Ecommerce ops · Production

leboncoin uses generative AI to help users write better classifieds ads, driving a 20% increase in inquiries and transactions

The problem

Many leboncoin users suffer from 'blank page syndrome' when writing ad descriptions, and those discouraged by the process post minimal descriptions, creating a vicious cycle of poorly described items that don't sell well and reduce seller engagement on the platform.

First attempt

Early AI-generated descriptions were too verbose and formal, reading more like product catalogs than authentic leboncoin ads, and failed to match the platform's natural, concise conversational tone.

Workflow diagram · grounded in source
1
User uploads photos and details
trigger
“Upload your photos, fill in a few basic details about your item, and watch as AI crafts a description that captures everything important.”
2
AI generates structured description
ai_action
“The algorithm considers your photos, title, and item details to generate relevant, structured descriptions that feel natural and engaging.”
3
Seller reviews and edits
human_review
“Sellers maintain full control: they can tweak the text, add personal details, or start fresh if they prefer.”
Reported outcome

Ads using the AI description feature see a 20% increase in both inquiries and completed transactions, and the feature earned leboncoin the Grand Prix Favor'i e-commerce grand prize for innovation in March 2025.

Reported metrics
inquiries on ads using AI feature20%
completed transactions on ads using AI feature20%
Seller time savingssave time
Reported stack
Claude HaikuAWS Bedrock
Source
https://medium.com/leboncoin-tech-blog/from-blank-page-to-perfect-pitch-how-ai-is-transforming-ads-at-leboncoin-eeff51c3bf42
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Ads using the AI description feature see a 20% increase in both inquiries and completed transactions, and the feature earned leboncoin the Grand Prix Favor'i e-commerce grand prize for innovation in March 2025.

What tools did this team use?

Claude Haiku, AWS Bedrock.

What results were reported?

inquiries on ads using AI feature: 20%; completed transactions on ads using AI feature: 20%; Seller time savings: save time (source-reported, not independently verified).

What failed first in this deployment?

Early AI-generated descriptions were too verbose and formal, reading more like product catalogs than authentic leboncoin ads, and failed to match the platform's natural, concise conversational tone.

How is this ecommerce ops AI workflow structured?

User uploads photos and details → AI generates structured description → Seller reviews and edits.