The first thing I did wrong was ask ChatGPT what a passage meant.
It answered. Of course it answered. It gave me something coherent, well-organized, and almost entirely beside the point. I had gone to a text that has unsettled serious people for two thousand years and received, in under three seconds, a summary that made it feel resolved. That is not Bible study. That is Bible sedation.
The second thing I did — after Conor Grennan talked me out of giving up on the experiment entirely — was ask a different question. Not "what does this mean" but "what does this passage refuse to settle?" The difference in output was not incremental. It was the difference between a closed door and an open one.
Key facts
- 01AI tools like ChatGPT can provide instant historical and cultural context for Bible passages — background information that used to require a commentary library.
- 02The episode emphasizes using AI for "pre-reading" context rather than letting it interpret meaning, preserving the reader's own encounter with the text.
- 03Conor Grennan describes prompting AI to surface questions a passage raises rather than answers it provides, which deepens rather than shortcuts personal reflection.
- 04The hosts caution that AI's spiritual guidance should always be weighed against community, tradition, and prayer — not treated as authoritative on its own.
This is the thing nobody tells you about using AI for Scripture: the tool is only as searching as the question you bring to it. Ask it to explain, and it will explain. Ask it to comfort, and it will comfort. Ask it to challenge you, to find the tension in a text you've read so many times it's stopped landing — and it will do that too, with a thoroughness that would have taken you an afternoon in a seminary library.
“Ask AI what the text means, and you'll get an answer. Ask it what the text refuses to resolve, and you'll get a Bible study.”— Jaeden Schafer
The question is what you're actually after.
Most people who grew up in church were trained, subtly and persistently, to want resolution from the Bible. The sermon ends with an application point. The small group ends with a takeaway. The devotional ends with a prayer you can say to close the loop. This is not entirely wrong, but it produces a kind of spiritual incuriosity that is genuinely dangerous — a habit of arriving at the text with the answer already in your pocket and using the reading to confirm it.
AI, deployed carelessly, accelerates that habit at scale. It is very good at producing the answer you were already looking for. Feed it your assumptions and it will hand them back to you, polished.
But AI deployed with intention is something different. Conor and I spent a month experimenting with prompts, and the ones that produced the most genuinely useful output shared a common feature: they asked the AI to do something harder than explain. They asked it to surface what scholars have disagreed about. To find the interpretive pressure points. To provide the cultural background that made the first listeners hear something completely different from what modern readers assume.
That background is where the power is. First-century listeners hearing Jesus's parables understood the social stakes of a Samaritan, the legal implications of a prodigal son's request, the political danger of a king's wedding feast in a way that most contemporary readers simply don't. AI can reconstruct that context quickly and accurately. And context, it turns out, is not the enemy of mystery — it's often what restores it. A passage that seemed obvious becomes strange again when you understand what it actually cost to say it.
There is a harder point underneath the practical one. The reason AI can be useful for Bible study is that most of us have impoverished access to the scholarly tradition that the church has built over centuries. Commentaries exist. Lexicons exist. Church fathers and Reformation thinkers and liberation theologians have all wrestled with these texts and left records of the fight. Most people in most pews never encounter any of it. AI makes that tradition accessible in a way that nothing before it has.
That is a genuine gift. It is also a responsibility. Because the tradition is not neutral, and AI doesn't always tell you which tradition it's drawing on. Push back on it. Ask whose reading this is. Ask what a different tradition would say. The text is large enough to hold the disagreement.
What AI cannot do is be present with you when the passage lands in a way that changes something. That moment — which is what serious readers of Scripture are always waiting for — happens in you, not in the model. The tool can get you to the door. It cannot walk you through.
Jaeden Schafer is the host of AI in Faith, a podcast about artificial intelligence, faith, and the future of human purpose.
Working on something we should cover, or seeing a story we missed? Send leads, documents, or feedback to hello@aichatdaily.com. For sensitive tips, see our secure tips page for Signal and PGP options.
Spotted an error? Email hello@aichatdaily.com with the URL and the issue, or read our full corrections policy.
