482 products with thin copy
For Shopify merchants · AI-readable catalog
Your weak product descriptions, rewritten.
One click to apply. 30 days to undo. You approve every word. Legible grades every product description against the six signals AI shopping agents read, then rewrites the ones that aren't landing.
trylegible.com/store/acme/readiness
62
/ 100
material, gender, audience missing
702 images unlabeled
product_type consistent
18 near‑dupes to review
fr-FR partial, de-DE missing
- Product content only. Legible writes product descriptions, structured metafields, and taxonomy attributes — only when you click Apply. Never prices, inventory, images, alt text, or customer data.
- Pre-apply diff. You read the exact before/after text and approve every change before it publishes.
- Hallucination scan. Every rewrite is screened for unsupported claims, numbers, and brand names before it reaches you.
- 30-day Undo. Revert any change for 30 days, with a conflict guard if Shopify drifted in between.
Why now
Shoppers aren't browsing anymore.
They're asking agents.
ChatGPT, Perplexity, Rufus, Gemini, Claude — each one is turning into a storefront. When a buyer asks "find me a linen shirt, breathable, under $80, ships to Paris," the agent reads your product data and decides in milliseconds whether to surface you. Legible tells you, line by line, where that decision goes wrong.
We don't promise an agent will pick you — nobody honestly can yet. We make sure that when it reads your catalog, it can understand and rank you. That's the part you control. That's the part we fix.
6pillars
The signals agents actually read before surfacing results
~1second
Average time an LLM spends evaluating a candidate product
30day undo
You approve every write. Undo any change for 30 days, with a conflict guard.
The six core pillars
What an AI agent sees
when it reads your catalog.
Critical · fixes first
Descriptions that actually describe.
We score every product description with Claude Haiku against a rubric that mirrors what LLMs look for: concrete attributes, use cases, fit, material, what problem it solves. Fluff gets a low score. Copy that sells to a human but fails an agent gets flagged.
- Per-product quality score 0–100
- Distribution chart across your catalog
- Ranked list of the products whose rewrites move your score most
Critical · first impression
Images on every product an agent ranks.
Multimodal shopping agents look at your product images before they recommend you — and a product with no image, or only a single thumbnail, reads as low-effort and gets skipped. Legible measures image presence and coverage across your catalog: which products have zero images, which have just one where the category expects several, and where the gaps cost you the most.
- Per-product image-presence and count check
- Flags products with no image, or thin coverage for their type
- Ranked by score impact, highest-traffic gaps first
High impact
Metafields an agent can actually query.
Agents don't read prose to find sizing. They query structured fields. Legible audits your metafield coverage across the namespaces AI shopping systems actually pull from — material, audience, gender, origin, care — and shows you exactly which products are invisible on each.
- Per-product metafield-presence check
- Flags products missing structured attributes
- Ranked by score impact
Silent killer
Near-duplicates, grouped and ranked.
We embed every product with Voyage AI's voyage-3-lite and cluster variants, re-releases, and accidental duplicates. Agents punish catalogs that look cluttered — you'll know which SKUs to merge, which to retire, and which to just re-name.
- Confidence score per cluster
- Near-duplicate, re-release, and color-alias detection
- Deep-link into Shopify admin to action each group
Accessibility + agents
Alt text that does double duty.
Alt text matters for screen readers. It also matters for multimodal agents that caption your images before ranking you. We find every unlabeled image and report coverage per product, so you know exactly which gaps to fix for both audiences.
- Per-image alt-text coverage
- Highest-impact gaps surfaced first
- WCAG-aligned
Structure
Taxonomy that doesn't contradict itself.
"Tee", "T-shirt", "Tshirt", "Graphic Tee" — four product types, one actual thing. Legible flags products whose product_type field is missing or out of step with the standard Shopify taxonomy that agents rely on.
- Product-type coverage
- Standard taxonomy mapping checks
- Per-product fix list
Global reach
Multilingual, audited honestly.
If you ship to France, an agent querying in French will read your fr-FR copy — or fall back to your English, or skip you. Legible checks the translations you already have, flags placeholder strings and missing locales, and shows you where each market is exposed.
