1 Month, $5000 in AI Subscriptions and Tokens.
I’m one person. With Claude Code + Codex + Copilot, I built 18 distinct systems. ~50k lines of code.
If you hired 2 full-stack engineers to build this from scratch, it’d take 6–12 months and cost ¥300k–600k.
Here’s what I built in each section 👇 (1/7)
【Quant Trading + Blog Traffic Acquisition】
🧠 Quant: Polaris strategy versions 1/5/6 live trading, dual-machine hot standby, backtesting lab v2 (Numba JIT + Walk-Forward + Monte Carlo + multi-symbol portfolio), desensitized Mac standby.
🌐 panshi.io blog: 64 technical articles, active-active AWS HK/US + Cloudflare CDN, 14-channel affiliate tracker with per-article attribution, 64 Flux AI hero images with consistent branding. (2/7)
【Release Management Web App :9891 · The Most Unique Piece】
A local web app that independently manages panshi.io publishing:
- 10+ admin pages (articles + affiliate attribution + editor + OG preview + image library)
- 7-step publishing pipeline + 10 scheduled tasks
- X three modes: short tweet / Premium long-form / thread digest (like this one)
That’s 2 months of solo engineering work. (3/7)
【Monitoring / Backup / Scheduled Tasks】
3-2-1 backup: Mac SSD + iCloud 2TB + S3 Deep Archive Tokyo (¥0.15/month)
20+ backup jobs + centralized monitoring on :9890 + boot-time catch-up
34 scheduled tasks on Mac via job_runner + Prometheus + Grafana + Telegram alerts
13 Grafana dashboards for connection monitoring
That infrastructure stack is 3 months of solo engineering. (4/7)
【Proxies + Security + AI Tooling Ecosystem】
🛡️ Dual-gateway redundancy + residential proxy 7-node fallback + Surge fail-closed sentinel (auto PF killswitch on crash) + custom Swift menu bar app (NetworkGuard)
🤖 Claude Code dual-channel switching, Sonnet/Opus/Haiku model mix (60% API cost reduction), cmux multi-session parallelization, 7 independent Telegram bots with division of labor (5/7)
【Three Truths About Solo AI Development】
1️⃣ Code is no longer the bottleneck—requirements definition is. Claude can churn out hundreds of lines in one go, but you have to figure out what you want yourself.
2️⃣ Deployment/monitoring/backup is worth more than initial development—70% of the effort goes there.
3️⃣ Standardized infrastructure lets AI transfer knowledge across tasks—efficiency grows exponentially.
It’s not that AI replaces humans—it’s that “one person who understands the business + knows how to use AI = a whole team from the past.” (6/7)
📖 Complete breakdown of all 18 systems + cost breakdown + development paradigm analysis: https://panshi.io/posts/5000-usd-token-what-i-built/
Drop your thoughts: what’s the most satisfying project you’ve shipped with AI? (7/7)