About Legible
Built by one merchant, for merchants selling into an AI-agent world.
No investor pressure. No growth-at-all-costs product decisions. Just a tool that tells you exactly what AI shopping agents see when they read your catalog — and rewrites the descriptions that aren't landing, one product at a time, only when you approve.
Hamza Ziouine
Morocco — Casablanca & Rabat
I've been building things on Shopify for a while. Stores mostly — figuring out what sells, what doesn't, why a product that everyone likes can still fail to convert. That hands-on time is what made the problem Legible solves feel obvious to me before it was obvious to anyone else.
Legible is bootstrapped, solo, and built out of Morocco. No office, no team of twenty, no runway pressure to ship features that look good on a roadmap but don't serve merchants. The app exists because I needed it myself.
Why Legible exists
I watched my own catalog disappear.
A while back I noticed a pattern: certain products I knew were genuinely good kept getting passed over by AI-powered shopping surfaces. ChatGPT, Perplexity, agent-style queries in Google. Meanwhile competitors with thinner products kept showing up. I assumed it was ad spend or domain authority or some algorithm I couldn't control.
It wasn't. When I looked closely at the difference between products that got surfaced and products that didn't, the gap was almost always in the catalog data itself. Descriptions that didn't name materials or use cases. Metafields that were blank or inconsistent. Images with no alt text. Duplicate product entries confusing the ranking signal.
Six specific things. The same six things, catalog after catalog. And there was no tool that audited them in one place, scored them honestly, and told you which to fix first. So I built it.
What we stand for
Things we don't compromise on.
- You approve every write. Legible writes back only what you approve — AI-generated product descriptions and structured product metafields (a subtitle, a care guide, and standard taxonomy attributes) — and only when you click Apply on a specific suggestion. Every applied change is logged and independently undoable for 30 days. Alt text and images are never written, and customer data is never accessed. Order data is read only in a data-minimized form — order totals and line-item quantities, never buyer details — to power the before/after sales-impact view, and is never written back. You stay in control of every edit.
- Pricing that doesn't exploit the trial. The 14-day trial is long enough to get a real score on a real catalog and apply fixes across it. If the app doesn't show you something actionable in the first session, you shouldn't pay for it. There's no lock-in, no credit card required to start, and Shopify always confirms before billing begins.
- No venture money, no growth pressure. Legible is bootstrapped. That means no investor telling me to prioritize growth metrics over merchant outcomes.
- Honest scores. The scoring rubric is based on what AI agents actually read when they evaluate a product. Not what sounds impressive in a dashboard. If your catalog scores a 41, you get a 41 — and a clear list of what to fix to raise it.
What's next
The roadmap, plainly.
V1 scores your catalog across six core pillars — seven if you sell in multiple languages — and lets you apply AI description rewrites with one click, every change undoable for 30 days. Here's where it goes from here.
- V2 Deeper bulk workflows. Description rewrites, structured metafields, and category/taxonomy attributes already write back today — each with the same per-change review, pre-apply diff, and 30-day Undo. V2 extends bulk apply across whole collections and adds richer queue controls on top.
- V3 Competitive benchmarks. See how your catalog's readiness score compares to other stores in your category. Know whether your 74 is strong or middle-of-pack for outdoor apparel, home goods, or wherever you compete.
Full public roadmap at trylegible.com/roadmap.
Get in touch
Talk to the person who built it.
I do all the support myself. If you have a question about whether Legible is right for your catalog, want to walk through your score, or just want to tell me something is broken — I'm the one who answers.