Skip to content
Architecture hub

VibingCoderAI · LLM Agent Architecture

How VibingCoderAI works.

A casual developer idea goes in. A senior-grade AI agent brief comes out. Four steps from a Vercel-hosted Next.js frontend to a Claude-powered Lambda brain — entirely provisioned in Terraform, no console-clicked resources in the stack.

  1. Step 01 · Next.js 16

    The interface.

    A Next.js 16 App Router frontend hosted on Vercel — Server Components by default, client islands only where interactivity demands. TypeScript strict, Tailwind v4, no CSS-in-JS, no module.css. The visitor's casual idea enters here, leaves shaped like a senior-engineer-grade prompt.

    vibingcoder.aiIDEA"build a snake game with score tracking"SENIOR-GRADE PROMPT
  2. Step 02 · Lambda + Claude

    The agentic brain.

    The frontend calls an AWS Lambda over public HTTPS. The Lambda handler runs the Anthropic Claude SDK against a master system prompt that enforces structural completeness, accessibility, error-handling and explicit out-of-scope boundaries. Output is a copy-pasteable Markdown brief any coding agent can execute without scope drift.

    λLAMBDACLAUDE
  3. Step 03 · Terraform

    The infrastructure.

    A decoupled monorepo: apps/web on Vercel, apps/lambda packaged as an ECR container image, all of it provisioned via Terraform — ECR registry, Lambda compute, API Gateway HTTP edge, DynamoDB tables. Zero console-clicked resources in the stack. Everything is plan-apply.

    REPO📁 apps/├─ web/ (Next.js · Vercel)└─ lambda/ (ECR + Lambda)📁 infrastructure/├─ ecr.tf├─ lambda.tfterraform
  4. Step 04 · DynamoDB

    The data layer.

    DynamoDB carries the persistence — prompt history, account-scoped settings, future billing state. On-demand billing keeps the cost flat at low traffic and elastic during a spike. Auth (Clerk) and payments (Stripe) sit in the roadmap behind the same table boundaries.

    prompt_historyPK SK KINDON-DEMAND BILLING