back_office_ops · ecommerce · workflow

Once Upon a Chat Bot: The Ada Story at leboncoin

leboncoin wanted to leverage LLMs internally but could not use public platforms like ChatGPT due to data security and privacy risks, particularly the risk of confidential or client data being exposed through external services.

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 · Employee submits question
Employees submit questions to Ada through dedicated Slack apps or a standalone web interface.
Tools used
ClaudeClaude 2Claude SonnetAWS BedrockLlama 2PostgresOpenSearchLangsmithAirflowOnyxn8nConfluenceLumappsBackstageRAGChatGPT EnterpriseMCPVespa
Outcome

Ada became a trusted internal assistant before being sunset in Q1 2025. The project delivered significant GenAI expertise to leboncoin's ML team. Transition is underway to ChatGPT Enterprise, with key features being ported via MCP connectors and Custom GPTs.

What failed first

The initial attempt to self-host Meta's Llama 2 on AWS was complex, slow for chat, and more expensive than a managed alternative. A later pilot of Onyx as a replacement was rejected due to infrastructure instability from its Vespa database and limited customization.

Results
Time saved30min to 3min
Volume0.63 to 0.73
Running sinceend of 2023
Source

https://medium.com/leboncoin-tech-blog/once-upon-a-chat-bot-the-ada-story-at-leboncoin-1a4c52000d82

How we source this →

Grounding & classification
Source type: technical build writeup
48 fields verified against source quotes, 1 dropped as unverifiable.
chatbotconversational aiknowledge searchragsummarizationknowledge basepolicy documentbuilder submittedfailure mode describedmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedecommerceaccuracy improvementemployee productivitytime savedtechnical build writeupback office opsit supportrag answering