Build with AI
Prompting your way to working software. Vibe coding, code review, working on existing codebases.
Vibe coding: prompting your way to a working app
The describe to generate to test to refine loop. What "vibe coding" actually means in practice. Where it breaks.
Pick your build environment: Lovable vs Bolt vs Cursor vs Claude Code
When each shines. Browser-only no-code, IDE pair programmer, terminal agent. Decision matrix included.
Catching AI-generated bugs before they ship
Hallucinated APIs, missing edge cases, security holes. How to review AI code without being a senior engineer.
Working with AI on a codebase you did not write
CLAUDE.md, context files, repo conventions. How to teach an agent your codebase so it stops hallucinating its way through your patterns.
Prompts vs Skills vs Workflows vs Agents — when to use which
A prompt is one instruction. A skill is a prompt packaged so the model loads it on demand. A workflow fixes the steps; an agent decides them. Where each one breaks.
How RAG works, and when to use it
The pattern that grounds an LLM in your data: how each step works (chunking, embedding, retrieval, reranking, generation), when RAG wins over fine-tuning and long context, and the failure patterns most beginner systems hit. With a modern 2026 stack.
Prompt, skill, RAG, knowledge base, or fine-tune? A decision guide
The five ways to get an AI to do what you want — a better prompt, a reusable skill, retrieval over your data, an indexed knowledge base, or fine-tuning. A decision order that starts with the cheapest and only escalates when you hit a real wall.
RAG vs an indexed knowledge base: what is the difference?
A knowledge base is the content; RAG is a technique for querying it. The real choice underneath is the retrieval method: vector search finds meaning, a keyword index finds exact strings. When each wins, and why most systems run both.
How to create an AI agent
The three honest ways to build one (no-code, a coding framework, or from scratch), with a first build for each, the failures to design for, and the resources worth your time. It starts with the question most people skip: do you even need an agent?
Prompting an AI app builder for a real backend: database, auth, and payments
App builders default to a front end with mock data unless the prompt names the backend. What to specify, in what order, and where prompting stops.
Ship and own your stack
Take your build from prototype to production. Real deploy, real monitoring, real ownership.