- Locale coverage per pillar
- Detection of machine-translated-and-forgotten copy
- Per-market readiness score
How it works
Score in five minutes
— then apply rewrites on your schedule.
-
Install from Shopify
One click install. Legible writes product descriptions, metafields, and taxonomy attributes — and only when you click Apply on a specific suggestion. Every change is undoable for 30 days. Your catalog stays yours.
-
We read your catalog
Products, variants, metafields, translations, images. First pass runs in minutes for most stores, background sync after that.
-
Fix in priority order
The opportunity list is ranked by how much each fix moves your score. No spreadsheets, no guessing — just the next best thing to do.
See it in action
A silent, captioned walkthrough
— score, read, and rewrite, end to end.
I built Legible after watching my own store disappear from AI shopping results while competitors with worse products kept showing up. The difference wasn't quality — it was data legibility. Six specific signals, the same six every agent reads. This app scores them, in order of what matters.
Hamza Ziouine
Founder · Legible
Pricing
Monthly or yearly
— 14-day free trial, no credit card.
One optimized product description from a freelancer costs around $100. Legible tells you which products to fix first — from $49 / month (or $490/yr, 2 months free).
Starter
$49/ month
or $490/ year — 2 months free
Up to 2,500 SKUs
- All six core pillars scored
- AI description scoring + AI-generated rewrites
- One-click Apply with 30-day Undo
- 500 description writes per rolling 24h (reverts exempt)
- Duplicate detection (embedding-based)
Pro
$89/ month
or $890/ year — 2 months free
Up to 10,000 SKUs
- Everything in Starter
- Larger catalog cap — up to 10,000 SKUs scored
- 2,000 description writes per rolling 24h (reverts exempt)
- Multilingual audit (target-locale translation coverage)
- Priority email support
Business
$199/ month
or $1,990/ year — 2 months free
Up to 50,000 SKUs
- Everything in Pro
- Up to 50,000 SKUs — 5× Pro's catalog cap
- 10,000 description writes per rolling 24h (reverts exempt)
- Direct email line to the founder (hamza@trylegible.com)
Need a larger catalog? Email us →
FAQ
Answers
— before you ask.
Does Legible change anything in my store?
Only when you click Apply on a specific suggestion. Legible writes AI-generated product descriptions and structured product metafields (a subtitle, a care guide, and standard taxonomy attributes), one item at a time, and only after you approve the change. Every 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.
How long does the first scan take?
Most stores complete the first scan in a few minutes. Large catalogs sync in the background and the dashboard fills in progressively — you don't have to wait for it.
Do I need a developer to use it?
No. Install is one click from the Shopify App Store. The dashboard, scores, and opportunity list are designed for merchants — no CLI, no SQL, no GraphQL. If you want to bulk-apply fixes in Shopify admin, a developer speeds that up. V1 itself requires none.
What happens when the trial ends?
You pick a plan to keep using Legible, or the app pauses and prompts you to choose one. Nothing auto-charges — Shopify always confirms the subscription before billing starts. You can cancel anytime from the Apps screen in your admin.
How is the score calculated?
Your score is the average of your core pillar scores — six for every store, plus a seventh multilingual pillar if you sell in multiple languages. Descriptions are usually the highest-leverage fix — they're AI-scored, and Legible can rewrite descriptions, metafields, and taxonomy for you on approval. The breakdown is visible per product on every report.
What data leaves my store?
Product text and image URLs are sent to Claude Haiku (Anthropic) for scoring and Voyage AI for embeddings. 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 sent to any AI processor. Processors are disclosed in our privacy policy and can be switched off in enterprise plans.
What if I have a very large catalog?
Email us (hamza@trylegible.com) — we'll size a plan for you. The Business tier covers up to 50,000 SKUs; above that, talk to us. SSO and a named point of contact are available on request.
Does it work for non-apparel catalogs?
Yes. The pillars are catalog-agnostic — the rubric was built against home goods, electronics, beauty, and food as well as apparel. The same six signals apply across product types.
Audit your catalog.
Fix what's costing you sales.
You approve every write · 14-day free trial · no card to start