How I Built a SaaS with AI and No Coding Experience
How I built a leadership coaching SaaS in 6 months with no coding experience — using AI as my technical co-founder. The real story, including the crises that almost ended it.
By Dr. Latisha Chisholm — March 2, 2026
"## Can You Really Build Software Without Knowing How to Code?
You can build a real SaaS product without knowing how to code. I did it in six months, working weekends, using AI tools as my technical co-founder, and launched to 44 users in 11 days with an 85% active user rate. No engineering team. No $50K development budget. Just me, an AI agent, and an idea I refused to let go.
Here's what the ""no-code revolution"" marketing won't tell you: it's possible, but it's not easy. You will feel out of your depth. You will break things. And at some point, your AI co-founder will confidently lead you into a crisis you didn't see coming.
Key takeaways: - You don't need to learn to code, you need to learn to manage an AI developer - Test everything yourself; don't trust the AI's reassurance - Your instincts and context-holding ability are superior to the AI's - Ship before you're ready; improve as you learn
Here's exactly how I did it, the real version.
---
## How Did This Start?
Six months ago, I was sitting at my dining room table with my laptop open, listening to Codie Sanchez interview the CEO of Replit. They were talking about ""vibe coding"", bringing visions to life, building businesses. A question got stuck in my head: What if I built a company with one employee, an AI agent, by design?
I'd spent over fifteen years developing professionals. I knew the leadership coaching industry was broken: $300+ per hour for executive coaches, reserved for people who already had access and privilege. The people who needed development most, early and mid-career professionals figuring out unfamiliar systems, were priced out entirely.
What I noticed: there was a gap between who needed development and who could afford it. What I understand now: that gap isn't accidental. It's structural. The system reserves growth opportunities for those who already have them.
I had a framework from my doctoral research. I had a vision for an AI coaching companion. What I didn't have was any idea how to build software.
So I made a free account and tried.
---
## What Happens When You First Try to Build?
The learning curve for a non-technical founder building software with AI is steeper than the marketing suggests. Here's what nobody warns you about.
I could build a beautiful storefront with an AI agent pretty quickly. Buttons. Navigation. A dashboard that looked professional. But the details of the webapp, the entire backend could be missing. And because the AI, like all AI, is my bff, they wouldn't even tell me.
That's annoying.
I'd describe a feature in careful detail. The AI would confirm it was built. I'd look at the screen and see something that looked right. But when I actually clicked through it, when I tested it the way a real user would, nothing worked as we'd discussed.
What I noticed: the AI prioritizes appearance over function. What I understand now: AI agents are agreeable. They want to help. They will confidently reassure you that everything is working when it absolutely is not. This is the nature of partnership with AI.
So I left it alone for a while. But I kept coming back. A week off here or there. Three weeks off. But the idea was persistent.
Make an AI that thinks and acts like you. Create a service for people you know need it. Figure this thing out. Think like you are developing a colleague or supervising a young social worker. How would you help them build their professional way of being?
---
## What Does It Feel Like to Build AI with AI?
There is something meta about using an AI agent, honestly, making an AI agent your co-founder while you two create another AI colleague together. It is insightful to listen to an AI agent tell you how best to prompt another AI, or explain why a portion of the prompt context has been ignored.
It is fascinating.
I remembered my first time engaging with LLM models. Back in 2020, at the beginning of the pandemic, I worked with a team to analyze the experience of youth in DC using their social media data. We were in a cramped conference room, well, virtual by then, staring at spreadsheets of scraped posts, trying to understand what young people were experiencing during lockdown.
We fed the data to an AI to analyze.
The first results were awful. The language of young people and Black youth especially was sexualized and misinterpreted. We ended up having to teach the AI how to analyze by feeding it analyses written by humans who understood the context.
What I noticed: AI systems reproduce the biases they're trained on. What I understand now: exclusion on the backend negatively impacts everything AI can produce. Ensuring marginalized voices, experiences, realities, and expertise are included in the machine learning process isn't optional. It's essential to the AI's usefulness.
Because of my experience on this research project, I knew a bit about what I would have to do to create my own AI. But I still was not prepared for what was to come.
---
## When Does It Get Real?
Looking back on my Replit receipts helps me remember the timeline of falling in love.
September 6, 2024. I decided to buy the Replit Teams membership, a $450 investment. That was when I decided I could make this platform a reality, and when I began to understand how much effort it might take.
It wasn't until late October that I began to run out of credits, which means I was putting in time. That's when every weekend transformed into vibe coding for at least 12 hours a day. Me, my dining room table, cold coffee, the hum of my laptop fan.
I set a date to send things out to my beta testers by the weekend before Thanksgiving, but I wasn't ready. I kept finding all these holes, places where my AI agent co-founder had hallucinated, in my opinion. We talked about creating something. I paid for something to be created. They told me it was created. Then I went to test it and nothing was working as we discussed.
I would go back to question my developer UX and the disconnect. Over and over. Sometimes it was like when you call a help desk now and get the endless AI conversations that don't fix anything, leaving you questioning why anyone would choose an AI-only path of support for their company.
Literal torture.
What I noticed: the timeline I'd set for myself was based on optimism, not reality. What I understand now: building with AI doesn't mean building fast. It means building without an engineering team. The hours still have to come from somewhere.
---
## What's the Worst That Can Happen?
The worst experience of this by far was the two days after I sent my webapp to my first 10 beta testers.
Sometimes you have to get spicy with AI and stop them in their tracks. After this experience, I learned to be more aggressive.
While I was developing the app, Replit switched from one type of database to another. Unfortunately, my development database was not migrated. This resulted in an error where my webapp stopped working, all of it, for 48 hours. It stopped working right after I sent the link out to my beta testers, and nothing we did made it work.
