← Back to work
Fitness · Europe

European supplier of fitness equipment

From hand-written product copy to SEO-optimised content in six languages.

± 2 weeks
to working AI generation
3+ weeks
to writing back to the product information system
82
text fields per product

The question

A new product has to reach the sales channels fast, with consistent content and without anyone losing control of quality and substance.

Before

High-end fitness equipment doesn't sell on half-finished copy. Yet every new product from this supplier started as an empty shell in the product information system. Each product is waiting on 17 Dutch master fields and 65 translated fields in five other languages to be filled: titles, descriptions, bullet points and channel-specific copy. As long as those fields are empty, the product doesn't leave the building. And every text has to fit the brand, the product group, the language and the requirements of the channel. That copy was written by hand and wasn't optimised to be found for every part of the product. The supplier wanted this faster and more consistent, with copy that also ranks in search engines, but not at the expense of its own editorial control.

What we built

We built a content portal that takes the existing product data as its starting point. AI checks the product benefits against the specifications, writes the Dutch copy and translates it into five languages. Every part of the product, from title and description to bullet points and channel copy, is written with findability in mind. The team keeps its hands on the wheel: they manage the writing instructions, brand style, terminology and rules per product group, and nothing goes back to the product information system until a person has approved the content. For every field you can see which version of the instructions was used, and earlier versions can be restored. Real AI generation was running after about two weeks of building. After just over three weeks, the portal was also writing approved content back to the product information system.

How it works

You see what happens at every step.

  1. 01automated

    Spot new products

    The portal finds new products and collects specifications, product benefits, brand and category. A data check immediately shows which source data is missing.

    Role of AI, automation and people: Automation collects the data; the team chooses which products are processed.

  2. 02AI + person

    Put the benefits to the test

    The product benefits supplied are checked against the specifications: for duplicates, contradictions and clumsy wording. Where benefits are missing, AI can suggest some.

    Role of AI, automation and people: AI (OpenAI) makes suggestions; the editor accepts or rejects them and decides which points go into the copy.

  3. 03AI

    Write the Dutch master

    The portal writes 17 master fields from product data, brand style and the rules per product group, optimised to be found.

    Role of AI, automation and people: AI writes the content. Code handles the fixed HTML structure of the long description and checks such as character limits.

  4. 04person

    Edit and approve

    The editor reads along, adjusts, or has a selected passage written again. Changes and earlier versions stay visible.

    Role of AI, automation and people: A person reviews; AI helps with targeted rewrites.

  5. 05AI + person

    Translate per market

    The content is translated into British English, German, French, Italian and Spanish for Spain, with fixed terminology and instructions per market.

    Role of AI, automation and people: AI translates; the team reviews the translations.

  6. 06automated

    Back to the source

    Only approved fields go back to the product information system. Publishing to the sales channels then runs through the existing process.

    Role of AI, automation and people: An authorised employee of the supplier confirms the action. Automation writes the fields back, within a set daily limit.

Result

One portal where SEO-optimised product content is written, approved, translated and written back: 82 text fields per product in six languages, with its own instructions per brand. The team steers the AI itself through writing instructions, terminology and product group rules, with no developer in between. Every change is traceable, and only authorised employees of the supplier can write approved content back.

1
portal to write, approve, translate and write back
82
text fields per product
6
languages

Yours, and what comes next

On the agreed handover, the supplier becomes the owner of the source code, hosting, database and AI account, including the generated content, prompts and rules. What comes next: feeding search data into what the AI writes. Then the copy doesn't just read well, it gets found too.

More work

Take a look at these too

  • Coinage

    Czechia, Slovakia, Poland

    From unused customer data to a view of every campaign, journey and return.

    All the customer and sales data was in house, but there were no figures to steer on. We built the ETL process, the data models and a secured BI portal, where the team follows campaigns, customer journeys and returns every day.

    3 weeks
    to live
    20+
    employees, every day
  • Sidon Water Benelux

    Benelux, Spain

    From looking for new customers to a large European fitness chain as a client.

    Sidon wanted steady contact with the people who buy its products, in the Benelux and Spain. On LinkedIn, owner Casper Pruijn’s profile grew from 200–300 to almost 8,000 connections, with lead lists from an ICP analysis and our own tool for the network building. We also built the mailing lists and wrote the campaigns per audience. One of their best customers came from the email marketing.

    almost 8,000
    connections, up from 200–300
    20–25%
    reply rate on messages
See all cases

Let's get started

Running into a similar process?