Flirthaus
The founder walked away from a content agency. I walked in, automated every bottleneck with AI, and took it from bleeding money to $50K/month in sales — in 30 days.
// results
30 days
turnaround time
$50K/mo
in sales generated
0–2 hrs
weekly time spent
0 clients
lost during transition
// the-situation
The founder quit. Left behind 5 clients, a team of chatters, and zero documentation. Schedules lived in people's heads. Information was pinned in Discord channels nobody read. Managers spent their days looking things up instead of managing.
My first benchmark was survival: don't lose a single client in 30 days. Day 30 came. Zero churn. Green light.
// phase-1: fix operations
First thing: moved everyone from weekday/weekend schedules to an 8-day rotation. Two groups — A and B. Four days on, four days off. No random swaps. This standardized performance tracking — same hours, comparable output.
Discussions moved from Discord (where messages go to die) into the app with internal and creator-facing sharing. Right information, right person. Managers whose time got freed up started innovating — once people aren't drowning in grunt work, they actually start managing.
// 8-day rotation scheduling — standardized performance tracking
// the-hype-bot
With operations stable, Discord was freed up for the important things. Like an AI sales HYPE-BOT. It announces every sale in real-time — and the messages get louder the bigger the amount. Plus clock-in tracking that flags who didn't show up, which is more useful than tracking who did.
// gets louder with bigger amounts 🔥
// phase-2: make it data-centric
Nobody knew why numbers went up or down. Without data, it was all vibes. I built a shareable Streamlit app — cohort analysis, segment breakdowns, activity by day and hour. One client didn't realize that even though his traffic was decreasing, we were increasing the ROI on each segment. The data told the real story.
// cohort analysis — why did this week look different?
// blue line (traffic down) vs bars (revenue up) — data told the real story
// phase-3: automate the money
The old process: calculate sales per client, create PDF invoices, send to Telegram, follow up until they pay, calculate commissions, send payroll through Wise one at a time. 2-day process. Every week.
Started with N8N (it was a beautiful mess), then replaced it with a Python TUI that does the same job in seconds and stays idempotent. The bonus: it's a CLI, so AI agents can call any part of it. Clients ask for their invoice over Telegram? Agent runs the command, returns the PDF.
// from beautiful N8N mess to simple CLI — agents can call any part of it
// phase-4: content & growth
By now I had streamlined operations, made the business data-centric, automated invoicing and payroll, and built a hype bot. Time for growth. Remotion templates + OpenRouter generate marketing content, pushed to Telegram channels. The plan is an agent that builds trust in community channels, then drives traffic and schedules calls.
// Remotion templates + OpenRouter content generation
// phase-5: training the team
The final piece — balance the seesaw of clients ↔ sales team. A standardized training system with lessons and an automated chat simulator. "Think flight simulator, but for flirting. I wish I was joking." They practice with an AI, get reviewed on engagement quality, and learn to handle "pushy" fans before they go live.
// practice flirting with AI before going live — reviewed on engagement quality
// the-result
30 days to turn around a failing agency. Operations streamlined. Data-centric decision making. Automated invoicing and payroll. AI hype bot. Content pipeline. Training simulator.
From losing money → $50,000/month in sales. With invoice margins, that's $12K–$15K/month in revenue. Time spent: 0–2 hours per week.
Six-month target: $100K–$200K/month in sales. The only remaining bottleneck is me closing calls. Maybe one day an AI agent does that too.