules activity](/vantage/documentation/advanced-designer/activities/extraction-rules/extraction-rules). Optionally add a [Fast Learning activity](/vantage/documentation/advanced-designer/activities/fast-learning) so Vantage can refine the skill over time.
## Related activities
Generalize across many semi-structured layouts.
Sharpen accuracy on known templates with manual review feedback.
Define rule-based extraction for outliers or low-data sets.
Branch the flow by document variant before extraction.