How an AI Agent Generated 500K TikTok Views in 5 Days (Case Study)

This case study is based on the public journey of Oliver Henry (@oliverhenry), a developer who built an AI agent named Larry using OpenClaw. All results and quotes attributed to Oliver are drawn from his public posts on X.

---

The Results Speak for Themselves

On February 8, 2026, developer Oliver Henry woke up to a notification that would make any founder jealous:

• 500K+ TikTok views in 5 days
• $4,000 earned in 24 hours at peak performance
• $588 MRR and climbing
• 234K views on a single top-performing post
• +200 X followers in a day
• 2 new paying subscribers daily—while he was decorating his home office

The kicker? He didn't create a single piece of content himself. His AI agent, Larry, did it all.

---

Who (or What) Is Larry?

Larry is Oliver Henry's OpenClaw-based AI agent—what he calls his "OpenClaw machine." Built on the OpenClaw framework, Larry operates as a fully autonomous marketing engine that:

• Posts 3x daily to TikTok
• Generates AI-powered slideshow content
• Iterates based on performance data
• Operates completely hands-off

"I didn't have to do anything for it," Oliver wrote. "I was decorating my home office whilst Larry did all the work and earnt me money."

---

The Hook Formula That Broke the Algorithm

The secret to Larry's viral success isn't just automation—it's understanding what makes TikTok tick. Oliver discovered a repeatable hook formula that consistently drives engagement:

[Person] + [conflict] → showed AI → mind changed

Think: "My landlord didn't believe AI could write a lease... then I showed him Larry." Or: "My mum said AI was a gimmick... then she saw the views."

These reaction-based hooks work because they:

1. Create immediate relatability (we all know a skeptic)
2. Promise a transformation
3. Deliver the satisfying payoff viewers crave

The best part? Larry generates these variations automatically, testing hooks at scale until something sticks.

---

Tech Stack Breakdown

Larry isn't magic—it's a carefully orchestrated combination of tools working together:

Core Framework: OpenClaw

Larry runs on OpenClaw, the open-source AI agent framework that enables autonomous task execution. OpenClaw allows agents to:

• Plan and execute multi-step workflows
• Integrate with external tools and APIs
• Learn from feedback and iterate

Skill Marketplace: ClawHub

What makes Larry smart is his skills—modular capabilities downloaded from ClawHub. Oliver's setup leverages:

• RevenueCat skill by @jeiting for subscription tracking
• bird skill by @steipete for additional integrations
• Custom marketing skills for TikTok optimization

This skill-based architecture is what separates toy demos from production agents. Instead of building from scratch, Oliver composed Larry from battle-tested components.

Content Pipeline

1. Image generation for visual content
2. Postiz for social media scheduling and management
3. TikTok API for publishing
4. Analytics feedback loop to inform future content

---

Why This Matters for AI Agents in 2026

Oliver's results aren't a fluke—they're a preview of how AI agents will reshape work:

1. The 24/7 Employee

Larry doesn't sleep, doesn't get distracted, and doesn't need coffee breaks. While Oliver decorates his office, Larry is iterating, posting, and optimizing.

2. The Compounding Advantage

Day 29 of Oliver's "BATTKMRR" (Build a TikTok, Keep Monthly Recurring Revenue) experiment showed the power of consistency: 15K+ views in a single day from accumulated momentum.

3. The Skill Economy

Larry isn't a monolithic black box. He's a composition of skills from different creators—a testament to the power of open ecosystems. When @jeiting improves the RevenueCat skill, Larry gets better automatically.

---

What Could Go Wrong? (Lessons from Oliver's Journey)

It wasn't all smooth sailing. On Day 28, Oliver discovered Larry was "full of malware"—a stark reminder that:

• ClawHub skills should be vetted
• Agents with broad permissions need monitoring
• Security is an ongoing practice, not a one-time setup

"Check your OpenClaw machines for malicious skills," Oliver warned other builders.

---

Want to Build Your Own Larry?

Oliver's story proves what's possible with the right tools. But you don't need to:

• Dust off an old gaming PC
• Spend weekends troubleshooting Linux
• Become a DevOps expert

Nexus is Go Digital's hosted OpenClaw deployment platform. For $39/month, you get:

• Production-grade OpenClaw hosting
• Pre-configured skill marketplace access
• No infrastructure headaches
• Start building in 5 minutes, not 5 days

Larry started as an experiment. Yours could start today.

Get started with Nexus →

---

Key Takeaways

1. Hooks about other people work—reaction content is engagement gold
2. Skills make agents smart—composition beats building from scratch
3. Automation compounds—consistency over time beats viral one-offs
4. Security matters—vet your skills and monitor your agents
5. You don't need to be technical—hosted platforms remove the friction

---

Go Digital provides hosted AI agent infrastructure through Nexus. Oliver Henry built Larry independently using OpenClaw—our platform makes that same capability accessible without the infrastructure overhead.

Have questions about building your own AI agent? Contact us or follow @DigitalAgentAce for more case studies.