Why we built Glossem
Every product is mostly words. Button labels, error messages, onboarding text, dialog confirmations, the empty-state copy that nobody else thinks about. Whether someone understands your product the first time they open it usually comes down to those words.
The problem is the words live inside code.
They sit in JSX files, string constants, database seeds, maybe a translation file if your team got religion about i18n. When a designer wants to rework the onboarding tone, or a writer wants to tighten a batch of error messages so they actually say what went wrong, the work has to go through an engineer. Engineers have other things to do. The copy work sits.
We kept hitting this wall on our own products. The shape of the problem was always the same. A non-engineer with strong opinions about the words. An engineering team that could not get to it for three sprints. Strings collected by hand into a Google Doc, edited there, then re-implemented manually back in code. Slow, error-prone, and demoralizing for everyone.
So we built the thing we kept needing. Glossem scans the repo, finds every user-facing string, presents them in a clean editing interface, and turns the changes back into pull requests. Review still happens in code. The actual writing does not require code.
Static analysis, not AI. We tried adding suggestions for unclear strings early on, and removed it within weeks because the suggestions were sometimes worse than the original. The right person to write your product's copy is somebody on your team. Glossem just gets the strings out of their way.
Related project
Glossem
All your product copy, in one place.
Other notes
We measured our own em dashes, then banned them anyway
The data says density is the tell, not presence, and our prose was already under the human baseline. We adopted the stricter rule regardless. Here is the argument that beat the evidence.
Admissions stopped trying to detect, and started changing the format
Universities are switching off their AI detectors, not upgrading them. The interesting part is what they are replacing them with, and what it asks of a seventeen-year-old.
Who supplied the judgment
The provenance conversation has moved from whether a machine wrote something to who decided. We have been shipping an answer to that question, per product, in public, for a while now. Here is what it cost us to keep it honest.
We do not know how many people use it
Privacy-first is the most crowded claim in mobile right now. Ours cost us the ability to answer the first question anyone asks about a product, and we would rather describe that cost than the feature.
The gate that passed by never running
We spent a week building checks that guard our writing and our code. Four of them reported clean while checking nothing at all. Every one was found by running something, and none by reading the code.
Why we built Tennis Tutor
A junior player gets an hour of correction a week and then practises for six. The scarce thing is not court time. It is someone watching closely enough to tell you what you actually did.
Why we built Myeiyo
Chore apps either turn kids into tiny investors or turn chores into a video game. Neither matches what actually happens in a house. We built the one that does.
The decisions that don't iterate
Most things you build are reversible. A few are not. Telling them apart is harder than it sounds, and getting it wrong is what most software regret turns out to be.
What 'honest software' means in practice
We use the phrase a lot. It is easy to say. It is harder to specify.
Why we built Vyzrly
College admissions has always been a black box. We wanted to make it a little more honest.
When AI is the wrong tool
The reflex to reach for AI on every problem is a symptom of taste failure, not technical sophistication.
Why we built USACO Tutor
Competitive programming builds a kind of thinking that matters. We wanted to make that more accessible.
Why we built ChessWarp
Every chess app asks you to find the best move. In real games, nobody tells you there is one. That gap is where most club players are stuck, and it is what we set out to fix.
Why we built Break the Test
The SAT has seven versions in circulation. Serious students burn through them in a month. The bigger problem is that even unlimited practice would not fix the thing that actually costs them points.