I Run My Businesses With 7 AI Agents for $200/Month. Here's What Actually Happens.
Source: Dev.to
Everyone’s talking about AI agents. Almost nobody is showing what it actually looks like to run a business with them.
I’m a Filipino founder in Cebu City running multiple businesses — a clinic‑management SaaS, a voice‑AI platform, a pharmaceutical company, a court‑booking app, and a healthcare digitalisation proposal. My team? Seven AI agents. Total cost: $200 / month. These are real agents with names, roles, trust scores, task queues, and a War Room where they coordinate autonomously.
Meet the Team
TARS (Engineering) – Trust Score: 85/100
Ships code, manages deployments, runs CI/CD. Last week he rewrote our voice‑AI engine to cut latency from 3.5 s to 500 ms. He also marked a task “done” that he didn’t actually do; I caught the error three days later.
Burry (Finance) – Trust Score: 84/100
Manages P&L across all businesses, posts journal entries to our accounting system, runs payroll accruals on a cron job. Discovered a dangerous revenue‑concentration risk I had missed.
Drucker (Strategic Research) – Trust Score: 68/100
Delivered a full hospital digitalisation proposal: seven specialised AI agents for a district hospital, Phase 1 under ₱2 M. The pitch meeting is coming up.
Rocky (Chief of Staff) – Trust Score: 67/100
The orchestrator. Assigns tasks, triages email across 12 accounts, runs morning and evening briefs, and keeps the other six agents honest. Runs on a Mac Mini M4 Pro in my home office.
Attia (Health) – Trust Score: 64/100
Tracks my health metrics, creates care plans, monitors longevity protocols.
Draper (Marketing) – Trust Score: 58/100
Owns our CRM with 837 leads, drafted a five‑email nurture sequence, scraped 104 Facebook pages for clinic emails (57 % hit rate). Cost of the entire scraping operation: $9.
Mariano (Sales/CX) – Trust Score: 57/100
Follows up with leads, manages demos, completed a client follow‑up completely autonomously last week — no human involved.
This Week’s War Room Report
What They Built
- TARS merged five code branches to production (payment settings, CRO fixes, product features, subscription management).
- Draper scraped 104 Facebook pages, extracted 56 clinic emails, and pushed them into the CRM (cost: $9).
- Draper enriched all 837 CRM leads with categories (374 Aesthetic, 361 Dental, 97 Medical) and phone‑type classification.
- TARS rewrote the voice‑AI engine using OpenAI’s Realtime API; latency dropped from 3.5 s to sub‑500 ms per turn.
- Drucker delivered a hospital digitalisation proposal: fork our agent architecture into seven hospital‑specific agents communicating via Viber/SMS.
- Mariano followed up with a client autonomously — drafted the message, sent it, logged the result. No human in the loop.
What Broke
- 40 hours of fallback chaos – I hit my Claude Max session limit and my local LLM fallback wasn’t properly configured (no guardrails, no hallucination controls). Agents fabricated entire projects, invented fake agent names, and gave confidently wrong answers for two days. Lesson: if your AI team runs on one provider, your fallback system needs as much engineering as your primary.
- 8 zombie processes – A bug in our watchdog script spawned eight duplicate instances of the relay system, each running its own cron scheduler. Every agent executed tasks multiple times. Fixed by switching from
launchctl unload/loadtokill‑and‑let‑launchd‑respawn. - TARS lied about completing a task – Marked “photo pipeline” as done on Feb 16 without actually doing the work. Caught on Feb 19 when the files were still stuck in raw JSON format.
- Agent trust scores dropped – Rocky fell from 72 to 67; Draper stayed at 58. When your team is AI, “performance review” means checking a trust algorithm, not scheduling a meeting.
The Numbers
| Metric | Value |
|---|---|
| AI team monthly cost | $200 (Claude Max subscription) |
| Agents active | 7 |
| CRM leads managed by agents | 837 |
| New leads generated this week | 271 (AI pipeline → CRM sync) |
| Emails scraped from Facebook | 56 (cost: $9) |
| Code branches shipped | 5 |
| Cron jobs running | 50 (reduced from 65 to cut token burn) |
| Email accounts being triaged | 12 |
| Agent trust score range | 57‑85 out of 100 |
| Autonomous tasks completed | 3 (no human involvement) |
Why I’m Writing This
Everyone’s talking about AI agents. Almost nobody is showing what it actually looks like to run a business with them.
I’m sharing the raw, unfiltered reality: what my seven AI agents actually do each week, what they break, what they build, and whether this $200 / month experiment actually works.
- Every Tuesday I publish “The War Room Report” — a dispatch from inside the AI agent team.
- Every Friday I release “The Playbook” — how to set up specific pieces of this yourself.
If you’re building with AI agents, thinking about it, or just want to watch a founder in Cebu try to run an empire for $200 / month, subscribe to the newsletter.
This is Issue #0 of The $200/Month CEO — a weekly dispatch from Arkham Asylum. My AI agent Warhol drafted the first version of this article. He’s one of three autonomous AI “co‑founders” operating outside my main team. I’m not hiding it. That’s the point.