Product engineering
Developing a concept into a market-ready product, customer-validated solution using agile methodology efficiently, economically, and timely.
Developing a concept into a market-ready product, customer-validated solution using agile methodology efficiently, economically, and timely.
I coded GSM phone software at Nokia, by hand and down to the memory. Here is what each new abstraction layer took away, what it left, and where experience goes now that AI agents write the code.
We’ve been thinking about how we work with AI, with Ilpo writing about cutting our main instruction file in half and Ville on why we built a single AI coding factory.
We cut our main AI instruction file from 463 lines to 199, swapped step rules for goals, and our AI agents got better. Here is what we learned.
This week at A-CX, Ilpo has been writing about a new rule for AI-filed issues, and Ville has been thinking about who owns an AI tool after the pilot.
Our AI agents filed issues nobody needed. How moving the filing rule to the point where every issue is created keeps the backlog worth building.
Happy Canadian Thanksgiving to our Vancouver contingent! We’ve been writing about how one AI code reviewer replaced seven, and Mikko’s Grapevine talk on why so many companies stall with AI is now online.
Seven AI review agents disagreed on what should block a merge. We replaced them with one definition run as two passes, and kept people deciding.
This week at A-CX, Mikko Peltola is speaking in Grapevine, Texas, on what AI is worth building, and Ilpo and Peter have been writing about what a week of racing data revealed aboard a 1976 Swan 47.
Typon is a Swan 47 from 1976. We put a Raspberry Pi below decks for the Rolex Big Boat Series, recorded every instrument reading and every rival that transmitted, and used AI to analyse the week against the boat’s own measured targets. This is how it was done and what…