How a 91-year-old vibe coded a complex church event management system using Claude and Replit
John Blackman (guest), Claire Vo (host)
In this episode of How I AI, featuring John Blackman and Claire Vo, How a 91-year-old vibe coded a complex church event management system using Claude and Replit explores a 91-year-old builds church event software via Claude and Replit John Blackman, a 91-year-old church volunteer, describes turning a manual paper-based “impact weekend” registration process into a full web app by using Claude to generate a roadmap, user stories, and requirements, then feeding that into Replit Agents to implement the system.
A 91-year-old builds church event software via Claude and Replit
John Blackman, a 91-year-old church volunteer, describes turning a manual paper-based “impact weekend” registration process into a full web app by using Claude to generate a roadmap, user stories, and requirements, then feeding that into Replit Agents to implement the system.
The app supports multiple churches and events with role-based admin levels, participant registration via QR codes, service toggles, waivers and signature capture, and printable “impact passports” (PDFs) that attendees can bring to the event.
It also generates operational reports (demographics for pastoral follow-up, service usage counts, food pantry/lunch ordering, vision center details) and includes an oil-change workflow that looks up oil/filter specs from a VIN using an API.
They discuss practical realities of agentic coding—fast progress and low cost (hundreds of dollars), but real deployment pain around dev vs production differences, PDF/email attachment issues, and secrets management—plus broader advice about embracing new technology as they did with AutoCAD decades earlier.
Key Takeaways
Start with a clear outline, then force the AI to ask questions.
John began with a Word document describing the workflow and explicitly instructed Claude to ask for missing details (“If you need more information… ask me the questions right away”), which produced more complete requirements and fewer gaps during building.
Get the full analysis with uListen AI
Using Claude as a product manager accelerates agentic coding success.
Claude generated an MVP roadmap, user stories, and non-functional requirements; those artifacts became the “source of truth” that Replit Agents could reliably implement.
Get the full analysis with uListen AI
Agentic tools can produce “enterprise-like” patterns from community needs.
The app includes multi-level admins, multi-church data separation, approvals for administrators, and reporting for ministry follow-up—capabilities that mirror multi-tenant SaaS design despite originating from a paper process.
Get the full analysis with uListen AI
Operational reporting is where the real value lands for events.
Beyond “a form,” the system outputs demographics lists for follow-up ministry, service-usage summaries, oil-change shopping lists, and food/vision center prep reports—reducing manual planning and errors.
Get the full analysis with uListen AI
The dev-to-prod gap is the biggest vibe-coding reality check.
John repeatedly hit issues where features worked in development but failed in production (PDF email attachments, environment variables/OpenAI key reuse), highlighting deployment, caching, and secrets-management as key pitfalls.
Get the full analysis with uListen AI
Treat the agent like a collaborator—but be ready to intervene.
John watches the agent work, tests when it claims it’s done, and uses simple control prompts (“Wait,” “Stop”) when it goes down a “rabbit trail,” then iterates with feedback.
Get the full analysis with uListen AI
Cost/time economics can be dramatically different with agents.
They report building major functionality in days and spending a few hundred dollars (with Claude free tier and Replit usage), compared to an estimate of months for traditional development—while acknowledging polish and reliability still take time.
Get the full analysis with uListen AI
Notable Quotes
“We started at 10:00 and finished about 3 o'clock in the morning.”
— John Blackman
“I just took and copied what Claude had put together and put it into Replit… and then it started going bloo-whoop, and there it was.”
— John Blackman
“Sometimes he goes off on a rabbit trail, and I have to bring him back.”
— John Blackman
“It always doesn't work in production what works in development, and that was very frustrating.”
— John Blackman
“It's just like AutoCAD… A lot of my friends didn't want to learn AutoCAD… I was still having fun.”
— John Blackman
Questions Answered in This Episode
Can you share the exact initial prompt + Word-doc structure you gave Claude that produced the roadmap and user stories (what sections mattered most)?
