Writing
Notes on building AI and SaaS products: how I work, working with founders, and lessons from my own studio products.
Do you need a prototype, an MVP or a production application?
The right deliverable depends on what you need to learn, not on which label sounds most impressive.
Read
The questions I want answered before we discuss features
Drawing on product design, software development and interviewing, these are the questions I want a product conversation to answer before it becomes a feature list.
Read
What you should receive when someone builds your AI application
A working URL is not the whole deliverable, so here is what I think a founder should own and receive when someone builds an AI product for them.
Read
Designing work queues teams actually clear
The design rules I use for operations queues: one definition of done, visible priority, clear ownership, recorded reasons, batch actions for the common case and counts that show whether the queue is shrinking.
Read
Where should an AI agent ask for human approval?
Useful automation needs boundaries: which actions an agent can take on its own, which need approval and what the person approving needs to see.
Read
How I would test a product idea before building the full application
Before investing in the complete product, design a smaller experiment that could genuinely change your mind.
Read
Is this design buildable? What I check before a design reaches code
The checks I run on a design before anyone builds it: every state, real data, screen sizes, roles, accessibility basics, implied interactions and component reuse, and why AI design tools make them matter more.
Read
Your AI feature is cheap to demo. What does it cost to operate?
Why the cost of an AI feature is the cost of a successful result, not a single model call, and what to work out before you add one to a subscription product.
ReadPage 5 of 8 · 60 articles