Using ChatGPT as Your Analytics Partner: What Evaluators Should Know by Wheeler del Torro

Date: Monday, April 28, 2025

Hello, AEA365 community! Liz DiLuzio here, Lead Curator of the blog. This week is Individuals Week, which means we take a break from our themed weeks and spotlight the Hot Tips, Cool Tricks, Rad Resources and Lessons Learned from any evaluator interested in sharing. Would you like to contribute to future individuals weeks? Email me at AEA365@eval.org with an idea or a draft and we will make it happen.

Greetings, readers! I’m Wheeler del Torro, Co-Founding Advisor of Evaluation + Learning Consulting (ELC).

As evaluators, we’re always looking for ways to strengthen our analysis, storytelling, and reflection processes. Lately, many of us are asking: can AI tools like ChatGPT really help without compromising the rigor of our work?

The answer is yes, if we use it thoughtfully.

Nearly a year ago, my colleague Liz DiLuzio put forth a framework for incorporating AI into the data analytics process. In the past year, our team at ELC has put the framework to the test, uncovering strengths, limitations, and exceptions to its guidelines. I’d like to share some learnings with you today.

Lessons Learned

• ChatGPT works best when treated as a tool to support, not replace, critical thinking. We recommend thinking of it like an eager intern: fast, flexible, and full of ideas, but needing careful guidance. It’s great for brainstorming, clarifying logic, summarizing results, and helping reframe findings for different audiences.
• It’s your job to know and guard against its risks. Common risks include data security, biases, and hallucinations.
• Throughout the data analysis lifecycle, ChatGPT can serve three main roles:
  • Planning Partner: Early in a project, ChatGPT can help identify key variables, suggest comparisons, and structure analysis plans. It can surface background factors you might not have considered and help tailor priorities for different stakeholder groups.
  • Assistant Data Analyst: During data cleaning and preliminary analysis, ChatGPT can draft formulas, check logic, and suggest efficient workflows. It can offer a second perspective on structure and approach, especially when time is tight.
  • Storytelling Partner: When it’s time to share findings, ChatGPT can help refine summaries, shift tone for different audiences, tighten language, and explain limitations in accessible ways.
• At every stage, it’s critical that the user stay in charge. ChatGPT can make us more structured, reflective, and clear, but it cannot replace our judgment, contextual knowledge, or ethical responsibility.

Used strategically, ChatGPT isn’t about cutting corners. It’s about amplifying our thinking and strengthening the impact of our work.

Rad Resource

Interested in exploring these and other lessons learned? We’re offering a free, one-hour webinar to dive into these and other learnings on Monday, May 5th @ 3pm EST.

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.