My daughter has taken up baking to relax. A couple weekends ago, she asked, “Hey Dad, you want to help me bake some cookies?”
The product manager in me jumped into action. I searched up the best chocolate chip cookie recipes and picked one from a famous chef. I printed it out and started rushing around the kitchen, marking off all the ingredients we’d need.
“Hon, we have to run to the store.”
“Dad, it’s been a long week. Let’s just use what we have.”
Forty-five minutes later, we were eating cookies.
What this essay explores
- Frame an AI workflow around a painful manual task before building a full product.
- Build the smallest proof of concept that proves what needs to get built.
- Use existing libraries and templates to avoid spending weeks on commodity functionality.
- Put working software in front of customers early and solve real problems with their data.
- Treat infrastructure limits as launch blockers and build the operational systems to handle them.
- Use onboarding data and customer feedback to find bottlenecks after launch.
- Cook with what’s in the pantry so effort stays focused on what matters.
Key takeaway
How we built and launched GPTcsv.ai in 19 days
