Date: Friday, July 18, 2025
Hi, we are Gizelle Gopez and Reagan Pearce from Evaluation and Research for Action (ERA) Center of Excellence (CoE), writing on behalf of the Health Evaluation TIG. This week you’ve heard from our colleagues on how Generative AI (GenAI) tools can be used across the evaluation lifecycle. These benefits include automation, optimization, content review and analysis, and overall productivity. Today, we’re sharing our tips for using GenAI on supporting the analysis and synthesis of evaluation data along with tools to help enhance your analysis.
Analyzing data using GenAI involves leveraging AI models to extract insights, identify patterns, and generate summaries. These tools include AI-powered text analysis platforms for understanding written feedback, coding assistants for statistical software, and data visualization tools that turn complex datasets into clear charts and graphs. Here are a few tips for using GenAI in your evaluation data analysis:
Hot Tip #1 – Confirm use of Gen AI: At this phase, you will have already collected your data, whether quantitative, qualitative, or a mix of both. Before using any type of GenAI tool, it is first important to confirm with your project leadership that it is permissible to use GenAI to analyze the data. Different clients, organizations, and/or projects may have different rules and regulations on the use of GenAI, and you’ll want to confirm the permissibility and parameters of its use.
Hot Tip #2 – Identify the appropriate tool: Next, you will want to identify the appropriate tool and platform to analyze your data. While there are a variety of tools on the market that are free, you’ll want to confirm that your data will be protected and safeguarded to ensure privacy of the client, project, and the individuals whose information may be gathered as part of the evaluation process.
Hot Tip #3 – Home in on specific GenAI features: For quantitative data, you first need to prepare your data, and you will want to look for tools that support data processing capabilities including cleaning and transformation, statistical analysis, and visualization options. Depending on the size of your data, you will want to see if machine learning, predictive modeling, and the ability to handle and process large data sets and support multiple data formats are available. Features for GenAI tools when analyzing qualitative data include NLP capabilities, sentiment analysis, thematic and content analysis, and text summarization.
Hot Tip #4 – Develop Strong Prompts: GenAI relies on prompts to guide the AI’s responses and outputs in analysis. When crafting prompts for data analysis, be specific and clear about the data context and desired outcomes. Include relevant details such as data sources, key variables, and the type of analysis needed. A well-defined prompt (see the previous blog posts this week on prompt development) helps the AI generate more accurate and useful insights but be prepared to iterate and refine your prompts based on the initial output from the tool to better align with your desired results.
As you navigate the evolving landscape of evaluation, incorporating GenAI into data analysis can offer valuable insights. While the tools mentioned above can enhance your capabilities, it’s crucial to apply human oversight to ensure AI-generated results are accurate and meaningful. By combining the power of GenAI with expert judgment, you can drive more informed decisions and impactful outcomes in your work.
Have a tool or a hot tip when it comes to using GenAI in evaluation? Drop them in the comments!
This posting contains general information only, does not constitute professional advice or services, and shall not be used as a basis for any decision or action that may affect your business. Deloitte shall not be responsible for any loss sustained by any person who relies on this posting. As used in this posting, “Deloitte” means Deloitte Consulting LLP, a subsidiary of Deloitte LLP. Please see www.deloitte.com/us/about for a detailed description of our legal structure. Certain services may not be available to attest clients under the rules and regulations of public accounting. Copyright © 2025 Deloitte Development LLC. All rights reserved.
The American Evaluation Association is hosting Health Evaluation TIG Week with our colleagues in the Health Evaluation Topical Interest Group. The contributions all this week to AEA365 come from our Health Evaluation TIG members. Do you have questions, concerns, kudos, or content to extend this AEA365 contribution? Please add them in the comments section for this post on the AEA365 webpage so that we may enrich our community of practice. Would you like to submit an AEA365 Tip? Please send a note of interest to AEA365@eval.org. AEA365 is sponsored by the American Evaluation Association and provides a Tip-a-Day by and for evaluators. The views and opinions expressed on the AEA365 blog are solely those of the original authors and other contributors. These views and opinions do not necessarily represent those of the American Evaluation Association, and/or any/all contributors to this site.