Skip to content
AI Full-Stack Wiki

Projects

Step-by-step builds of increasing difficulty, from a streaming chat app to a production SaaS assistant.

6 articles · about 143 minutes of reading

  1. Project: Build a Full-Stack AI Chat App with Next.js and ClaudeBuild a production-quality AI chat app: streaming replies, saved conversations in Postgres, history trimming, rate limits, usage tracking, and automatic titles.Difficulty: Intermediate22 min read
  2. Project: Build a Docs Q&A Assistant with RAG, Citations, and EvalsBuild a documentation assistant: incremental ingestion with content hashes, hybrid search and reranking, streamed answers with source links, feedback, and evals.Difficulty: Advanced24 min read
  3. Project: Build a Customer Support Agent with Tools, Approvals, and HandoffBuild a support agent that searches help articles, looks up orders, proposes refunds for human approval, and hands off to staff, with runs persisted in Postgres.Difficulty: Advanced26 min read
  4. Project: Build a Remote MCP Server for Your Product with Next.jsExpose your product to AI agents: a remote MCP server in a Next.js route with Streamable HTTP, hashed API tokens, scopes, per-user data access, and tests.Difficulty: Advanced21 min read
  5. Project: Build a Multi-Agent Research System with Web SearchBuild a research system where a lead agent plans, parallel subagents search the web, and a durable worker produces a cited report, with progress and cost limits.Difficulty: Advanced24 min read
  6. Capstone: Build a Multi-Tenant SaaS AI Assistant, End to EndThe capstone: a multi-tenant SaaS assistant with organizations, row-level security, per-org RAG, usage metering, plan limits, evals, and a launch checklist.Difficulty: Advanced26 min read