John Blackman, a 91-year-old church volunteer, describes turning a manual paper-based “impact weekend” registration process into a full web app by using Claude to generate a roadmap, user stories, and requirements, then feeding that into Replit Agents to implement the system.
Get the full analysis with uListen AI
How did you decide the boundaries between “system admin” and “local church admin,” and what mistakes did you make designing role permissions early on?
The app supports multiple churches and events with role-based admin levels, participant registration via QR codes, service toggles, waivers and signature capture, and printable “impact passports” (PDFs) that attendees can bring to the event.
Get the full analysis with uListen AI
What did Replit choose for the database/auth stack under the hood, and what would you change now that you’ve seen how it behaves in production?
It also generates operational reports (demographics for pastoral follow-up, service usage counts, food pantry/lunch ordering, vision center details) and includes an oil-change workflow that looks up oil/filter specs from a VIN using an API.
Get the full analysis with uListen AI
For the VIN → oil/filter lookup: what is the precise flow and why use the OpenAI API there instead of a dedicated VIN decoder service (accuracy, cost, reliability)?
They discuss practical realities of agentic coding—fast progress and low cost (hundreds of dollars), but real deployment pain around dev vs production differences, PDF/email attachment issues, and secrets management—plus broader advice about embracing new technology as they did with AutoCAD decades earlier.
Get the full analysis with uListen AI
What was the root cause of the PDF attachment failing in production, and what exactly changed about the PDF format between dev and prod?
Get the full analysis with uListen AI
Transcript Preview
We do impact weekends at our church. We go to a local church and provide free haircuts, free eyeglasses, free car wash, free food, and everything. I handle registrations for these events, and so I said, "It'd be nice to have that in the computer somehow." So I wrote up a kind of an outline of what I wanted to do. We sent it to Claude.ai, told Claude we want it for Replit. Then we had him write a program, and we sent it to Replit then to do the program.
If you all told me the story correctly, John, you and your other grandson did this into the wee hours of the night.
We started at 10:00 and finished about 3 o'clock in the morning.
It's beautiful. You've got beautiful [chuckles] navigation. It's easy to read. It's simple to navigate.
So I have control of all the churches, and here I see all the participants that have registered. I have the services that are available. I have reports, and I can print this report out beforehand to know what people are coming.
Do you have any wisdom or advice for us, as folks in our professional careers are facing this technology change?
It's just like AutoCAD. A lot of my friends didn't want to learn AutoCAD, and so when I retired in '94, I still was working in 2018. I was still having fun.
So that's another reason to learn this technology, because if you learn it, you can be having fun well into your 70s, 80s, and 90s. [upbeat music] Welcome back to How I AI. I'm Claire Vo, product leader and AI obsessive, here on a mission to help you build better with these new tools. I'm just gonna get to the punchline. Today, we have John Blackman, a 91-year-old vibe coding grandpa. He used Claude and Replit to build a very complicated, very impressive app for his church, and he's gonna show us how he did it. Let's get to it. This episode is brought to you by WorkOS. AI has already changed how we work. Tools are helping teams write better code, analyze customer data, and even handle support tickets automatically. But there's a catch: these tools only work well when they have deep access to company systems. Your copilot needs to see your entire code base. Your chatbot needs to search across internal docs, and for enterprise buyers, that raises serious security concerns. That's why these apps face intense IT scrutiny from day one. To pass, they need secure authentication, access controls, audit logs, the whole suite of enterprise features. Building all that from scratch, it's a massive lift. That's where WorkOS comes in. WorkOS gives you drop-in APIs for enterprise features, so your app can become enterprise ready and scale up market faster. Think of it like Stripe for enterprise features. OpenAI, Perplexity, and Cursor are already using WorkOS to move faster and meet enterprise demands. Join them and hundreds of other industry leaders at workos.com. Start building today. So I don't usually start this podcast with bios, but, John, yours is too good to not give a little time to.
Install uListen to search the full transcript and get AI-powered insights
Get Full TranscriptGet more from every podcast
AI summaries, searchable transcripts, and fact-checking. Free forever.
Add to Chrome