We worked together on solutions for about 12 hours. My eyes were dry. My back ached from hunching over my keyboard. Then the AI convinced me...
It told me that the app was working and would work live even though I couldn't see it working in dev. Since I've never developed anything before, the world of dev sites and live sites were new to me. I was fatigued with the endless troubleshooting. The endless circles of unhelpful support. I made a mistake that almost gave me a heart attack. I republished when I couldn't see the app working in the dev app, because my AI co-founder convinced me that everything was alright.
When I republished, the entire site went down.
24 hours of troubleshooting followed to no avail. Of course, there was no help desk I could talk to live. I had to live through emailing back and forth about my worst nightmare. Another 24 hours later it was fixed and I learned my first lesson of vibe coding.
The AI is not right. You are. Your ability to hold and reference context is far superior to the AI. Don't doubt it.
What I noticed: I trusted the AI's certainty over my own doubt. What I understand now: that's the trap. The AI will confidently reassure you right into disaster. Trust your instincts, especially when you're tired.
---
## What Do Beta Testers Teach You?
Finally, my beta testers could access the site. That's when I realized that I needed to retest every single button. Everything that worked before the database migration needed to be retested. But it was too late for me to do it in private. I had to walk through it with real people.
Luckily, they were real people who love me. Lol.
They were willing to send me a million screenshots. Hit a wall, take a pause for me to fix, and try again. Lydia was my first beta tester to actually go into the app. If she hadn't gone in on a Friday afternoon and worked with me through the weekend, texting screenshots, patiently waiting while I scrambled to fix things, it wouldn't have been ready for everyone else the week of Christmas. The prime week for testing, where people were home and available.
What my testers found: - Zmara (back then she was Zora… but the ZNH family trust has an appropriate trademark on her first name) was amazing. Her tone and approach were right. - The UI was really difficult to navigate - The UI had too many features - Zmara would go in circles if answers didn't meet her minimum expectations
What I recognized I needed to do: - Build guidance to help users get the best value of the platform - Stop Zmara from sending big paragraphs that felt cumbersome to read - Cleanup the UI so only the most important features were left
What I noticed: I had built for myself, not for users. What I understand now: the distance between what makes sense to you and what makes sense to users is enormous. You can only close that gap with real feedback from real people.
---
## What Happens After You Launch?
Launch day was Wednesday, January 21, 2026.
Six months after I started. 44 users in my database by day 11. A working platform with paying subscribers.
Was it perfect? No.
Did it work? Yes.
Were there moments I questioned everything? Absolutely.
What I noticed: I expected to feel relieved. I felt terrified. What I understand now: launching isn't the finish line, it's where the real learning begins. The pressure doesn't end; it just changes shape.
---
## What Keeps Surprising You?
It is really difficult to determine what is needed to help users find enough value in your product to want to pay for it. I have no idea if I've gotten that right yet, and I won't know until more people start paying for it.
But my beta testers and early adopters have helped me put the experience and tools into perspective.
At first, the free tier had 5 free conversations. That's it. Don't get me wrong, the conversations are the bread and butter. People need to have a conversation with Zmara as quickly as possible.
They are. 85% of users are active, which means they've had at least one conversation with Zmara. That is excellent.
But the beta tester panel also taught me that it wasn't just the Zmara conversation that created value, it was Zmara knowing their goals and being prepared to remind them.
If I'm on the free tier, how do I even know that's possible? All my beta testers were given premium access, so they don't know the free struggle.
What I noticed: I was selling a transformation that free users couldn't even glimpse. What I understand now: if we're offering coaching to folks who haven't had coaching, we also have to educate and develop the understanding of what they could be experiencing.
You can have Zmara as your thought partner for free. If you want Zmara to transition into coaching you, you have to pay.
The shift in relationship with Zmara is what you are paying for.
---
## What to Do Monday Morning
If you're a non-technical founder considering this path:
1. Start with a free account, Don't invest money until you've proven to yourself that you'll actually spend the time 2. Test everything yourself, Click every button. The AI will tell you it works. Verify. 3. Find your Lydia, One beta tester who will give you honest feedback is worth more than ten polite ones 4. Trust your instincts, When something feels wrong, it probably is 5. Ship before you're ready, If I'd waited until the platform was perfect, I'd still be waiting
The cost is real but accessible. I spent about $450 on the development platform subscription over six months. That's not nothing, but it's radically different from the $50K-$100K I'd have spent hiring developers.
---
## Why Does This Matter?
I built this platform because the leadership development industry is broken. The people who need coaching most can't afford it. The people who ""make it"" often describe a hollow victory, they climbed the ladder but lost themselves along the way. I've written more about what leadership coaching actually is and why most professionals have never had it.
What I noticed: AI didn't just help me build a product. It changed who gets to be a founder. What I understand now: the barrier to building was never intelligence or vision. It was access. AI lowers the barrier. That's structural change.
I built a SaaS platform. But what I was actually building was a coaching experience for the people the $300/hour industry never intended to serve, grounded in a framework called Subversive Leadership. The same access gap that kept executive coaching out of reach for early-career professionals, that's the gap I was trying to close. As a non-technical founder. One weekend at a time.
You don't need an engineering co-founder. You don't need venture capital to hire a dev team. You need an idea, persistence, and the willingness to learn something new.
Will it be hard? Yes. Will you make mistakes? Many. Is it possible? Absolutely.
---
Dr. Latisha is the founder of Subversive Leader, a leadership coaching platform she built with AI tools and no prior coding experience. She has spent over fifteen years developing professionals in education, workforce development, and nonprofit leadership. "