← The Vault
Free guide · the taste layer

The Build With AI Playbook — make AI build things that don't look AI

You can spot AI-built work instantly. So can everyone else. Here's the method that stops you getting the average: direction + references + correction + taste.

Built for Day 14 · Building With AIDuplicate it · use it as a checklist

First, the problem

You can spot AI-built work instantly. The tells:

None of this is a model problem. It's an input problem. The model gives you the average of everything it's seen — because you asked it for the average. Generic in, generic out. Here's how to stop.

The method — 4 steps, in order

1. Know what you're building first

Don't ask AI to make something from scratch. That's how you get the average. You decide the direction; the AI executes it. Before you generate anything, answer: what is this exactly (one sentence)? Who's it for? What feeling should it give? What does it explicitly not look like?

Prompt to run first — before any generation
Before you build anything, ask me 5 questions to understand what I actually want — the purpose, the audience, the feeling, the references, and what it should NOT look like. Don't generate until I've answered.

That one move kills 80% of generic output. You're directing, not delegating.

🔒 Unlock the rest of the playbook

Read steps 2–4 + the tools, free

Drop your email and the full playbook opens right here — nothing to download.

  • The references system (where to pull them, what to never copy)
  • The "treat it like an intern" correction loop
  • How to actually build taste
  • The one Claude Code skill that upgrades everything (with the install command)
Free. I'll also send you the rest of the series. Unsubscribe anytime.
Something went wrong — try again or DM @alixqureshi.
✓ Unlocked — here's the full playbook.

2. Give it real references

The single biggest lever on quality. AI has no taste of its own — you lend it yours through references. Where I pull them:

The rule: don't reference anything that already looks AI. No purple gradients, no floating blobs. Pick work with a clear point of view. Save 5–10 strong references, then feed them in.

Prompt
Here are 5 reference images [attach]. Don't copy them — extract the design language: the type treatment, the colour discipline, the spacing, the overall feeling. Then apply that language to what we're building.

3. Treat it like an intern

The AI doesn't have the answers. It's guessing. A talented intern on day one — capable, fast, but it needs direction and correction. So never accept the first output. Correct it like you'd correct a junior:

Every correction is the actual instruction. The 3rd or 4th pass is where it starts looking like yours. The shortcut that changes everything: ask it to show you options, not describe them.

Prompt
Mock up 3 versions of this on a single page so I can see them side by side. I'll pick one, then we'll refine it.

You can't judge a visual decision from a text description. Make it render. Choose with your eyes.

4. Build taste

The hard one. AI can execute taste — it can't have it for you. If you can't tell good from average, no prompt will save you. The good news: taste is trainable. How I built mine:


The one-line summary

Direction + references + correction + taste. Skip any one and you're back to the purple gradient.


Bonus — the tools I use

The Front-End Design skill for Claude Code (Anthropic). The biggest single upgrade. It pushes Claude away from generic AI aesthetics — the purple gradients, the default fonts — toward distinctive, production-grade design with real typography, creative layouts, and thoughtful animation. Install it (one command in your terminal):

npx -y skills add anthropics/skills --skill frontend-design --agent claude-code

That drops it into your project's .claude/skills folder. Then just build as normal and tell Claude: "Use the front-end design skill to build this. Direction: [brutalist / editorial / premium SaaS / etc]." It outputs working HTML/CSS/JS or React with the design baked in. Pair it with steps 1–3 above and you're a long way past anything that looks AI-built.


Built this for Day 14 of Building With AI. If it was useful, the rest of the series is at @alixqureshi.

© 2026 Ali Qureshi · home · the vault
ali@adcrate.com