For the complete documentation index, see llms.txt. This page is also available as Markdown.

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.

Aspect
Summary

Execution

Requires a data object present in the workspace.

Marketplace

Recipes can be published without predefined ingredients.

Scenarios

Scenario
Ingredient Status

Specific data required, such as service request analysis

Ingredients required.

Flexible logic, such as data quality evaluation

Ingredients optional.

  • Execution depends on the availability of at least one data object.

  • Optional ingredients enable broader reuse of recipes across data environments.

For more detailed information, please refer to Recipe User Guide.


Copyright © 2026, OvalEdge LLC, Peachtree Corners, GA USA

Was this helpful?