FastAPI is a Python natural fit 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 FastAPI workflow.
GreatCTO reads your pyproject.toml / requirements.txt and detects fastapi + 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 FastAPI-style projects.
qa-engineer runs mypy / ruff / pytest --cov; security-officer scans for SQL injection patterns common in ORMs (SQLAlchemy, Django ORM); performance-engineer profiles async patterns for I/O contention.
Bugs you've hit before in other FastAPI 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-fastapi-app && npx great-cto init ✓ scanning manifests… found pyproject.toml ✓ stack: fastapi (Python) ✓ archetype: agent-product ✓ overlay: applied ✓ 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.
# app/routers/agent_product.py — drafted by senior-dev, reviewed by 5 agents
from fastapi import APIRouter, Depends
from app.auth import require_user # security-officer: auth before handler
from app.audit import audit_log # gate:agent-product: every decision logged
router = APIRouter(prefix="/agent-product")
@router.post("/")
async def create(payload: AgentProductIn, user=Depends(require_user)):
result = await handle(payload, user) # qa-engineer: pydantic schema enforced
await audit_log(who=user.id, what="tool-calling endpoint for the agent loop", confidence=result.confidence)
return resultagent-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.
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.