How I AI: How a 91-Year-Old Vibe-Coded a Complex Church App with Claude and Replit

I have to say, today's episode features one of the most inspiring stories I’ve had the chance to share. I sat down with John Blackman, a 91-year-old retired electrical engineer, and his grandson Brandon. John is the definition of a lifelong learner; from being the first in his department to learn AutoCAD in the 1980s to helping launch Google Fiber, he's always been on the cutting edge. And now? He's vibe-coding.

At 91, John saw a problem in his community and decided to solve it with technology. He single-handedly built a complex, multi-functional application for his church's community outreach events. He went from managing registrations with pen and paper to a full digital platform with different admin levels, real-time reporting, and even third-party API integrations. The most incredible part is that he had never written code like this before.

In this post, I'll break down the exact two-part workflow John used to bring his idea to life. First, we’ll look at how he used Claude as his product manager, turning a simple concept into a detailed development blueprint with user stories and technical requirements. Then, we’ll see how he handed that blueprint to a Replit agent and worked with it to build, iterate, and deploy the entire application. John's story really shows how AI can empower anyone, at any age, to become a builder.

Workflow 1: From Idea to Blueprint with Claude

Every great application starts with a clear plan. John’s project began with a need to streamline the registration process for his church’s “Impact Weekends,” which are community events that provide free services like haircuts, food, and even oil changes. The existing process was completely manual and paper-based. John knew there had to be a better way, which is when he turned to Claude.

Step 1: Defining the Vision and Requirements

Instead of just asking Claude to build an app, John started by treating it like a project manager. He began with a general query about creating a development roadmap. He had already typed up his ideas in a Word document, outlining the entire user journey. This included:

• Participant Registration: What data to collect from attendees.
• Service Selection: A list of available services like haircuts, dental care, etc.
• The 'Impact Passport': A concept he’d seen at another church, where participants get a printed schedule of the services they signed up for, which he wanted to digitize.

He fed this detailed document to Claude, essentially giving it a product brief. He was clear about his goals, even specifying that the application should be built on Replit, a platform his grandson, Brett, had recommended.

Step 2: Generating User Stories and a Development Plan

Claude was especially helpful here, acting as a real product partner. Based on John's input, the AI didn't just give him code; it gave him structure. It generated a complete set of professional-grade product artifacts:

• User Stories: Claude broke down the needs of different users. It created stories not just for participants and administrators, but also for specific roles like the pastor or ministry leader. For example: "As a system admin, I want to be able to see all data across all churches, but as a local church admin, I only want to see data for my own church."
• Multi-Tenant Architecture: The chat outlined a sophisticated system with role-based access control. It defined a system admin who could oversee all church events, and local admins who could only manage their specific event.
• MVP and Phased Rollout: Claude proposed a minimum viable product (MVP) with core features like an admin interface, passport generation, and data management, followed by a phased development plan.
• Non-Functional Requirements: John even got Claude to outline requirements like security and data privacy, showing a level of detail you'd expect from a professional product manager.

John said the user stories were remarkably accurate right from the start. He made a few tweaks, but Claude had successfully translated his vision into a clear, actionable blueprint that was ready for development.

Workflow 2: Vibe-Coding the Application with Replit

With a solid plan from Claude, John was ready to build. But instead of hiring a developer, he turned to another AI tool: the Replit agent. This workflow is a great example of the new style of AI-assisted development, where a person provides the direction and the AI handles the complex coding.

Step 1: Kicking off the Build

The handoff was surprisingly simple. John explained, "I just took and copied what Claude had put together. And put it in the Replit, and then started going and there it was." He pasted the entire requirements document and user stories into the Replit agent's chat, and the agent immediately started building. It generated the file structure, set up the database schema, and began writing the code for both the frontend and backend. John described watching it work in amazement: "It was so fast, I couldn't believe it."

Step 2: Building Complex, Multi-Tenant Features

The final application is much more than a simple form. It's a full-featured platform with some serious functionality, all built through conversation with the Replit agent.

Here’s a tour of what John built:

• Admin Dashboard: A secure login for system admins and local church admins. The system admin has a global view of all events and participants, while local admins are restricted to their own church's data.
• Event and Service Management: Admins can create events and toggle services on or off. If a service like "free haircuts" isn't available for a specific event, it can be easily disabled.
• Reporting Suite: John built several automated reports that can be exported to Excel. These include a demographics report for pastor follow-up, a service usage report to track popular services, and specialized shopping lists for the food pantry.
• VIN Lookup for Oil Changes: This is a pretty clever feature. When a participant signs up for a free oil change, the form asks for their car's Vehicle Identification Number (VIN). The application then hits the OpenAI API to look up the exact type and amount of oil and the correct filter needed for that specific car. This generates a precise shopping list for the event volunteers.
• Participant Registration & Passport: Participants can scan a QR code on a flyer, which takes them to a mobile-friendly registration form. After signing waivers with a digital signature feature (watch out, DocuSign!), the system generates a personalized "Impact Passport" PDF that is emailed to them using SendGrid.

Step 3: Iterating and Adding New Features

John didn’t stop with the initial build. He continuously adds new features by describing them to the Replit agent. For instance, he wanted to replace handwritten staff name tags with professionally printed ones. He prompted the agent:

I want to add a function that will populate a volunteer list when a local administrator fills an input page.

He watched as the agent added a new 'volunteer' table to the database, updated the application schema, and built the new interface. This process involves a feedback loop. John monitors the agent's work and steps in when he needs to. He's learned when to say "Wait" or "Stop" if the agent is going down a "rabbit trail."

This iterative cycle of prompting, observing, testing, and providing feedback is the heart of vibe-coding. It's a collaboration where John provides the what and the why, and the AI provides the how.

A New Era of Building

John’s story is a great example of what's now possible. For about $350 and a few weeks of late-night coding sessions (from 10 PM to 3 AM, a true developer's schedule), he built an application that he estimates would have taken a traditional team six months. He didn't need to know TypeScript or how to manage a database; he just needed a clear vision and the willingness to learn and collaborate with his AI partner.

His advice for others facing new technology is simple but meaningful. He compares AI to the rise of AutoCAD in the 80s. Many of his colleagues were resistant to learning it, but by embracing it, John extended his career and continued having fun well into retirement. "That's another reason to learn this technology," he says. "Because if you learn it, you can be having fun well into your seventies, eighties, and nineties."

John's story is about more than building an app; it's about empowerment. It's about taking an idea and, with the help of new tools, turning it into something real that has a positive impact on your community. I hope this inspires you to think about the problems you can solve. You might be surprised to find that you, too, can be a builder.

Thanks to our Sponsors

A huge thank you to our sponsors for making this episode possible:

• WorkOS—Make your app Enterprise Ready today
• Orkes—The enterprise platform for reliable applications and agentic workflows

Episode & Guest Links

• Watch the full interview on YouTube
• Listen on Spotify or Apple Podcasts