Free playbook · 13 pages
Build with AI without building a monster
A practical guide to planning, designing and shipping with AI. The workflow we use ourselves at SmplCo to keep AI builds from going off the rails.
Get the free playbookThe workflow, top to bottom
Plan → Figma → Claude Design → Claude Code → GitHub → Deploy. The same flow we use ourselves on every project. Built from 125+ products shipped and refined every week. Recognised by Figma as a global exemplar of AI-assisted development.
Plan, design, decide
Brief writing and journey design before AI gets involved. The boring questions — who, problem, journey, what "done" means — are where the value lives.
Operationalise via Claude Design
Turn your Figma system into actual rules so AI builds inside it, not beside it. No purple gradients. No invented colours. No glassmorphism nobody asked for.
Build with Claude Code, carefully
Plan first. Then prompt. Like a good junior developer, not a caffeinated raccoon with access to your repo. Main journey only, design rules as the source of truth.
Ship, secure, sustain
GitHub, deploy, domain, data. The boring infrastructure that turns a prototype into a product. Plus a sanity check on what you can actually defend to a customer.
The mistakes we see every week
Six predictable patterns that turn an AI investment into a budget drain. The playbook covers how to spot and avoid each one.
Starting with the prompt, not the brief
Asking AI to "make an app" before deciding who it is for, what problem it solves, or what "done" means. Wasted weeks dressed up as iteration.
Letting AI invent its own design system
Default purple gradients on every screen. Glassmorphism nobody asked for. Crypto-startup dashboards. Fine for a throwaway, less fine when investors are in the room.
Picking the cheap model first
Trying to save on inference, then shipping a feature that almost works. The gap between a frontier model and a budget one is usually the whole product — pay for the good one.
No evals, no observability
Shipping AI features with no way to tell when they degrade or how much they cost per request. Then panicking.
Bolting AI onto the wrong feature
Adding a chat interface because a competitor did, rather than starting where AI actually moves a metric.
Going all-in on one model
Treating one provider as a permanent partner. The right answer is usually a thin abstraction and the freedom to swap.
Get the free playbook
13 pages. No fluff. The actual workflow Andreas and Mike use with the founders and product teams they work with every day.
Get the free playbook
6 pages of frameworks for integrating AI into your product without burning cash or stalling execution.
Need a second opinion on your AI bet?
Book a free 30-minute call with Andreas. No pitch — just a sanity check on what you're building, where the cost is going, and whether the AI part is doing the work it's meant to.