Generative AI Workflow Automation via Clarifying Dialogs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional workflow automation software relies on detailed descriptions of operations, which can lead to incomplete or inaccurate workflow generation if the descriptions are insufficient, requiring manual intervention by users.
Innovation Solution
A generative AI model engages in a dialog with users to refine the understanding of a task by asking a series of questions and receiving answers, allowing the AI to automatically generate a workflow based on the user inputs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If workflow automation software uses a single detailed description to generate workflows, then automation extent is improved, but manufacturing precision deteriorates when the description is insufficient
Solution Approach 1:
The system performs preliminary actions by proactively generating clarifying questions before finalizing the workflow. The AI model asks questions about task details, required operations, and constraints to gather sufficient information upfront, ensuring accurate workflow generation without requiring manual correction later.
Solution Approach 2:
The system implements feedback by having the AI model generate questions based on the initial description and use the user's answers to refine its understanding. This iterative question-answer process provides continuous feedback loops that improve workflow generation accuracy while maintaining automation.
2Manufacturing precision
If manual workflow generation is used, then manufacturing precision is improved, but productivity deteriorates due to time consumption
Solution Approach 1:
The system enables self-service by allowing the AI model to autonomously generate workflows based on user inputs and automatically formulate clarifying questions when information is insufficient. This reduces the need for manual workflow generation while maintaining accuracy through the AI's self-directed question-asking process.
3Manufacturing precision
If more questions are asked during dialog, then manufacturing precision is improved, but loss of time increases
Solution Approach 1:
The system applies partial action by asking only the necessary number of questions required to generate an accurate workflow, rather than exhaustively questioning all possible aspects. The AI model selectively asks questions based on what is needed to achieve sufficient understanding for workflow generation.
Solution Approach 2:
The AI model performs preliminary analysis of the initial description to determine what specific information is missing, then asks targeted questions only about those gaps. This preliminary assessment prevents unnecessary questioning and reduces overall dialog time while maintaining accuracy.
Data Source
AI summary
Techniques are described herein that are capable of automatically generating a workflow using responses to AI-generated inquiries as inputs to a generative AI model. An initial prompt from a user is provided as an input to a generative AI model. The initial prompt indicates that a task is to be completed. Inquiries are provided in a first successive order to the user. The inquiries are generated by the generative AI model based at least on the initial prompt. The inquiries solicit information regarding the task. Response prompts are received in a second successive order that corresponds to the first successive order. The response prompts are responses to the respective inquiries. The generative AI model is caused to automatically generate a workflow, which is configured to achieve the task, based at least on the response prompts.