Back to feed
Dev.to
Dev.to
8/1/2026
I built an AI job-search agent solo — here's the full stack

I built an AI job-search agent solo — here's the full stack

Short summary

A solo founder breaks down the full stack behind Reclaim, an AI job-search agent that reads résumés, scores them honestly, and matches against real roles. The stack includes Next.js, FastAPI, Supabase, Clerk, Stripe, and Gemini with tiered model routing to keep per-user cost around five cents. Key lessons include a Clerk webhook trailing-newline bug, Prisma unique-constraint races requiring idempotent handlers, and a silent cost leak from unentitled users hitting the Gemini API.

  • •Full stack breakdown: Next.js + FastAPI + Supabase + Clerk + Stripe + Gemini
  • •Tiered Gemini model routing keeps per-user cost around $0.05
  • •Hard-won lessons on webhook bugs, idempotency, and silent cost leaks

Generated with AI, which can make mistakes.

#ai-agents#ai-tools#industry-adoption
Read full article at Dev.to

Is this a good recommendation for you?

Comments

Failed to load comments. Please try again.

Explore more

How I Built an AI-Powered Reverse Hiring Platform with Next.js, Supabase, and OpenAI
Dev.to
Building an AI résumé scorer with Claude + AWS Bedrock - architecture and lessons learned
Dev.to
The original title is "How I Built a Job Search OS with Aurora PostgreSQL, AWS Bedrock and Vercel"
Dev.to
I built a Stack Overflow for gamers as a solo dev — here’s the stack and why
Dev.to