← All modules
Documentation Blog Sign in to your licenses Contact
codingrow.com — Human thought, digital logic. AI catalog content · Magento 2

AI Babel Enchanter

AI rewrites your product texts into rich, persuasive copy and translates them into any language, for every store view. It automatically builds cross-sell and related products, choosing only real SKUs from your catalog — no hallucinations. It handles SEO for you: url_key with 301 redirects, JSON-LD and hreflang. Works with Hyva and Luma. Risk-free: preview before you spend, undo anytime.

See it running on a live store

Explore the admin, run a dry-run preview and see AI-generated cross-sell on our public demo — no install required.

Open the live demo
€799.00 + VAT
Indicative total, incl. Italian VAT: €974.78 — the exact amount is calculated at checkout and is waived for EU business buyers with a valid VAT number (reverse charge).
one-time · per domain · 12 months of updates
Free one-time · per domain · 12 months of updates

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Instant delivery: license key and download link by email right after checkout.

One license activates one production domain (staging and dev environments are free).

Includes 12 months of updates and priority support.

30-day money-back guarantee — no questions asked.

AI Compare — pick the best model on evidence

Don't guess which AI to trust with your catalog. AI Compare runs several models on your own sample products — a dry-run, nothing is written — lays the results in a matrix, and lets an AI judge (or a whole panel) score them side by side on quality, speed and cost, then names a winner.

AI Compare: the model matrix and the judge's verdict — quality, time and cost side by side, winner highlighted.
AI Compare: the model matrix and the judge's verdict — quality, time and cost side by side, winner highlighted.

The AI cross-sell & related-products generator for Magento 2

AI Babel Enchanter fills Magento's native related, cross-sell and up-sell fields automatically — choosing only real products that already exist in your catalog. It looks inside the product's own categories and sibling categories, and optionally at complementary items mentioned in the improved text. Three independent toggles, zero hallucinations.

Every suggested link is validated against your catalog before it is written. If a SKU does not exist, it is never used — the AI cannot invent products.
AI-generated related, cross-sell and up-sell mapped to real catalog SKUs.
AI-generated related, cross-sell and up-sell mapped to real catalog SKUs.

From thin supplier text to rich, on-brand copy — in every language

Most catalogs ship with dry, one-line supplier text. AI Babel Enchanter rewrites each product into rich, persuasive, on-brand copy — then translates it into the language of every store view.

Before

Curved Chestnut Chest — Solid mango wood, hand-painted, 1 drawer.

After — improved

A statement piece that turns a hallway into a welcome. The Curved Chestnut Chest is carved from solid mango wood, its front hand-painted with warm chestnut tones that age beautifully. A single deep drawer glides smoothly, keeping keys, gloves and everyday clutter out of sight while its sculpted silhouette does the talking.

After — translated (Italian store view)

Un pezzo d'arredo che trasforma un corridoio in un benvenuto. La Cassettiera Curva in Castagno è intagliata in legno massello di mango, con il fronte dipinto a mano in calde tonalità di castagno che invecchiano splendidamente. L'unico ampio cassetto scorre morbido e tiene chiavi, guanti e piccoli oggetti fuori dalla vista, mentre la sua silhouette scolpita parla da sola.

Translation runs per store view, into any language in the world — it follows each store's locale, so it is never limited to a fixed set of languages.
The content grid: track improved and translated copy across products and store views.
The content grid: track improved and translated copy across products and store views.

One profile, many steps

Each profile chains several steps in sequence. The text is improved once, then translated into the languages of your stores — efficient and consistent, because every language starts from the same polished source.

1

Improve in the source language

The AI rewrites the product into rich copy in your base language — for example, improve the description in Italian.

2

Translate to your next store view

The improved text is translated into the target locale — for example, translate to English — matching the right store view.

3

Repeat for every language

Add as many translation steps as you have stores — translate to French, German, Spanish and more — all from the same improved source.

Because the text is improved only once and then translated, wording stays consistent across languages and you avoid paying to rewrite the same product again and again.

Tell the AI who your shop is

Create one profile per supplier or catalog segment, then give it a persona prompt — a short brief that tells the AI your tone of voice and expertise. The same catalog can sound completely different depending on the profile you apply.

Furniture profile: "You are an expert in handcrafted furniture. Write in a warm, evocative tone that helps the customer picture the piece in their home."
Spare-parts profile: "You are a spare-parts technician. Write in a dry, precise tone focused on compatibility, dimensions and specifications."
Profiles: one persona prompt per supplier or segment, applied across the catalog.
Profiles: one persona prompt per supplier or segment, applied across the catalog.

Preview without risk

Try any prompt on a sample product without writing a single change. You see the raw AI response and a rendered preview of exactly how it will look on the storefront — including the Google snippet.

