Live in production2025–present
Voltrisks
Production AI-powered macroeconomic risk intelligence platform.
Stack
Next.jsReactNode.jsPythonPostgreSQLSupabaseRedisStripeGitHub ActionsRenderVercelGrafanaClaudeGPT
GPT-powered SaaS that monitors 350+ economic variables across 6 government and financial APIs, delivering real-time macroeconomic risk assessments across 11 GICS equity sectors and 7 risk categories. Solo-built and shipped to live launch.
The problem
Individual investors don't have access to the kind of macroeconomic risk intelligence that institutional desks treat as table stakes. Bloomberg terminals are $24K/year. Most retail research stops at "the Fed raised rates 0.25%" without answering "what does that mean for my energy sector exposure this quarter?"
Voltrisks closes that gap with AI-powered macro risk dashboards that translate 350+ raw economic indicators into sector-level risk assessments — updated 5× per weekday, accessible to anyone with a subscription.
Voltrisks closes that gap with AI-powered macro risk dashboards that translate 350+ raw economic indicators into sector-level risk assessments — updated 5× per weekday, accessible to anyone with a subscription.
What I built
- Full product, solo. 13 months from blank repo to live launch. 1,305 commits, 222,000+ lines of code. Backend, frontend, data pipelines, AI workflows, billing, observability — every layer.
- Production data pipeline. 422,000+ macroeconomic data points across 354 variables from 5 government and financial APIs (FRED, EIA, BLS, CFTC, GPR), spanning 21 years of historical depth, stored across 195 PostgreSQL tables.
- Statistical pipeline rigor. 5-module Python pipeline across 4 frequencies (daily, weekly, monthly, quarterly), producing 103,000+ validated macro-sector correlations using t-tests, Benjamini-Hochberg FDR correction, walk-forward validation, and k-means regime classification across 4 market regimes (VIX, credit spreads, yield curve).
- Agentic AI workflows. LLM-in-the-loop content generation pipeline for risk scenario translation: technical inputs → user-friendly content → automated validation (10+ rule checks, auto-fix loop) → director-review pass. Guidelines, governance docs, and tests written specifically to prevent model drift, hallucination, and shortcut-taking.
- Reliability layer. 5× daily CI/CD deployments, 700+ automated daily data jobs at 96% success rate, Prometheus + Grafana observability with 9 custom metrics, circuit breakers across 6 external API integrations, 3-tier rate limiting.
- Security & compliance. 215 Snyk scans executed via CI, automated dependency patching, Stripe webhook signature verification, Supabase row-level security, CORS lockdown. All critical and high CVEs resolved.
Architecture
Three repositories: a Node.js + Python backend, a Next.js frontend, and a separate Grafana observability agent. Production on Render (API), Vercel (frontend), Supabase (Postgres), and Grafana Cloud (monitoring).
Backend (Node.js + Python)
├── Express API on Render (REST, auth, billing)
├── Python risk engine (5× daily via GitHub Actions)
├── Python data pipelines (FRED, EIA, BLS, CFTC, GPR)
├── Statistical pipeline (correlation, FDR, walk-forward)
├── LLM scenario quality pipeline (Claude CLI)
└── Redis/BullMQ async report queue
Frontend (Next.js on Vercel)
├── App Router, Tailwind, React Query
└── Supabase Auth, Stripe billing
Data (Supabase)
└── PostgreSQL, 50+ tables, 4.6M+ rows
Observability
└── Prometheus metrics → Grafana Cloud
What I learned shipping this solo
Building a production AI SaaS solo over 13 months changed how I think about the role of an AI builder. A few takeaways:
- LLM-in-the-loop ≠ LLM-everywhere. The statistical pipeline is deterministic. The risk engine is deterministic. The LLM lives in the content quality layer — where it's genuinely useful and where the cost of being wrong is bounded. Choosing where AI shouldn't live is half the job.
- Governance is engineering, not paperwork. The 10+ automated rule checks, the auto-fix loop, the director-review pass — that's how you prevent drift in a production LLM pipeline, not a Notion doc nobody reads.
- Solo means picking your battles. Render + Vercel + Supabase + Stripe + Grafana Cloud — boring, reliable, well-documented platforms — let one person ship what used to need a small team.