Product descriptions for the SKU catalog (SEO optimization)

An AI agent based on a low-code workflow takes raw product data and turns it into a ready-made SEO description for the SKU card. The editor receives a draft that only needs to be read and adjusted, rather than written from scratch. According to Reactively reports, the cost of a single description drops from £64 to £6.40, while at Fnac Darty draft accuracy stays at 95%.

Specific process steps:

1. The agent retrieves the product card from the CMS or file storage (CSV, XLSX, JSON export from PIM).
2. Normalizes attributes: category, brand, material, size, compatibility, key specifications.
3. Pulls in target keywords and SEO rules for the relevant category.
4. Generates three blocks: a short title/lead, an expanded description, and bullets with specifications.
5. Checks the draft against a checklist: length, keyword presence, prohibited phrasing, tone of voice.
6. Saves the result back to the CMS as a card draft and marks it with the status «on review».
7. A copywriter or category manager reads, edits, and publishes.

What automation does NOT do:

• Does not replace the category manager and editor. The final decision on publishing and product positioning remains with a human.
• Does not verify the factual accuracy of specifications. If there is an error in the source data (incorrect size, incompatible article number), it will end up in the description as well.
• Does not replace a full SEO strategy. The agent writes within the defined rules and keywords, but does not form a query cluster and does not decide which categories to promote.

Automation addresses three e-commerce catalog pain points at once: slow creative output when launching new collections, repetitive routine tasks for copywriters, and manual data entry/copying between PIM and CMS. As a result, the marketing team spends time on editing and strategy, rather than rewriting specifications in their own words.

At the core is a low-code workflow that connects a product data source, an LLM, and a CMS. The architecture is assembled on a workflow engine or similar orchestrator and does not require a dedicated backend for the task.

The technical flow looks like this:

1. Trigger. A new SKU appears in the CMS/PIM or a file with a product batch is uploaded to file storage. The workflow catches the event or runs on a schedule.
2. Context collection. The agent collects product attributes, image links, category, brand, target audience, and keywords from a separate SEO rules table.
3. Prompt preparation. The data is templated into a structured prompt with strict constraints: tone of voice, length, prohibited words, required sections (lead, description, bullets).
4. LLM call. The agent queries the model and receives a draft in the specified JSON format.
5. Validation. The workflow checks length, keyword presence, and absence of hallucinations in the attributes (every number and attribute is verified against the source data).
6. Writing the result. The draft is placed back into the product card in the CMS with a status of "pending review" and the tag AI-draft.
7. Editor notification. The copywriter receives the task in the familiar CMS interface or in a separate queue.

Implementation steps:

1. Week 1. Catalog audit, selection of a pilot category (200-500 SKU), collection of "good" description examples for few-shot.
2. Week 1-2. Setting up access to the CMS and file storage, documenting the product data schema.
3. Week 2. Building the workflow in the low-code orchestrator, first run on 20-50 SKU, prompt calibration.
4. Week 2-3. Validation rules, connecting the SEO dictionary, editor review of the first batch.
5. Week 3-4. Launch on the full pilot category, collecting metrics on edit time and the share of accepted drafts, decision on scaling.

Workflow components:

For scaling to the entire catalog, it makes sense to split the workflow into two queues: a fast stream for new SKUs (event-based) and a batch run for mass regeneration of old descriptions, to avoid hitting API limits and disrupting the editors' review process.

Automation relies on product data already existing in a structured form and being programmatically accessible. Without this, the agent will write polished but reality-detached copy.

What you need for data and access:

• A product catalog in a CMS or PIM with attributes (name, category, brand, key specifications, images).
• API access or export to file storage (CSV/XLSX/JSON) for reading product cards and writing drafts.
• SEO glossary: a table of keywords and rules by category (minimum for the pilot category).
• 20-50 reference descriptions that the team considers "done right" — for few-shot and style validation.
• A tone of voice guide and a list of prohibited phrasings.

What you need from the team:

• A category manager or marketer — the process owner, makes decisions on description structure.
• A copywriter/editor — reviews drafts and provides feedback during the first iterations.
• A technical implementer — sets up the low-code workflow and integrations with the CMS.
• Readiness to work with drafts: the team must accept that an AI description is a draft that gets edited, not published automatically.

Implementation timeline: 2-4 weeks for a pilot on one category (weekend complexity with data ready, up to 4 weeks if the catalog needs to be put in order). Scaling to the full catalog — another 2-4 weeks depending on the number of categories and the quality of source attributes.