Two ways in: use AI to answer questions from your own documents today — no code, no setup required — or own the production-grade AWS starter behind it, built to give your engineers years of hard-won production lessons on day one instead of a blank repo. AI included either way.
Free until you have real users. Serverless cost tracks usage, not time — measured spend before revenue is under $2/month.
Pick the one that fits you. Both start with a quick access request below.
For business owners and teams. Upload your documents and get accurate, grounded answers in seconds — no code, no setup, no AI expertise required.
For developers. Get the full source — auth, IAM-authed database, CI/CD, observability, and a working AI (Bedrock RAG) module. It runs in your GitHub and your AWS account — you own it end to end, and we help you through setup.
AI is what makes both paths possible — a document assistant your whole team can use today, and a production AWS starter your engineers can build real product on without standing up an ML team from scratch. Grounded answers from your own documents, running on AWS Bedrock, wired in from day one.
Ask in plain English; answers come straight from your content — accurate and specific, never invented.
When it doesn't know, it says “I don't have that yet.” No confident hallucinations, no guessing.
Your documents stay in your account, isolated per user and IAM-authed — nothing shared, nothing trained on.
Titan embeddings + Claude, wired and working out of the box — no API keys, no model plumbing, no ML team.
The things that separate "a demo" from "a product you can actually run."
Auth, IAM-authed DB, secrets isolation, rate limiting, OWASP error handling.
Five test layers — including Playwright UI end-to-end tests — and a staging gate stand between you and production.
GitHub Actions check every push and gate every deploy — nothing reaches prod un-tested.
CloudWatch alarms for errors, throttles, latency and 5XX, plus an AWS Budgets alarm.
Serverless cost tracks usage — under $2/month before revenue.
A complete, opinionated, production-grade skeleton.
The AI module, wiredGrounded document Q&A on AWS Bedrock — Titan embeddings + Claude, an honesty gate, and per-user isolation. Included and working, not a stub to build later.
The stackVanilla JS SPA → API Gateway → Lambda (Node 24, Express) → Aurora DSQL (scales to zero) → SES — all IAM-authed, no long-lived DB password.
Auth done rightbcrypt, JWT, email verification, admin approval, brute-force lockout, enumeration prevention, password strength.
The full delivery pipelineSetup wizard, schema migrations, staging gate, smoke tests, frontend deploy with cache invalidation, a doctor health check.
CI/CD + observabilityGitHub Actions for test-on-push and gated deploys, plus one-command CloudWatch + budget alarms.
The ingredient guidesTesting, security, scalability, observability and cost docs — so you understand the system, not just run it.
The "now what?" bridgeA guide that walks you from a working skeleton to your first real feature, in the order that never burns you.
Five steps. The heavy lifting is a single command; the rest is a clone and a deploy.
No prior cloud experience needed — and if your team already has AWS chops, you'll move through this even faster. The free tier plus scale-to-zero DSQL keeps spend under $2/month until you have real users.
AWS CLI, GitHub CLI, Node 24, and psql — each a one-line install, all free.
One command — node provision.mjs — creates the IAM role, DSQL database, secrets, Lambda, API Gateway, and S3 bucket. Idempotent and resumable if it stops.
bash deploy.sh runs tests → staging → smoke tests → prod. bash deploy-frontend.sh ships the site and invalidates the cache.
The FIRST_FEATURE guide walks you from a working skeleton to your first real feature — in the order that never burns you.
Prerequisites: an AWS account, plus AWS CLI, GitHub CLI, Node 24, and psql — nothing else, nothing paid.
A free boilerplate is a snapshot. This is a maintained knowledge stream.
The real cost of building on AWS isn't the first deploy — it's the hundred small, expensive mistakes between deploy and a stable product: the DSQL constraint that isn't standard Postgres, the API Gateway timeout you hit at 29 seconds, the config call that silently wipes your env vars, the CloudFront cache that serves a stale frontend for hours. Every one of those is already a documented pitfall here, with the cost and the fix.
You're not buying a folder of files. You're buying the compounding output of every debugging session that's already been paid for — so you don't pay for it again.
Most builders abandon a SaaS attempt at one of five predictable cliffs.
| The cliff | The fix |
|---|---|
| Setup too hard | Dependency-free setup wizard + SETUP guide + a doctor health check |
| First deploy fails | doctor validates the whole environment before you deploy; staging gate catches prod-path bugs |
| Cost shock | Sourced cost numbers + "free until real users" + budget-alarm setup |
| "Now what?" | An end-to-end guided bridge to your first feature |
| Drift | Schema contract, smoke tests, a pitfall catalog, and a live state file keep the project honest |
Honesty is part of the product. For a commercial SaaS you'll also need things this skeleton doesn't ship today — flagged plainly, and on the upgrade roadmap:
Access is granted by invitation. Request access below and verify your email — you'll be approved by the owner before you can sign in.