Leboncoin builds Ada, an internal Claude-on-Bedrock chatbot with RAG assistants over Confluence and Backstage, then phases it out in favour of ChatGPT Enterprise with EU data residency
French e-commerce platform Leboncoin built Ada from late 2023 so employees could use generative AI without exposing sensitive data to public LLM services. It started as a Claude chatbot on AWS Bedrock after self-hosted Llama 2 proved harder to run and more expensive, and grew into specialised RAG assistants integrated into Slack. Leadership phased Ada out at the end of Q1 2025 and moved to ChatGPT Enterprise with EU data residency.
Overview
French e-commerce platform Leboncoin built Ada from late 2023 so employees could use generative AI without exposing sensitive data to public LLM services. It started as a Claude chatbot on AWS Bedrock after self-hosted Llama 2 proved harder to run and more expensive, and grew into specialised RAG assistants integrated into Slack. Leadership phased Ada out at the end of Q1 2025 and moved to ChatGPT Enterprise with EU data residency.
This entry has 13 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
In late 2023 Leboncoin's data science and machine learning teams wanted to explore LLM capabilities for employees without exposing sensitive data to public LLM services.
The solution
The team first compared self-hosted Llama 2 on AWS with Claude via AWS Bedrock and chose Bedrock. Ada then grew into specialised assistants: classic RAG over a Postgres vector database for Confluence, OpenSearch lexical retrieval with a reranker and keyword rephraser for Backstage, and full-context loading for policy and organisational-chart data. The assistants were integrated into Slack. At the end of Q1 2025 leadership decided to phase Ada out in favour of ChatGPT Enterprise with EU data residency.
Reported business value
The source reports no cost savings or adoption figures for Ada. It describes Ada as a safe learning environment for teams new to LLMs. For the Backstage assistant, a keyword rephraser raised context relevance from 0.63 to 0.73 and returned the correct source link in 70% of cases. Ada was ultimately phased out because a small team could not scale to meet internal demand for assistants.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other e-commerce entries in the register.
Foxintelligence Enhances Ecommerce Insight Using AWS and Generative AI
Foxintelligence by NielsenIQ, the largest ecommerce measurement and consumer analytics company in Europe with around 5 million active online buyers tracked, uses Amazon SageMaker to build, train, and deploy its machine learning models and is exploring Amazon Bedrock to access foundation models, fine-tune them, and do prompt engineering, reducing time to market for generative AI innovation. As a company handling consumer personal data, Foxintelligence relies on AWS security features to comply with the EU's General Data Protection Regulation (GDPR) and other regional regulations as it expands globally, with advice from the AWS engineering team on new compliance features.
ElasticRun helps small businesses improve supply chain with Databricks
Indian B2B e-commerce platform ElasticRun rebuilt its data infrastructure on Databricks with Delta Lake, Spark Declarative Pipelines and MLflow to manage over 10,000 machine learning models for supply chain and demand forecasting, cutting data pipeline slowdowns by 90% and IT costs by 33%.
Zalando builds an LLM proxy, CLI and risk-based PR approval bot for agentic engineering across 250+ engineering teams
Zalando's ML platform team deployed a LiteLLM-based API proxy in January 2024 giving engineers access to OpenAI, AWS Bedrock and Google Vertex models, plus a chat UI, a pydantic-ai CLI, a shared agent skill collection and governance via its Tech Radar. A risk-based PR approval bot auto-approves the 33% of PRs rated low-risk, which the source says reduced PR lead time by 20-40% compared with all PRs.
Rakuten accelerates development with Claude Code
Rakuten, a large Japanese ecommerce company, uses Claude Code to automate coding tasks across its engineering teams, reducing time to market for new features from 24 days to 5 days and achieving 7 hours of sustained autonomous coding on a complex open-source refactoring project. Rakuten also deployed Claude Managed Agents across product, sales, marketing and finance, plugging into Slack and Teams for non-engineers to complete tasks.
Was this helpful?
Your feedback helps us improve our use case database