Working Surfacelink · 19 Sep · 02
02
A small robot builds a model house at a workbench in three fixed stages, first a tray of matching tiles and trim, then walls and roof, then the cellar, while a figure seen from behind, the back of the head showing, sets ready-made locks and a letterbox from a crate beside the bench before the robot starts, the whole scene drawn with wide empty margins on every side.
Product Talk

Creating Aha! Builder: Concept to Code, No Engineers Required

Teresa Torres with Brian de Haaff, Chris Waters and Sarah Moisan-Thomas · 17 September 2026

Company story · prototyping · roles · Changing roles

Read the original
Takeaway

Aha!, a maker of product-planning software, built an AI app builder for product managers that creates a design system first and uses ready-made parts for sign-in and data.

Summary

The company Aha! makes software that product managers use to plan products, and its new AI tool, Builder, lets them create working apps without engineers. Teresa Torres, who hosts the podcast Just Now Possible, interviewed chief executive Brian De Haaff, chief technology officer Chris Waters and product manager Sarah Moisan-Thomas. They explain which parts of an app the AI writes and which stay fixed.

Key points
  • The builder works in fixed stages: it creates a design system, then a prototype, then the working application. The team says this gives better results than a single open-ended chat prompt.
  • Sign-in, single sign-on, database access and email are ready-made components, not code the AI writes. The team says this lowers the cost of each build and makes those parts reliable.
  • The first version ran each app in its own container and cost too much to scale, so the team rebuilt it to run many customers' apps on shared infrastructure.
  • The guests argue that as building gets easier, a product manager's value lies in knowing what to build. This is a company describing its own product, and only the show notes are open to read.
Implication

A team that lets AI build apps can decide in advance which parts the AI may generate and which parts must stay the same in every build. This is an inference from Aha!'s own account of its product.

Suggested actions
Product

Build AI-generated apps in a fixed order, design system first, then prototype, then working app, and use ready-made components for sign-in, databases and email.

Design

Have an AI app builder settle the design system as its first stage, before it generates any prototype.

Derived by Working Surface from the article. Source line: produces better outcomes than a single open-ended chat prompt

Source issue

19 September 2026: AI makes prototypes, apps and comparisons cheap, and their worth depends on what is settled first or can be checked.