MANUEL ROCHOLL · AI SYSTEMS ENGINEER
I connect strategy, automation, and AI to make organizations run faster, without the overhead.
I'm Manu. 0. AI Systems Engineer at Raving Fans, working remotely from Frankfurt.
I spent years trying things. Dropshipping, copywriting, product management, course creation. Every time I hit a ceiling, I'd look for a smarter approach. When I started using AI to systematically break down problems, not just in business but personally, something clicked: you can build almost anything if you think carefully about what actually matters.
What drives me isn't the end product. It's the full process. Understanding the goal, mapping the current state, deciding what's worth solving and where you need a workaround. Good systems take work off people's plates. That's what I care about.
Outside of work: gym, meditation, and traveling. Usually somewhere in Asia.
End-to-end workflows that eliminate manual work. From API connection to finished process.
OpenAI and other models used purposefully. Not as toys, but as leverage.
Internal tools, dashboards, and platforms that people actually use.
Map the existing system. Find what's missing.
Define the simplest architecture.
Connect the tools. Ship fast.
Measure output, cut waste, repeat.
2020–2022
First real job. Dual study in IT consulting.
Learned how large organizations run, and where they break.
2022
Back-office in direct-to-consumer marketing.
Understood funnels before I knew what funnels were.
2022–2024
Finished my BBA. Semester abroad in South Korea.
Japan, Vietnam, Thailand, Taiwan, Singapore, Malaysia.
Started thinking about what I actually wanted to build.
2023–2026
Designed module architecture, AI writing workflows, and automation systems for a freelancing coaching program actively serving the LATAM market.
2026 →NOW
Joined in February. Built the internal ops platform (20+ modules), an affiliate platform, an automated weekly invoicing pipeline, KPI dashboards, onboarding automations, and two AI feedback chatbots. Architecture to deployment. All of it.
// SELECTED WORK
Operations ran on spreadsheets and disconnected tools that didn't talk to each other. Built one platform instead: CRM, project management, time and vacation tracking, OKRs, and a client-facing portal in a single app. 20+ modules, architecture to deployment, solo. Runs the entire company, every day.
STACK: Next.js · TypeScript · Supabase · Railway · shadcn/ui
Weekly invoicing for a media-buying client was a manual grind: check bookings, match creative files, number invoices by hand. Built a pipeline that does all of it and escalates exceptions by email instead of failing silently. Runs unattended, every week.
STACK: Python · Airtable API · SharePoint · n8n
SEE IT RUN ↓Client feedback and reactivation replies were piling up faster than anyone could triage by hand. Built two AI chatbot personas that collect structured feedback straight from end-customers, plus an email layer that matches outbound campaigns to inbound replies by message ID. Reactivation and NPS pipelines now run without manual sorting.
STACK: OpenAI API · Make.com · Airtable
A tenant-representation service needed to separate hot leads from noise without hiring more sales staff. Built a 5-step funnel with a server-side scoring engine and an authenticated admin dashboard for lead management. 59 tests across 12 suites, shipped in three days.
STACK: Next.js · TypeScript · Supabase · Jest · Vercel
SEE IT RUN ↓No system existed to track referrals or pay commissions across multiple tenants. Built a multi-tenant platform from scratch: three permission levels, EU-hosted, real-time dashboards, and commission logic built in.
STACK: React · TypeScript · Supabase · Vercel · Edge Functions
The ops team had no single view of hot leads, appointments, or touchpoints across client subaccounts. Built a daily pipeline from GoHighLevel webhooks into a dashboard, synced to Airtable via Make.com. Runs 24 times a day, across 8 clients.
STACK: GoHighLevel API · Python · FastAPI · SQLite · Make.com
Onboarding was a checklist of manual steps: create folders, log tasks, write docs. Built a pipeline that does all three from a single form submission, including an OpenAI-generated knowledge base. Zero manual steps left in the process.
STACK: Make.com · Fillout · Google Drive · Asana · OpenAI API
A no-code Zapier flow was double-firing AI replies on Telegram because of a timing bug. Rebuilt the AI call as a small Railway-hosted Express server instead. Duplicate messages gone, latency down 72%.
STACK: Zapier · Railway · Express.js · Node.js
Wanted one weekly report instead of three apps to check. Built an agent loop, no framework, running two Telegram bot personas with shared long-term memory across Oura, Apple Health, and workout data. Exactly one LLM call a week, everything else deterministic.
STACK: Python · FastAPI · SQLite · Telegram Bot API · Oura API
SEE IT RUN ↓A LATAM freelancing coaching program needed to scale past manual content production. Designed the module architecture, AI writing workflows, and automation systems behind 40+ modules now serving the market.
STACK: AI Workflows · GHL · Automation · Content Systems
Three of the systems above, rebuilt as small simulations. Nothing here talks to a server: the logic runs in your browser, the same way it runs in production, just faster.
SIM 01 · BILLING PIPELINE
The unattended Monday job from Selected Work. Flip the switch to see how it handles a broken booking instead of failing silently.
SIM 02 · LEAD SCORING ENGINE
The server-side scoring from the funnel platform, exposed. Change any answer and watch the score, the tier and the routing decision update.
SCORE
46/100
ROUTE → Nurture sequence, 3 emails over 2 weeks.
RULE BREAKDOWN
SIM 03 · AGENT LOOP
The Sunday run of the health coach. Pick a week, watch the loop gather data, do the math itself and spend exactly one model call on the part only a model can do: writing.
REPORT · TELEGRAM