INTERNAL OctoMonic
2026-08-19

Full Stack Survey → the Workshop Cut

Everything we actually run, surveyed live across all projects (2026-08-19), then filtered down to what belongs in the 6-hour workshop. Canonical files: memory/reference_stack_inventory.md · prospects/jobhub/workshop-stack-decision.md

Part 1 — The full stack, by layer

1 · Languages
TypeScript / JavaScript (primary, all web) · Python 3.10 (all AIOS automation, scraping, briefs) · SQL (Postgres) · Bash
2 · Frontend
Next.js 15/16 + React 19 (Monesys, OctoMonic OS, Beertza) · Vite + React (octomonic.com) · Tailwind CSS (universal) · shadcn, Radix, Base UI, lucide-react, framer-motion, next-intl, recharts
3 · Databases
Neon Postgres (GPI/GoMobile, AIOS Knowledge + pgvector) · Supabase (Monesys — Postgres/Auth/Realtime/Edge Functions) · Firebase Firestore (Beertza, octomonic.com, Dog Camp) · Elestio Postgres (ops DB) · Redis (n8n cache)
4 · Hosting & Infra
Vercel (Monesys, OS, pi-dashboard, mockups) · Firebase Hosting (octomonic.com) · Elestio VM (n8n, Evolution, Operator 24/7) · Hetzner VM (GPI) · Cloudflare (registrar, DNS, tunnel, Zero Trust)
5 · AI / LLM
Anthropic Claude (primary — Claude Code is the team's dev surface) · Google Gemini · Groq (Llama 3.3 70B) · Ollama (local) · ElevenLabs (TTS) · NotebookLM (grounded research)
6 · Automation & Orchestration
n8n (pipelines/webhooks) · cron + launchd · Playwright (browser automation + deploy QA) · Evolution API (WhatsApp) · Resend (email) · Google Workspace APIs (Gmail, Calendar, Drive)
7 · Data & Scraping
ZenRows (GPI primary) · Apify · Spider API · BuiltWith · Brandfetch
8 · Business Ops
Monday.com (task system of record) · Notion (pipeline) · Green Invoice · GitHub · Google Workspace
9 · Dev Environment
git + worktrees · 8 MCP servers (notebooklm, supabase ×2, postgres, firebase, n8n, filesystem, docker) · Claude Code plugins (superpowers, context-mode, claude-mem, designlang, skill-creator, frontend-design)
10 · Methodology — the actual differentiator
Context hierarchy (CLAUDE.md) · ~55 codified correction rules · 20 skills · state continuity (session log + open-items ledger) · verification discipline · persistence proof · deliverables-as-URLs · orchestrator-worker subagents · goal loops with acceptance criteria · CLI-first · local-time discipline

The survey's own finding

Layers 1–9 are commodity — anyone can buy them. Layer 10 is the product. It's why the same tools produce different results here, it's what transfers to a client, and it's what a syllabus can't be copied from.

Part 2 — The filter

Every candidate scored on one question: capability delivered ÷ setup cost for someone with zero technical background. Anything that adds an account, a console, or a concept without unlocking a visible new power got cut.

1 · One platform, not best-of-breed per layer. We run Neon + Supabase + Firebase because each wins its niche. A beginner needs one login. Firebase wins on consolidation alone: database + storage + auth + hosting behind a Google account they already have, in a visual console where progress is seeable.

2 · No layer that only pays off at scale. n8n, Vercel, Redis, ZenRows, Playwright, worktrees — real capability, invisible inside six hours.

3 · Teach the method, not the tool list. Layer 10 transfers to any assistant on any stack, and it's what actually makes someone effective.

✅ In — taught

  • AI assistant — Claude / ChatGPT / Gemini (their choice)
  • Firebase — Firestore + Hosting (+ Storage as needed)
  • The browser — everything runs in it

Total footprint: two accounts, one browser.

⚠ Stretch — session 4 / fast rooms

  • Connectors (Gmail, Calendar, Drive/Sheets) — highest wow available
  • GitHub — version safety + recruiter-visible portfolio
  • n8n / scheduled automations — things that run without you

✕ Out — ours, not theirs

  • Neon · Supabase · Vercel · Cloudflare
  • Elestio / Hetzner VMs · Redis
  • Playwright · ZenRows · Apify
  • Next.js / React / Tailwind toolchain
  • Monday · Notion · Green Invoice
  • MCP authoring · worktrees · Python layer

Part 3 — Layer 10, translated for participants

Our practiceWorkshop languageSession
Context hierarchy (CLAUDE.md)The context file — CV, target roles, standing instructions read every time1
Codified corrections (feedback_*.md)Standing caveats — corrections written in once, never repeated2
Verification disciplineMake it prove it — demand real output, never accept "done"2
Voice / screenshot inputFeed it reality — record and screenshot instead of describing2
Skills (repeatable procedures)Save your winning prompts as reusable recipes2
Goal acceptance criteriaDefine "done" before starting — the plan prompt in every recipe3
State continuity (session log)The project notes file that lets you resume where you stopped3
Deliverables as URLsShip a link, not a file — the interview artifact3

Part 4 — What we run the cohort on

Invisible to participants, zero new tooling for us: mockups on *.octomonic.com for handouts and the syllabus · WhatsApp (Evolution API) for reminders and the no-show chase · Monday for cohort tracking · Google Calendar for scheduling · Firebase for a graduates gallery if that direction lands.

The one open decision

Connectors. Adding Gmail/Drive moves a graduate from "built a tool" to "my assistant works my inbox" — a materially bigger interview claim and the strongest hook into the corporate product. It costs about an hour and carries the highest in-room failure risk (OAuth consent screens are where beginner rooms fragment).

Recommendation: keep it out of the pilot, run it as the session-4 upsell once the three-session flow is proven. Revisit with the first cohort's friction data.

OctoMonic · internal · related: curriculum · market evidence