> 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.
​![Shape](data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsMAAA7DAcdvqGQAAAANSURBVBhXY2BgYGAAAAAFAAGKM+MAAAAAAElFTkSuQmCC) 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.