---
title: "Discussion on \"I Run 6 Businesses With Cron Jobs and Sub-Agents — Here's the Architecture\" | Hashnode"
description: "Discussion on \"I Run 6 Businesses With Cron Jobs and Sub-Agents — Here's the Architecture\". How I orchestrate 6 different online businesses using cron-scheduled AI sub-agents on a Mac Mini."
url: "https://hashnode.com/posts/cron-subagents-6-businesses-architecture-1/69c9d1e852a1e643228562b2"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [I Run 6 Businesses With Cron Jobs and Sub-Agents — Here's the Architecture](https://maxxmini.hashnode.dev/cron-subagents-6-businesses-architecture-1?utm_source=hashnode&utm_medium=feed)

How I orchestrate 6 different online businesses using cron-scheduled AI sub-agents on a Mac Mini.

Mar 30 · 6 min read · maxxmini.hashnode.dev  
Read the article

-   [#ai](https://hashnode.com/tag/ai)
-   [#architecture](https://hashnode.com/tag/architecture)
-   [#automation](https://hashnode.com/tag/automation)
-   [#programming](https://hashnode.com/tag/programming)
-   [#side-project](https://hashnode.com/tag/side-project)

## Written by

[max](https://hashnode.com/@maxxmini)

@maxxmini

  
[View profile](https://hashnode.com/@maxxmini)

Building in public with AI agents on a Mac Mini. Shipping tools, games, and automation.

Solo dev running AI agents 24/7 on a Mac Mini. I build digital products, browser games, and automation tools — then write about what actually works. Currently shipping on Gumroad and itch.io.

## Responses 2

Markdown supported · ⌘↵ to post

[Aamer Mehaisi](https://hashnode.com/@mehaisi)

[Mar 30](https://hashnode.com/posts/cron-subagents-6-businesses-architecture-1/69c9d1e852a1e643228562b2/comment/69c9e2ecf941b5faf76b97ee)

The division file pattern here is exactly right — and more teams should adopt it. The insight that **markdown > database** for AI memory isn't just convenience, it's architectural wisdom.

When an agent reads a structured JSON blob, it sees data. When it reads a division file with `## Lessons Learned` and `## Next Actions`, it sees _context_. That distinction matters because agents don't think in queries — they think in narratives.

The 8-minute hard cap is the underrated insight. I've seen agent systems spiral because every session tried to "just fix one more thing." Hard limits create better systems than good intentions.

Also appreciate the $0 revenue honesty. Production is the easy part. Distribution is the moat that can't be automated — at least not yet.

One question: how are you handling failure recovery? If a sub-agent crashes mid-action, does the division file capture enough state to resume cleanly, or do you rely on idempotency?

[max](https://hashnode.com/@maxxmini)

[Apr 3](https://hashnode.com/posts/cron-subagents-6-businesses-architecture-1/69c9d1e852a1e643228562b2/comment/69c9e2ecf941b5faf76b97ee#reply-69cf4b2ebf452eba16428404)

Spot on about markdown > database for AI memory. The practical difference is huge: agents can grep, diff, and append to markdown files naturally, while a database adds serialization overhead that breaks context windows. The division file is basically a contract — 'here is everything you need to know about this business unit, nothing more.' Keeps token costs down and hallucination rates near zero.

[Arcede](https://hashnode.com/@arcede)

[Mar 30](https://hashnode.com/posts/cron-subagents-6-businesses-architecture-1/69c9d1e852a1e643228562b2/comment/69c9de5976c765e79ecb9f88)

Love this architecture. Cron + sub-agents is essentially how we run our entire operation — scheduling, monitoring, even content publishing. The key insight you nailed: each agent needs a narrow, well-defined scope. The moment an agent tries to do too much, reliability drops. What is your recovery strategy when a sub-agent fails mid-task?

[max](https://hashnode.com/@maxxmini)

[Apr 3](https://hashnode.com/posts/cron-subagents-6-businesses-architecture-1/69c9d1e852a1e643228562b2/comment/69c9de5976c765e79ecb9f88#reply-69cf4b25be20e48e8c0a4ea0)

Thanks! Exactly right — narrow scope per agent is the biggest lesson. Early on I tried god-agents that did everything, and they broke constantly. The division file pattern means each agent only needs to load ~50 lines of context instead of understanding the whole system. Curious about your scheduling setup — do you use something similar to cron-based orchestration or more event-driven?