> 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/release8.2/askedgi/askedgi/recipes.md). # Recipes This article explains how to create and use recipes in askEdgi. It describes how to save analysis workflows, including datasets, queries, AI enrichments, and visualizations, so they can be reused without repeating the same steps. ### Why Recipes Matter Ad-hoc analysis provides quick insights, but repeating the same steps manually is inefficient. Recipes capture the entire workflow, datasets, joins, AI enrichments, and visualizations. A saved recipe can be rerun with fresh data, reused internally, or shared through the Marketplace in Public deployments.
### What Can Be Done with Recipes * Save analysis sessions, including datasets, joins, AI enrichments, and outputs * Assign a descriptive name and purpose * Store ingredients (datasets metadata) and steps (queries, prompts, enrichments) * Reuse workflows without retyping instructions * Publish recipes to the Marketplace for wider adoption #### Use Case & Real-Life Scenario After completing a product returns analysis by joining orders and returns, calculating return rates, categorizing products, and applying sentiment analysis, the workflow was saved for reuse within the company. Recipe Name: Product Returns & Sentiment Analysis Description: Analyzes return rates, classifies high-return products, and correlates with customer sentiment Ingredients: orders, returns, customer\_reviews Steps: * Join orders and returns on order\_id * Calculate return\_rate column * Classify products into High/Medium/Low return categories * Apply sentiment analysis on customer reviews (sentiment\_label) * Generate a bar chart of returns vs. sentiment * The recipe is saved to the Recipe Catalog for future reuse.
AspectSummary
ExecutionRequires a data object present in the workspace.
MarketplaceRecipes can be published without predefined ingredients.
**Scenarios**
ScenarioIngredient Status
Specific data required, such as service request analysisIngredients required.
Flexible logic, such as data quality evaluationIngredients optional.
{% hint style="info" %} * Execution depends on the availability of at least one data object. * Optional ingredients enable broader reuse of recipes across data environments. {% endhint %} For more detailed information, please refer to [Recipe User Guide](https://docs.ovaledge.com/release8.1/askedgi/user-guides/recipe-user-guide). *** Copyright © 2026, 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 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.ovaledge.com/release8.2/askedgi/askedgi/recipes.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.