Gen AI Risk Assessment for Cloud Optimization Recommendations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Assessing and implementing computing resources optimization recommendations in cloud environments is challenging due to the volume of recommendations, lack of domain knowledge, and the difficulty in determining the impact and risk of implementation, leading to inefficient and costly manual assessments.
Innovation Solution
A dynamic and robust risk assessment mechanism using a Generative Artificial Intelligence (Gen AI) model generates Optimization Implementation Risk Indicator (OIRI) scores and assessments to evaluate the risks associated with implementing computing resources optimization recommendations, providing users with informed decision-making.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual assessment of computing resources optimization recommendations is performed, then domain knowledge and careful evaluation can be applied, but labor costs and time consumption increase significantly
Solution Approach 1:
An AI model serves as an intermediary between the optimization recommendations and human decision-makers. The model processes recommendations, extracts relevant features, and generates risk scores and assessments, thereby reducing the time and effort required for manual evaluation while maintaining reliable decision support
Solution Approach 2:
The manual mechanical process of expert assessment is replaced with an automated AI-based system. The AI model automatically evaluates recommendations by analyzing features such as resource type, optimization type, and potential impact, substituting human labor with computational processing to reduce time costs
2Reliability
If comprehensive risk assessment of optimization recommendations is performed, then implementation risks are minimized, but system complexity and processing requirements increase
Solution Approach 1:
The risk assessment system is segmented into distinct functional modules: recommendation processing module, feature extraction module, risk scoring module, and assessment generation module. Each module handles a specific aspect of the assessment process, making the overall complex system manageable and maintainable through modular design
Solution Approach 2:
The AI model is designed to handle multiple types of optimization recommendations across different computing resources (virtual machines, containers, storage) using a unified assessment framework. This multi-functional approach reduces system complexity by avoiding the need for separate assessment systems for each resource type
3Productivity
If AI model is used for automated risk assessment, then labor costs are reduced and processing speed increases, but implementation complexity and computational requirements increase
Solution Approach 1:
The AI model performs self-service by automatically processing optimization recommendations, extracting features, generating risk scores, and producing assessments without requiring manual intervention. This automation increases productivity while the model handles its own computational requirements through efficient processing algorithms
4Measurement precision
If detailed feature extraction from recommendations is performed, then assessment precision is improved, but data processing time and computational resources increase
Solution Approach 1:
The system extracts only the most relevant features from optimization recommendations, such as resource type, optimization type, affected services, and potential impact metrics. By selectively extracting critical information rather than processing all available data, the system maintains high assessment precision while reducing data processing time
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Methods, systems, and computer-readable storage media for evaluating risks associated with implementation of computing resources optimization recommendations. A parquet file is generated for the computing resources optimization recommendations according to a predetermined format. The predetermined format includes a set of fields representing information of the computing resources optimization recommendations. The parquet file is processed to obtain values corresponding to a subset of the set of fields for each of the computing resources optimization recommendations and a prompt is generated based on the obtained values. Further, Generative Artificial Intelligence (Gen AI) model is used to generate an optimization implementation risk indicator (OIRI) score and an OIRI assessment of each of the computing resources optimization recommendations based upon the respective prompt. The OIRI score and the OIRI assessment along with each of the computing resources optimization recommendation are displayed in a graphical user interface of a client device of a user.