Using AI to Train Students for Meaningful Spiritual Conversations

Published: 26 Apr 2026, Last Modified: 26 Apr 2026CEC 2026 OralEveryoneRevisionsCC BY 4.0
Keywords: Artificial Intelligence, Large Language Models, Faith Learning Integration, Spiritual Conversations
TL;DR: Analysis of assignments that utilize LLMs to help students practice faith conversations.
Abstract: The engineering workplace can be a spiritually dark place in need of the light of the Gospel of Jesus Christ. Jesus’s Great Commission calls all Christians to go make disciples of people in all nations, including those in the engineering profession. However, research shows that the number of Christians actively sharing their faith has dramatically dropped over the last few decades, often due to insecurity or lack of experience in faith-based conversations. As Christian Engineering educators, we are called to train Christian engineers who are both technically excellent and can love their coworkers well through civil conversations on spiritual matters. To that end, we have integrated a discussion of Questioning Evangelism by Randy Newman into a junior-level engineering project curriculum and augmented the assignments with Artificial Intelligence (AI) spiritual conversation practice. Students use Large Language Model (LLM) AI to engage in low-stakes practice conversations using engineered prompts that portray a range of perspectives, from culturally Christian to staunch atheist. These exercises allow students to practice discourse techniques from readings, build conversational skills, and gain confidence before engaging in peer debrief discussions. Student feedback has indicated that these exercises have been an effective means of both solidifying helpful conversation techniques discussed in the readings and diminishing anxiety around faith conversations in the workplace through simulated practice.
Email Sharing: We authorize the sharing of all author emails with Program Chairs.
Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.
Submission Number: 11
Loading