惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Recent Announcements
Recent Announcements
J
Java Code Geeks
雷峰网
雷峰网
Microsoft Security Blog
Microsoft Security Blog
博客园 - 【当耐特】
腾讯CDC
博客园 - 司徒正美
B
Blog RSS Feed
博客园 - 三生石上(FineUI控件)
I
InfoQ
N
Netflix TechBlog - Medium
L
LangChain Blog
博客园_首页
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
T
Tailwind CSS Blog
MyScale Blog
MyScale Blog
美团技术团队
The Cloudflare Blog
爱范儿
爱范儿
Stack Overflow Blog
Stack Overflow Blog
博客园 - 聂微东
H
Help Net Security
Martin Fowler
Martin Fowler
V
Visual Studio Blog

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
I Rode a Scooter in the Rain for 12 Hours. My 6 AI Agents...
bluefin ship · 2026-04-24 · via DEV Community

Today I rode my 125cc scooter through Taipei rain for twelve hours and made NT$2,100 (about US$65) delivering lunch and dinner shifts.

In the exact same window, my phone was running six AI agents. By the time I peeled off the wet jacket, a $19 product was live on Gumroad. I didn't touch a keyboard.

This is not a manifesto. This is a Thursday.

The team that ships while I ride

Six roles, each a separate Claude CLI process with its own system prompt and memory slice:

  • CEO agent — decides scope. This morning's call: "ship Agent Cookbook to Gumroad today, $19, no feature creep."
  • PM agent — splits the day into six working blocks and assigns deliverables per block.
  • Copywriter — drafts launch copy. Fires on a red light.
  • Designer — renders covers and OG images. Runs while I wait at the restaurant counter.
  • Dev — writes and patches code. Gets the longest turns.
  • QA — reviews everything the others produce and returns a numbered list of defects.

A seventh helper, the CC Daemon, polls IMAP for 2FA codes, pastes them into forms, and pushes completion notices to Discord so I hear a ping on my helmet speaker.

A real timeline from today

  • 09:40, red light on Dunhua: I Discord-send "cookbook launch — $19 — today." CEO answers in 14 seconds.
  • 11:22, waiting for a bento: Designer drops v1 of the cover. Too busy. I reply with one emoji. v2 lands while I strap the bag.
  • 14:08, left turn on Section 4 of Zhongxiao: QA finds three factual errors in the draft. Dev patches them before the light turns green.
  • 19:55, ringing a customer's doorbell: Gumroad sends a KYC code. CC Daemon reads the email, fills the field, publishes the listing. My phone buzzes: live.

I got home soaked. The product had already made its first sale.

The architecture, end to end

Phone (Discord)
   |
   v
CC Daemon  (hourly tick + event triggers)
   |
   v
Blackboard  (tasks.jsonl — append-only)
   |
   v  fan-out
Subagents  (Claude CLI, parallel)
   - CEO, PM, Copy, Design, Dev, QA
   |
   v
Shared memory  (MemPalace — MCP knowledge graph)
   |
   v
Output queue ---> Gumroad / Discord push / inbox/

Enter fullscreen mode Exit fullscreen mode

The blackboard is the whole trick. Every agent reads the same tasks.jsonl, claims a row, writes its output back as a new row with a parent_id. No orchestrator god-object. If one agent crashes, the row stays unclaimed and the next tick retries it.

MemPalace is the shared brain. When the Copywriter references "last week's tone notes," it's pulling from the same knowledge graph the CEO used to write today's brief. Context survives /compact, reboots, and me forgetting what day it is.

The minimum viable tick

Strip away the Discord bridge, the IMAP poller, the MCP servers, and this is the beating heart:

# Minimal daemon tick — run every 5 minutes via launchd/cron
import subprocess
from pathlib import Path

def call_agent(role_prompt: str, user_prompt: str) -> str | None:
    r = subprocess.run(
        ["claude", "-p", "--max-turns", "1",
         f"[ROLE]\n{role_prompt}\n[TASK]\n{user_prompt}"],
        capture_output=True, text=True, timeout=120,
    )
    return r.stdout if r.returncode == 0 else None

draft = call_agent(
    "You are a copywriter. 200 words max. Hook in first line.",
    "Write a Threads post about shipping while delivering food.",
)
review = call_agent(
    "You are QA. Return a numbered list of factual or tonal defects.",
    f"Review this draft:\n{draft}",
)

Path("inbox/draft.md").write_text(draft or "")
Path("inbox/review.md").write_text(review or "")
# Next tick: a Dev agent reads review.md and patches draft.md.

Enter fullscreen mode Exit fullscreen mode

Fifteen lines. Two agents. A handoff via files. Scale the same pattern to six roles and you have my setup — minus the keys I'm not going to paste.

Why I built it this way

My fixed monthly bills are NT$47,000. I cannot afford one human employee. I cannot afford to stop delivering to "focus on the startup." So I built a team I pay in electricity — less than one coffee a day on an M1 Max — that doesn't clock out when I go back on the road.

The reframe that made it click: I'm not trying to automate myself out of delivery. I'm trying to make sure the six hours I'm on a scooter aren't six hours my business is asleep. Food delivery pays cash today. Agents compound tomorrow. I need both.

What's in the cookbook

I wrote down every piece: the role prompts, the blackboard schema, the Discord-to-daemon bridge, the handoff patterns between CEO and PM, how QA returns structured defects Dev can actually apply, and the failure modes I hit in the first six weeks (there were many).

One honest line: this is a pattern cookbook — you'll wire your own Discord, IMAP, and API keys to make it run. I'm handing you the architecture and the prompts that survived contact with reality, not a one-click installer.

$19 on Gumroad. I'm asleep, on a scooter, or soaked — it's still selling.

https://vampireheart3.gumroad.com/l/agent-cookbook

This is Thursday.