> It's easier to win a habit than change one
Shopify Shipping's real competitor was inertia. New merchants with no shipping habit came fast. Merchants who already shipped elsewhere came too, just far more slowly.
All Posts
> Not every AI feature has to pay for itself
Before deciding how to charge for an AI feature, ask whether it should make money at all. That depends on whether it feeds your core product.
> A low-stress mode for Google Maps
Maps finds the fastest route. The best route depends on who's driving, and a few minutes is often worth fewer hard decisions.
> Your pricing is the product
How you charge changes how people use what you built, so decide the behavior you want first. Cursor and Cline showed me the difference.
> The AI in your product doesn't have to be a chat box
Chat is the obvious way to add AI, and it demos well. The one I keep finding useful is quieter: AI sprinkled through the product, doing a step the user used to have to think about.
> Why I moved my PM automations from Claude Code into Linear
Moving recurring PM checks into Linear made them something the whole team could see and change. How I set up the loops, and what it suggests about where agents belong.
> Architecture linting, as cheap as a typecheck
Encode the correction as a check instead of repeating yourself. It runs on every change while the agent is still working, so the mistake gets caught before you ever see it.
> What I learned watching agents use my tools
Building CLIs, APIs, and MCPs for agents works a lot like building for people. Watch them use it, see where they get stuck, and fix that.
> Every shortcut pulls a block
A Jenga rule from an old office: fix a bug without a test, pull a block. Why the follow-up after an urgent fix gets lost, and why it's easier to keep now.
> What scheduling looks like when agents are the user
Calendly turned availability into a link. But links were built for humans. When agents book the meeting, the whole model changes.