> For the complete documentation index, see [llms.txt](https://docs.aisera.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aisera.com/aisera-platform/content-generation-from-tickets/analyze-kb-article-generation-results/ai-generated-document-details-side-panel.md).
# AI Generated Document Details Side Panel
The document details page includes several additional options in the left-side panel.
 These options include:
#### KB Generation Accuracy Feedback
You can provide feedback for AI-generated documents on the **Knowledge Details** page using the following options:
* **Highly Accurate:** Indicates complete satisfaction with the generated document.
* **Moderately Accurate:** Indicates the document is mostly correct but contains minor issues.
You can select **sub-options** to specify the nature of the issue:
* **Inaccurate:** Indicates the document is incorrect or not useful. Sub-options are available to help identify the specific issue. The sub-options that are available to the you change based on the option radio buttons that the you choose.
* **Additional Comments:** You can provide additional feedback in a **free-text** field. This feedback helps Aisera improve the quality of generated knowledge documents. If you submit feedback multiple times, the latest feedback will override the previous one. Only the most recent feedback is considered.
* **Data Source:** This field displays the data source associated with the AI-generated document. All AI-generated documents are linked to an automatically created data source generated during the job run.
* **Naming Convention:** `Generated Document `
* **Similar Documents:** This field shows the number of customer crawled documents that are similar to the AI-generated document. This is the same **Similar Documents** field that appears on the AI Generated Documents page.
* **Created On:** Displays the date and time when the AI-generated document was created.
* **Validated Chunk:** The Validated Chunk represents the raw comment or resolution content identified by the system as containing a potential solution.
### How It Works
The Resolution Classifier service analyzes ticket comments and resolution notes.
It extracts only the lines that are likely to contain a solution.
Based on the analysis, the system assigns a quality tag, such as:
* **Very Good**
* **Good**
* **Poor**
You can review the **Validated Chunks** for all tickets within a cluster.
Instead of reading all ticket comments, you can focus on the key extracted lines, making it easier to compare them with the generated knowledge article.
### Where Validated Chunks Are Visible
Validated Chunks are visible:
* on the **Ticket Details** page for tickets categorized as **Good**, **Very Good**, or **Poor** quality
* on the left-side panel of the generated knowledge article
### Source of Solution Extraction
To ensure higher accuracy and avoid confusion in knowledge generation, the system extracts solutions from only one source at a time.
The solution is extracted from either:
* **Resolution Notes**, or
* **Ticket Comments**
Extracting from both sources simultaneously may introduce:
* Conflicting information
* Misleading context
* Lower quality outputs from the LLM
If required, external comment fields can be concatenated during data ingestion, as mentioned in the prerequisites.
---
# 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 dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.aisera.com/aisera-platform/content-generation-from-tickets/analyze-kb-article-generation-results/ai-generated-document-details-side-panel.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.