Dry-run: rendered preview and Google snippet before anything is written.
Dry-run: rendered preview and Google snippet before anything is written.

Undo anything

Every write is reversible. AI Babel Enchanter takes a snapshot before it changes a product, so you can roll back to the original state at any time — texts, url_key and 301 redirects, and product relations included.

100% reversible: if you do not like a result, put the product back exactly the way it was — from a single click or via CLI.
Restore original: bring products back to their pre-AI state at any time.
Restore original: bring products back to their pre-AI state at any time.
Review and edit AI content before or after it is applied.
Review and edit AI content before or after it is applied.

See it running on a live store

Explore the admin, run a dry-run preview and see AI-generated cross-sell on our public demo — no install required.

Open the live demo

SEO built in

Good copy is only half the job. AI Babel Enchanter keeps your catalog technically sound for search engines as it rewrites and translates.

Never stuck on credits

If your AI provider runs out of credit, AI Babel Enchanter does not waste attempts or lose your queue. It pauses cleanly, emails you, and resumes on its own or with a single Resume click.

Nothing is dropped and nothing is duplicated: the queue picks up exactly where it left off.
The Queue page: pause, resume and track every AI job.
The Queue page: pause, resume and track every AI job.

Multi-provider, your choice

Bring your own AI provider for writing, and choose how you translate. Pick the model that fits your budget and quality — and switch anytime.

Choose your model and compare costs before you run — see the cost calculator in the documentation to estimate a full-catalog run.
Run and automate from the command line for large catalogs and cron jobs.
Run and automate from the command line for large catalogs and cron jobs.

Requirements

Magento 2.4.x (Open Source or Adobe Commerce), PHP 8.1 or newer, and an API key from at least one supported AI provider. Works with Hyva and Luma themes. Composer install, no core changes.

Documentation

Full setup and usage docs cover installation, profiles and persona prompts, the improve/translate pipeline, cross-sell generation, dry-run preview, rollback, the Queue, provider setup and the cost calculator.

→ Read the full documentation

Money-back guarantee

Not satisfied within 30 days of purchase? Request a refund yourself from your account area (codingrow.com/login), no questions asked. The refund is processed instantly, automatically, and the license is deactivated upon confirmation.

Changelog

Every release is listed here so you always know what changed.

v3.1.0

Every operation is now fully tracked: if the relations (cross-sell) step comes back empty or fails, the product is flagged as partial in the queue — with the real reason — instead of failing silently, and you can re-run just that step. New force re-run to re-apply a corrected prompt to already-processed products (it restores the original text and regenerates). Failover is now yours to control: a per-step toggle, a per-credential "Use for failover" flag to keep costly models out of the automatic fallbacks, and drag-to-order priority. And categories are now set PER GROUP, so a single profile can cover several suppliers or sections, each with its own categories and rules.

v3.0.0

The single provider becomes a reusable AI — Models pool with automatic cross-provider failover, and the model and prompt are chosen per pipeline step. New AI Compare bench: run several models on your own sample products and let an AI judge — or a whole panel — score them side by side on quality, time and an indicative cost, so you pick the best model for your catalog on evidence. Also adds a per-AI Max tokens control (no more truncated or empty output), the real provider error shown in the queue, a live formatted preview inside the product page, and a clear-queue button.

v2.2.0

Duplicate-free SEO titles (always on): when the AI regenerates product titles, each title is guaranteed unique across the catalog. The model receives a small sample of the titles already used by products in the same category (so it varies the wording instead of repeating the same formula) and a deterministic uniqueness check guarantees that no two products share the same title — retrying or, if needed, adding a distinctive product detail. Stays cheap even on very large catalogs (only a sample is sent, never the whole catalog). Plus queue throughput controls: configurable run budget/batch and the babel:run --drain flag to clear the whole queue in one go.

v2.1.0

Title regeneration from the description: a new per-step option rewrites the product title (name), synthesised from the description (or short description, or both), with a free-text title instruction. The 'title-only' mode sends the description as read-only context and rewrites just the title — ideal for huge catalogs with uniform titles, at minimal cost. The new title updates the url_key with a 301 redirect.

v2.0.0

First public release: profiles pipeline (improve + translate to any language per store view), AI cross-sell/related/up-sell from real SKUs, dry-run preview with rendered output, full rollback, Queue with credit circuit-breaker, multi-provider, SEO url_key/301/JSON-LD/hreflang.

Frequently asked questions

What does AI Babel Enchanter do?
It rewrites product texts into rich, persuasive copy and translates them for every store view using AI.
Can it build cross-sell and related products?
Yes, it can build cross-sell and related-product links from the catalog.
Which AI providers are supported?
It supports multiple LLM providers, configurable per operation.