AI Summary
5 min readOliver Henry shares how he built an AI agent named Larry using OpenClaw to automate TikTok marketing for his mobile app Snugly, generating hundreds of dollars in monthly recurring revenue (MRR) passively. Starting from a personal need to redesign his home with AI image generation, he turned frustration with manual marketing into a self-improving system that creates viral slideshows, analyzes performance, and optimizes conversions.
Building Snugly and Early Marketing Struggles
Henry created Snugly after using ChatGPT to generate consistent room redesign images for his house, locking down prompts to maintain room sizes and features. He published the app without much promotion but soon realized marketing was the bottleneck. Initial manual efforts—hook-and-demo face reaction videos and Canva slideshows—took hours and yielded modest views (e.g., 6,000 on one). SaaS tools for automation underperformed, prompting him to treat the problem like hiring a virtual assistant: automate TikTok slideshows entirely.
He installed OpenClaw and tasked Larry with one job—automate marketing—granting access to TikTok posting (as drafts), analytics, a Brave browser for research, and WhatsApp for communication. No multi-agent "mission control" was needed; Larry operates as a single employee, spinning up sub-agents for long tasks while retaining context.
Continue reading the full summary in the app — free to try.
Read Full Summary →Free • No credit card required
What you'll learn
- 1 `* (01:08) **Episode Goals: Automated MRR via OpenClaw Marketing**`
- 2 `* (02:35) **App Origin: Snugly Interior Design Tool**`
- 3 `* (05:58) **Launching Larry: OpenClaw as AI Employee**`
- 4 `* (08:26) **Early Iterations: Hooks, Images, and Posting Hacks**`
- 5 `* (11:27) **Optimizing CTA and Funnel Learning**`
- 6 `* (18:22) **Letting Larry Loose: Autonomous Scaling**`
- 7 `* (23:37) **Advanced Autonomy: Brainstorming and Onboarding**`
+ Full timestamped outline available in the app
Show Notes
I sit down with Oliver Henry, a full-time employee who is generating hundreds of dollars in monthly recurring revenue from mobile apps he barely touches, thanks to an AI marketing agent he built on OpenClaw called Larry. We walk through how Larry autonomously creates TikTok slideshow content, reads analytics, iterates on hooks and CTAs, and feeds performance data back into the content loop. Oliver also shares how he packaged the entire system as a free, downloadable skill on Larry Brain so anyone can replicate it. By the end of the episode, you will understand the full “Larry Loop”—from content creation to conversion optimization and why skills are poised to reshape how we think about SaaS altogether.
I'm hosting a free workshop so you can build your business in the age of AI.
Sign up here: https://startup-ideas-pod.link/build-with-ai-2026
Links Mentioned:
Larry Brain: https://startup-ideas-pod.link/Larry-brain
QMD Skill: https://startup-ideas-pod.link/qmd-skill
Timestamps
00:00 – Intro
01:25 – Background on Marketing IOS app with OpenClaw
06:43 – Larry’s first posts and iterating
03:55 – Posting Strategy and First viral hit: 137K views
12:01 – Communicating with Larry via WhatsApp
12:53 – Mission control vs. single-agent workflow
14:36 – The CTA problem: views without conversions
17:07 – The Larry Loop explained: analytics → content → metrics → iterate
18:15 – Boomers, engagement bait, and the algorithm boost
20:33 – The importance of iteration
23:36 – How Larry brainstorms and validates new hooks
27:57 – The power of OpenClaw
30:04 – The vision for Larry
31:49 – Model choices: Claude vs. OpenAI and over-optimization
34:38 – OpenClaw vs. cloud alternatives (Manus, Cowork)
37:39 – Getting started: Larry Brain onboarding and 80+ skills
40:13 – Ernesto Lopez: $70K MRR using the Larry Loop
41:27 – Doing all of this with a full-time job
42:28 – QMD Skill for cutting token usage and closing thoughts
More from this podcast