# Generative AI Learning

To use the Generative AI Learning feature, select the **Gen AI Learning** tab from the Aisera Administration application (Admin UI).\
\
The **Generative AI Learning** window includes a **Summary** of the knowledge gained from ingested data, and then breaks down the data to **Ticket Learning**, **Knowledge Learning**, and **Case Insights**.

<div align="left"><figure><img src="/files/pLqQDIkjxpsAtNbUYCSo" alt="" width="563"><figcaption><p>Case Insights Tab</p></figcaption></figure></div>

The Aisera AI Gen Platform needs to process some of your enterprise software's institutional knowledge so your applications/bots can answer questions based on the information in your enterprise Tickets and Knowledge Articles.&#x20;

In addition, the platform uses information about Users, Groups, and Permissions to deliver the correct content to the correct audience (users or teams).

**When data is ingested, three types of objects (Aisera Entities) are being pulled in:**

1. **Knowledge** (`LearnKB`) - *What answers already exist?*

Pull in KB articles from **Confluence, SharePoint,** ServiceNow, Zendesk, etc. so the AI can answer employee questions directly ("How do I reset my VPN?") without creating a new ticket.

2. **Tickets & Incidents** (`LearnTickets`, `LearnIncidents`) - *What problems have people had before?*

Pull in historical tickets from **Salesforce, Jira, ServiceNow, Zendesk**, etc. so the AI can recognize recurring issues, suggest resolutions based on past solutions, and route new tickets intelligently.

3. **Users, Groups & Permissions** (`LearnUsers`, `LearnUserGroups`) — *Who is asking, and what are they allowed to see?*

### Ticket Learning

**Ticket Learning** helps you analyze your ticket inflow and assess how effectively the Aisera Gen AI Platform processes your issues. This efficiency enables automated answer generation, leading to reduced ticket creation and minimized manual resolution efforts by IT agents.

Additionally, **Ticket Learning** identifies areas where issues are not processed correctly ('not understood by the bot') and highlights the modules in the Aisera Gen AI Platform that can address and improve these gaps. This module plays a vital role in assessing customer data and projecting automation opportunities.

See **Set Up Ticket Learning** and **Analyzing Ticket Learning Output** for details.

### Case Insights

Use the **Case Insights** tab tab to review your tickets by clusters.

You can use clusters to see the Top Drivers of tickets receiving Negative Feedback on Agent Assist recommendations or receiving No recommendations at all (Knowledge Gaps).

1. Gen AI Learning > Case Insights > and then choose the ‘Start Learning Job’ button to display the Learning Configuration window.

<figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXfzt-79gLe_AKnqbF842Bq7whyS4cqW1FakcotnYn9dxJY8O4WffbaYI2cYMrICSFY7VQxKogG1CB4FNR_3PCnRwDNb68bWeZPmFq30E0zuD8wyt8TjRqTv6vDnU1A_F_Y6Nt_GiA?key=32daBUKwJuG0RBHF93yiY93O" alt=""><figcaption><p>Case Insights Job Results</p></figcaption></figure>

2. Configuration > Select the criteria of tickets you want to consider (a few important items are shown below).
   1. Add a ‘Job Name’ - Include details on your configuration criteria so you can remember when viewing past jobs
   2. ‘Data Source’ field is Required&#x20;
   3. Add ‘Last Updated’ to select the date range of tickets you would like to job to look at&#x20;
   4. ‘Feedback Type’ - Select Summary, Answer or Next Best Actions depending on your criteria
   5. ‘Feedback’ - Select Positive or Negative depending on your criteria
   6. Or ‘Recommendation State’ - Select all&#x20;
      1. Use Recommendation State only (not Feedback field) if you want to see the Knowledge Gaps&#x20;

<figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXdC0FLRe76-f6ivgkQsvxORaCilXQ_b2hZdb7vPuHStOTyMtTFS-toXg8P6Kr4bDL2dgHVy22qeKz6IeImPeNRioLar20Sw_4Y1YKkI_94_0AgbN6mQcrkHjEB1XKYrJ8A_gDKScA?key=32daBUKwJuG0RBHF93yiY93O" alt="" width="563"><figcaption></figcaption></figure>

<figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXdWb2PD5CbFQ-o9z1efxg5wDzctHnVMM1YUOiw6UcJnUOMLhcbBHMUvYGyfqAlmVC7PELrzKI_hOnDurIfhKGvKGX-lI8p1KcbL4CiRDnshyAWv1A9Co-vbhJU0qXc5JBw3e7ezjA?key=32daBUKwJuG0RBHF93yiY93O" alt="" width="563"><figcaption></figcaption></figure>

3. Go to the Preprocessor tab and select ‘Title and Description’ in ‘Fields to process’.&#x20;
   1. You can add any other exclusion criteria as desired to have a clean set up tickets

<div align="center"><figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXelra_JC8tOJz28Bd4FeE6SNvVXBxuiBYXVENuVEGqdb3YGrCyyzQ08JMrWmE3HgPWvHvxPithQkmGBkWFmLzW8D2mMixZMPHC-FbIdQRWkHDzJsRtIRa8-HRBl-rnIB5x7JsbH?key=32daBUKwJuG0RBHF93yiY93O" alt="" width="563"><figcaption></figcaption></figure></div>

4. Run **Start Learning Job**
5. Monitor Case Insights Job Status in the Jobs Page&#x20;
6. Once Job completes, you can review the top clusters formed out of the tickets on the Case Insight tab.


---

# 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.aisera.com/aisera-platform/generative-ai-learning.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.