> 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.md). # AI Prompt AI Prompt enables OvalEdge to generate descriptions for Data Catalog objects and Business Glossary terms by combining AI-generated content with information provided by subject matter experts. AI-generated descriptions based only on basic metadata can be incomplete or inaccurate, particularly when object names do not clearly explain their business purpose. AI Prompt addresses this limitation by collecting additional context through configurable questions and providing the collected information to the configured AI model. The feature supports two complementary approaches: * **AI-assisted description generation**, where AI generates descriptions based on available metadata and prompt question answers. * **Human-assisted curation**, where users answer business or technical questions to provide additional context that improves the quality of AI-generated descriptions. **Inputs Used for AI-Generated Descriptions** | Module | Inputs | | ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Business Glossary | Domain name, category name, subcategory name, term name, configured questions, and the corresponding answers. | | Data Catalog | Schema name, table/file/report/API/code name, table column/report column/file column/API attribute, data type, configured questions, and the corresponding answers. | ## How the AI Prompt Works The AI Prompt workflow consists of the following stages: 1. An administrator configures AI prompt questions. 2. Users select the applicable questions for an object. 3. Questions can be assigned to appropriate users through the Question Wall. 4. Assignees provide answers based on their knowledge of the object. 5. OvalEdge combines the available metadata and answers. 6. The configured AI model generates a description. 7. Users can refine the generated result by providing additional instructions or regenerating the description. The quality of the generated description depends on the context available to the AI. Descriptions can be generated without answering all questions, but providing complete and relevant answers can improve the result. *** 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.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.