> For the complete documentation index, see [llms.txt](https://docs.ovaledge.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ovaledge.com/release8.3/ai/ai-prompt/ai-prompt-and-audit-trails.md). # AI Prompt and Audit Trails AI Prompt Audit Trails provide visibility into AI interactions so administrators can understand which AI model processed a request, what prompt and instructions were used, what response was returned, and how many tokens were consumed. The Audit Trails > AI area contains two relevant tabs that provide AI prompt context for different workflows: OvalEdge AI Audits and askEdgi Audit. View the two tabs separately, as each records a different type of AI interaction. ## OvalEdge AI Audits The OvalEdge AI Audits tab records AI activity generated by OvalEdge. For AI Prompt and description generation, select Description Generation to view the related audit records. The audit record provides execution details that help administrators trace the AI request and troubleshoot failures or unexpected results. ![](https://content.gitbook.com/content/8fgltewNgYZ8ucAp7Svt/blobs/mXptNFvlhE1qvHUL1C9y/unknown.png) The available columns include: | Column | Description | | ------------- | ------------------------------------------------------------------------------------------------------------------------------------------- | | AI Engine | The AI engine used to process the description-generation request. | | AI Model | The model used to generate the description. | | Object Type | The type of object for which the description was generated. | | Object Name | The name of the object for which the description was generated. | | Field | The description field for which the AI request was generated, such as Business Description, Technical Description, or Detailed Description. | | Prompt | The prompt sent to the AI model for description generation. | | Instructions | The instructions provided to guide the AI model when generating the description. | | AI Response | The response generated by the AI model. | | Error Message | The error returned when the description-generation request fails or encounters an issue. | | Total Tokens | The total number of tokens consumed during the AI interaction. | | Created By | The user associated with the description-generation request. | | Created Date | The date and time when the AI interaction was recorded. | **Example**: If an AI-generated Business Description is created for a table, the audit record can identify the table, the AI model used, the prompt and instructions provided, the generated response, the token consumption, the execution time, and any error details. ## askEdgi Audit The **askEdgi Audit** tab records conversational AI interactions initiated through askEdgi. For AI Prompt context, select **User Prompts** to view the related interactions. In this workflow, the user prompt and the AI response are the primary audit inputs and outputs. ![](https://content.gitbook.com/content/8fgltewNgYZ8ucAp7Svt/blobs/7MyUO87yLaQFlLDrito5/unknown.png) The **User Prompts** audit screen also displays the total input tokens and total output tokens at the top of the page. The available columns include: | Column | Description | | ----------------- | ---------------------------------------------------------- | | AI Engine | The AI engine used for the interaction. | | AI Model | The model used to process the askEdgi request. | | User Name | The user who initiated the interaction. | | Conversation Type | The type of askEdgi interaction, such as a prompt. | | Prompt | The request submitted to askEdgi. | | Response | The response generated for the prompt. | | Error | Any error captured during processing. | | Input Tokens | The number of tokens consumed by the request input. | | Output Tokens | The number of tokens generated in the response. | | Created Date | The date and time of the interaction. | | Cost | The recorded cost of the LLM call. | | LLM Call Details | Additional technical details captured for the LLM request. | **Example**: A user asks askEdgi, “How many tables are available in a schema?” The askEdgi Audit tab can record the prompt, the AI model, the generated response, input and output token usage, cost, timestamp, and any processing error. *** Copyright © 2025, OvalEdge LLC, Peachtree Corners, GA, USA. --- # 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 by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.ovaledge.com/release8.3/ai/ai-prompt/ai-prompt-and-audit-trails.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.