# Sherpa Process Discovery

**Sherpa Process Discovery** is an analyst tool for identifying opportunities for automating business processes within an enterprise, providing the identification and description of routine business processes using machine learning and artificial intelligence methods.

The main task of Sherpa Process Discovery is to determine which processes within the enterprise are suitable for automation or robotization. To achieve this, data on employee activities is collected and processed in several stages:

1. **Process Discovery**\
   The neural network analyzes repeating sequences of actions, identifies their variations, and assesses the potential for automation.\
   Based on the results, a detailed report (PDD — Process Definition Document) is generated with sequences of steps and possible robotization scenarios.
2. **Process Analysis**\
   The system analyzes business processes to identify repetitive routine tasks.
3. **Automation Recommendations**\
   Based on the collected data, recommendations for automation are created, as well as prototypes of solutions and descriptions of scenarios for Robots, significantly speeding up the implementation phase.

## Technology of Sherpa Process Discovery

<figure><img src="https://3237142148-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FscP4BXwl9ufpJr5mfVln%2Fuploads%2Fgit-blob-a2386892b85ce6b542e16c32771e6e3200a2a0c2%2FPD.png?alt=media" alt=""><figcaption></figcaption></figure>

The system is based on the following methods:

* **Computer Vision** (OCR, contour and object detection) for recognizing interface elements.
* **Natural Language Processing** (NLP, lemmatization, NER) for analyzing text and descriptions.
* **Intelligent Decision Support**: process mining, Petri net generation.
* **Clustering and Classification Methods** for segmenting processes and identifying typical scenarios.

## Operating Modes

Sherpa Process Discovery can operate in the following modes:

* **Task Mining** — collecting data on employee actions (mouse clicks, scrolling, dragging, screen changes), aimed at identifying repetitive actions and modeling work scenarios.
* **Deep Task Mining** — includes all types of data from the previous type, as well as creating screenshots with each action for a deeper analysis of visual interface elements.
* **Process Mining** — uploading already prepared data from external systems with information about business processes for analysis and optimization.

## Recommendations for Process Automation

It is recommended to automate Processes that are characterized by:

* high labor intensity (duration/frequency);
* significant time costs;
* high cost;
* an estimated level of robotization of more than 50%.

## Advantages of Sherpa Process Discovery

Using this technology allows for:

* significant time savings in identifying automatable processes,
* increased accuracy of analysis and reduced implementation risks.

Automated data collection and analytics ensure objectivity in assessment, while integration into work processes prevents data leakage.


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.sherparpa.ru/en/sherpa-process-discovery.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.