StartupDeckAI AI startup analysis and pitch decks, built full stack.

StartupDeckAI is an AI platform that turns a startup idea into market analysis, competitor intelligence, a scored GO / PIVOT / KILL verdict, and a pitch deck.

I built it end to end: the React front end, the API and data model, the analysis engine, the background jobs, payments, and the CI/CD pipeline.

Founders juggle spreadsheets, research tabs, and slide templates, and the pitch ends up disconnected from the analysis.

Generic chatbot output is hard to trust and harder to turn into something investors will read.

AI generation is slow and costs money on every call. An analysis gets a 90-second budget and streams its progress to the browser as it runs, with heartbeats so the proxy in front of the API does not cut the connection.

The data model had to absorb new signals and a changing product shape without backfills.

The front end is React and TypeScript on Vite, with TanStack Query for server state, Zustand for client state, Tailwind CSS and Radix UI for the interface, Recharts for charts, and Three.js and Framer Motion for the interactive layer.

An Express API serves REST and server-sent events on PostgreSQL through Drizzle ORM, plus a read-only GraphQL endpoint for the internal admin page. Sign-in uses Passport (email and Google OAuth) with sessions in Redis, and payments run on Razorpay.

The analysis engine runs four LLM stages in parallel and a synthesis stage, then scores eight dimensions with a deterministic formula; every figure carries a source label set in code. The analysis and the pitch deck stream to the browser over server-sent events, and the deck exports to PDF. BullMQ on Redis runs email delivery and scheduled market news and funding jobs.

GitHub Actions runs lint, type checks, 3,400+ unit tests with coverage, an npm audit and Playwright end-to-end tests on every push. When it passes on main, a deploy workflow triggers the API deploy on Render; Vercel builds the front end from main.

The platform prioritizes a structured idea-to-deck workflow over open-ended conversation.

Rich 3D visuals cost performance budget, so they are kept progressive and responsive.

Additive schema design paid off: pivoting the product from validation to pitch decks did not require a painful migration.

It also reinforced how SaaS complexity grows once auth, payments, background jobs, and SEO enter the picture, and why a strict CI gate pays for itself.