ecommerce_ops · ecommerce · workflow
leboncoin uses generative AI to help users write better classifieds ads, driving a 20% increase in inquiries and transactions
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.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User uploads photos and details
The user uploads photos and fills in a few basic details about their item to start description generation.
Tools used
Claude HaikuAWS Bedrock
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.
What failed first
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.
Results
Time savedsave time
Volume20%
Grounding & classification
Source type: technical build writeup
21 fields verified against source quotes.
content generationproduct catalogbuilder submittedfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedecommerceconversion increasetime savedtechnical build writeupecommerce opsmarketing opsai draft human approval