Ruby on Rails is a Ruby natural fit for edtech. GreatCTO auto-detects both — adds the edtech archetype overlay, wires edtech-specific gates, and runs 83 specialist agents around your existing Ruby on Rails workflow.
GreatCTO reads your Gemfile and detects rails + edtech archetype from signals: imports, file structure, env vars, README hints.
Attaches the edtech archetype overlay: archetype-specific reviewer + compliance gates. Override if your specifics differ; the defaults are sensible for Ruby on Rails-style projects.
qa-engineer runs rubocop / rspec / brakeman; security-officer flags mass assignment + N+1 ORM queries; performance-engineer checks ActiveRecord query hot paths.
Bugs you've hit before in other Ruby on Rails projects (connection-pool exhaustion, ORM N+1 queries, retry storms) — the agent's Step 0 includes the prior detection order. MTTR drops 94 % on second occurrence (methodology).
$ cd my-rails-app && npx great-cto init ✓ scanning manifests… found manifest ✓ stack: rails (Ruby) ✓ archetype: edtech ✓ overlay: applied ✓ 83 agents ready $ /start "add course enrollment endpoint" ▸ architect drafting ARCH-edtech.md… ▸ pm decomposing into beads tasks… ⚐ gate:plan — your approval needed
Approve → 3 senior-devs run in parallel worktrees → 5 reviewers fan out in parallel → gate:ship → deploy. One real run walked stage-by-stage: /proof.
This is the shape of what senior-dev drafts for "course enrollment endpoint" — auth first, schema validation, and the audit line the edtech reviewer requires before gate:ship opens.
# app/controllers/edtech_controller.rb — reviewed by 5 agents
class EdtechController < ApplicationController
before_action :authenticate_user! # security-officer: auth before handler
def create
result = EdtechService.call(permitted_params, current_user)
AuditLog.record(who: current_user.id, what: "course enrollment endpoint",
confidence: result.confidence) # gate:edtech: every decision logged
render json: result
end
endedtech overlay.Student tools under COPPA / FERPA with parental consent.
Classroom platforms meeting Section 508 / WCAG 2.2 AA.
K-12 products aligned to state student-privacy laws.
No black-box "AI does it all" loop. GreatCTO is a deterministic state machine — 8 stages, 22 nodes, 2 human gates. Every node maps to a real agent on GitHub. Inspect the state machine →
$ npx great-cto init
Free, MIT, runs locally. Built as a Claude Code plugin — install with one command.
Eight stages, two human gates, four memory layers. Why this exact shape, and what I tried that didn't work.
One run, one feature, from prompt to merged PR. Time, cost, and gate-by-gate breakdown — no marketing math.
Regex vs LLM-based archetype detection, the false-positive count, and why I keep rejecting the obvious fix.
The bottleneck in agentic SDLC isn't model quality — it's process governance. Here's the state machine that closes the gap.