Using AI in apps
Notes on where AI helps inside an app, where a plain rule does the job better, and how we check AI output before anyone relies on it.
How do we decide where AI belongs in an app?
We use one test across all five of our apps: AI should take real work off the person using the app and leave them in charge of the result. If it only adds a feature nobody asked for, it stays out.
OwnSites writes the first draft of a whole website from one sentence, and the owner reviews and changes every page. ProfVault reads job application forms and fills them from stored documents, and the applicant checks every field before submitting.
Brandreel drafts a script and lays out the scenes of a brand film from a short brief, then the person directing it changes any scene in a live preview before anything is rendered. In each case the AI does the slow first pass and a person makes the decisions.
What happens when AI gets something wrong?
We plan for it. Homeroom's reading passages pass a set of rules, then a second model answers the questions without the answer key, and a parent approves each passage before a child sees it. Where rules are predictable, instant and free, as with Homeroom's worksheets, we use rules instead.
If your idea includes AI, the posts below show how we find the part where it earns its place.

Your customers may never leave the chat. Here is how to show up there
AI assistants now show calculators and forms right inside the answer, so customers can finish a task without visiting you. Here is how to stay in...

AI agents are starting to use your app. Is it ready?
Google’s new Gemini agent works across business tools and any MCP server. Here is what makes an app usable by an AI agent, and how we build for it.

Small businesses are building AI faster than they can manage it
Small businesses are no longer just trying AI. They are building with it. A Pax8 survey published this week of 1,150 small business leaders in the...

AI agents are at work now. Checking them is the new job
For the last two years most AI agents lived in pilots and demos. That has changed. AI agents now answer customers, sort leads, fill in forms and...

A new AI release every day: keep up or fall behind
Hardly a day goes by without a new model, a new feature or a new tool from one of the big AI companies. And people are not just reading about them....

AI didn't take our work. It sped it up
We expected AI to do the work and leave little for people. Instead the pace went up: more security fixes, more updates, more rules, and more to build.

Where AI earns its place in an app
A look at where AI earns its place across five apps, including OwnSites, ProfVault, Homeroom and Brandreel, and where rules do the job better.