DEV Community: Shannon Long

After the Hack: OmniVeo Is Just Getting Started

Shannon Long — Sun, 06 Jul 2025 16:18:08 +0000

The Bolt.new hackathon may be over… but for us, it was just the beginning. What started as a last-minute solo project idea turned into a functioning, collaborative AI-powered tool that could reshape how people learn creative software. OmniVeo isn’t just an experiment anymore. It’s a real product, and we’re fully committed to bringing it to the world.

What’s Next

We’re now entering the next chapter: turning OmniVeo into a real business.
We’re working on:

-Validating with real users in creative fields—especially beginners and career switchers.

-Raising our first $10K in pre-seed funding to cover infrastructure and operating costs.

-Improving our RAG database and support across 12 creative tools.

-Testing pricing models based on usage and token-based AI limitations.

-Launching a limited-access beta for creators and learners worldwide.

We’ve already submitted for a few grants and are building a GoFundMe to help sustain the backend costs while we validate. Long-term, we aim to integrate with platforms like Fiverr, Gumroad, or even Adobe—to help creators not only learn but earn.

What I Learned

Before this, I had never led a dev team. I wasn’t even a developer. I’m a junk hauler who designs skateboard decks on Canva.
But this month changed me.

I learned how to:

• Scope and pitch a product from scratch

• Recruit international teammates and coordinate across time zones

• Handle real technical pipelines—from Gemini Vision to ElevenLabs, Supabase, n8n, and Bolt.new

•Deal with burnout, deadlines, pivots, crashes, and last-minute miracles

Most importantly, I learned to believe in my own ideas—even if I don’t have the full technical skill set. With the right team, the right platform, and the right problem, you can build something that matters.

The Real Win

We didn’t build OmniVeo just to compete. We built it because we needed it. I needed it.
And now, seeing it come to life, I realize the true value wasn’t in submitting with 8 minutes left. The real win is that we now have a shot at solving a real pain point for millions of people trying to learn powerful tools—and giving them a mentor that sees, understands, and adapts.
The hackathon gave us the push. Now it’s time to keep building.

OmniVeo: Built Across Timezones, Fueled by Grit

Shannon Long — Sun, 06 Jul 2025 16:07:16 +0000

When I saw the Bolt.new hackathon announcement, I was a full-time junk hauler, running my own art business on the side, and juggling being a husband and father—all while dreaming about building something that could actually change how people learn complex software.

I’m not a developer. Most of my design work is done in Canva, and I’ve never written code professionally. But one frustrating Photoshop session—where five YouTube tutorials couldn’t help me do a simple task—sparked the idea that led to OmniVeo.

The Idea That Ignited It All

OmniVeo started as Forge, a gamified platform for creators to learn, compete, and collaborate. But as the build progressed and complexity grew, we realized the heart of the product was the live AI mentor—a tutor that could see your screen, understand your context, and guide you step by step like a real expert sitting beside you.

That vision eventually became OmniVeo, from the Latin “to know” and “to see.”

Building a Global Team

On day 17 of the competition, I knew I needed help. I posted in the Bolt Discord—and within 24 hours, had a team:
• Swara (Backend, India)
• Maruf (Backend, Bangladesh)
• Tobi (UI/UX, Nigeria)

We were literally across four continents, five time zones, and all working around wildly different life schedules.

I was waking up at 5 a.m., working full shifts at my job with 1-800-Got-Junk?, coming home to spend time with my wife and kids, then staying up through the night to build. It wasn’t easy—there were nights I’d crash for an hour and be right back on a call before work.

One of the biggest lessons I learned was this: Don’t rely on Discord chat alone. If we had jumped on daily calls from the beginning, we would’ve stayed more aligned and avoided a lot of double work and late-game scrambling. That single shift would’ve saved us days of confusion and helped us finish earlier and more polished.

Teamwork That Pushed Boundaries

What we built technically was a challenge in itself—integrating Gemini Vision, ElevenLabs, and a real-time screenshot loop via n8n, all powered by a custom RAG database trained on complex creative software documentation.

But beyond the code, it was the resilience and team communication that pulled us through. Swara struggled for hours trying to merge backend workflows into the Bolt production project. Maruf eventually cracked the final integration—while I was literally on a junk-hauling shift. I saw the update in Discord, pulled out my laptop on break, tested it, and sure enough: it worked.

The agent could see my screen. It could answer context-aware questions. It was real.

The Final Sprint

We were still piecing things together hours before the deadline. My computer crashed mid-demo render. Our GitHub collab wasn’t working. We hacked together a shared Bolt account so each team member could push changes in shifts. I pulled an all-nighter while the team, in different time zones, did the same. We screen-shared, called, and built side-by-side—despite being across the globe.

