Blitz.js is a TypeScript workable choice for agent product. GreatCTO auto-detects both — adds the agent-product archetype overlay, wires agent-product-specific gates, and runs 83 specialist agents around your existing Blitz.js workflow.
GreatCTO reads your package.json and detects blitz + agent-product archetype from signals: imports, file structure, env vars, README hints.
Attaches the agent-product archetype overlay: OWASP LLM Top-10 evals, prompt-injection review, EU AI Act high-risk classification. Override if your specifics differ; the defaults are sensible for Blitz.js-style projects.
qa-engineer runs tsc --strict / eslint / vitest --coverage; security-officer checks for prototype pollution + XSS sinks; performance-engineer reviews bundle size + cold-start times.
Bugs you've hit before in other Blitz.js 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-blitz-app && npx great-cto init ✓ scanning manifests… found package.json ✓ stack: blitz (TypeScript) ✓ archetype: agent-product ⚠ archetype + stack combo is unusual — review overlay manually ✓ 83 agents ready $ /start "add tool-calling endpoint for the agent loop" ▸ architect drafting ARCH-agent-product.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 "tool-calling endpoint for the agent loop" — auth first, schema validation, and the audit line the agent-product reviewer requires before gate:ship opens.
// src/agent-product/mutations/createAgentProduct.ts — reviewed by 5 agents
import { resolver } from '@blitzjs/rpc';
export default resolver.pipe(
resolver.zod(CreateAgentProduct), // qa-engineer: zod schema enforced
resolver.authorize(), // security-officer: auth before handler
async (input, ctx) => {
const result = await handle(input, ctx.session.userId);
await auditLog(ctx.session.userId, 'tool-calling endpoint for the agent loop', result.confidence); // gate:agent-product
return result;
}
);agent-product overlay.Customer-support agents with tool-calling and human escalation.
Research / browsing agents with cost-runaway protection.
Workflow copilots embedded in existing SaaS products.
Blitz.js (TypeScript) is not a typical fit for agent product. The archetype overlay still attaches, but you may want to override defaults more aggressively. Check the agent-product archetype page for the typical stack list and decide if your case is the right tool / right archetype.
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.