We submitted with 8 minutes to spare.

Beyond the Code

We didn’t just build an app—we built trust. We built habits. We built a working relationship across four countries. And somehow, we pulled off something no one thought we could: a real-time, AI-powered mentor that can teach you Photoshop, Premiere, Maya, Ableton, and more—just by seeing your screen.

This experience taught me more than any course or job ever could. I now believe that with the right people and the right platform, even a junk hauler with no tech background can lead a team and ship a groundbreaking product in less than 30 days.

Shoutouts

•Huge thanks to the Bolt.new team for enabling non-technical builders like me to experiment freely.

•Shoutout to my teammate, @maruf_ahmed_52b289e12806c ,and Tobi and Swara

•Special thanks to the Discord community for support, encouragement, and advice during crunch time.

Built with: Bolt.new, ElevenLabs, Gemini Vision, Supabase, n8n, and caffeine. Developed from California, India, Bangladesh, and Nigeria.

Building with Bolt: From Skateboards to Screen-Aware AI Tutors

Shannon Long — Sun, 06 Jul 2025 15:54:43 +0000

This journey started a week before the hackathon, long before I knew I’d be leading a global dev team. I’m a junk hauler by trade, running my own deck art business on the side. I’m not a developer. I design with Canva and sell skateboards online. One day, a custom order pushed me to try something more advanced in Photoshop. Five YouTube tutorials later, I still couldn’t figure it out.

That frustration sparked a wild idea: What if AI could guide me inside the software itself?

I started tinkering in Replit, but when I saw the Bolt.new hackathon—offering access to cutting-edge tools like ElevenLabs and Gemini—I decided to go all in.

The original idea was called Forge: a gamified learning platform for creators, where users would earn XP for using an AI mentor (in “Forge Mode”) and compete in creative challenges judged by the community. Think: “Design a landscaping logo in Photoshop” or “Make a classical remix of a rap song in Pro Tools.” Players could win gold, unlock avatar skins, and eventually compete for paid opportunities.

But around Day 17, I hit a wall. I realized this was bigger than I could build alone. So I posted in the Bolt Discord and that’s when everything changed.

Within hours, I had a global team:
• Swara (Backend, India)
• Maruf (Backend, Bangladesh)
• Tobi (UI/UX, Nigeria)

We jumped into a group chat and immediately got to work. Our priority: making “Forge Mode” functional. The technical vision was ambitious:

Real-Time Screen Awareness: Every three seconds, a screenshot is taken from the user’s screen and sent through an n8n workflow.
Visual Analysis with Gemini: The screenshot goes to Gemini Vision, which interprets the screen and returns a structured JSON of what’s visible.
AI Tutoring via ElevenLabs: This JSON is passed to Percival, our ElevenLabs conversational agent, as context for answering the user’s question.
Software-Specific Knowledge via RAG: Percival uses a RAG database we created, containing in-depth docs and tutorials across 12 major creative tools, to provide expert-level answers tailored to the software in use.

The backend was like having Google Vision, ChatGPT, and a software mentor rolled into one.

Tobi and I worked on the frontend and UX while Swara and Maruf tackled backend pipelines. With 5 days left, time was slipping. Tobi suggested we drop the gamification and avatars to focus entirely on the AI tutor—the true MVP. We renamed the app OmniVeo, from the Latin “to know” and “to see.”

We ran into serious GitHub merge issues, so I created a shared Bolt.new account so everyone could contribute in turns. It wasn’t ideal, but it worked. With less than 12 hours remaining, we hopped on a late-night global call. I stayed up all night, screen-sharing with my team while preparing for my 7:30am job.

At 8am, while I was hauling junk in California, I got a message: It works.
Maruf had solved the final integration. I tested it live in Photoshop. The AI could see my screen, understand my context, and answer with precision using our RAG-powered system. It was working exactly as envisioned.

Swara had been facing issues merging the backend workflow into the production project on Bolt, but after hours of troubleshooting and team collaboration, everything finally aligned.

The final hours were chaos. Tobi was finalizing the UI. I was trying to finish a demo video during a lunch break. My computer crashed during the upload. We re-rendered and submitted with 8 minutes to spare.

It wasn’t perfect. But it was real. It worked. And we did something that’s never been done before. We created an AI tutor that can see your screen, understand your problem, and guide you through complex software in real time.

None of this would’ve been possible without Bolt.new. The platform gave a non-technical person like me the tools—and the global collaborators—to take a raw idea and turn it into a working product in under 30 days.

Now, we’re taking OmniVeo into production and working on making it scalable, affordable, and available to the world.