← Back to 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

Source proof for 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

Source-bound proof

Verified source excerpts for every supported field

Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.

13 fields supported

Title

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

quote · high
…al and operational overhead relative to focusing on more user-facing use cases. At the end of Q1 2025, leadership decided to phase out Ada and transition to OpenAI’s platform as the internal assistant foundation. The migration strategy demonstrates thoughtful technical planning. Several Ada…

Description

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.

quote · high
…Production Insights Conclusion and Key Takeaways Overview and Business Context Leboncoin, a major French e-commerce platform, embarked on building Ada, an internal LLM-powered chatbot assistant, at the end of 2023. The project emerged during the GenAI boom when concerns about data security wit…

Company

Leboncoin

quote · high
…Production Insights Conclusion and Key Takeaways Overview and Business Context Leboncoin, a major French e-commerce platform, embarked on building Ada, an internal LLM-powered chatbot assistant, at the en…

Country

France

quote · high
…Production Insights Conclusion and Key Takeaways Overview and Business Context Leboncoin, a major French e-commerce platform, embarked on building Ada, an internal LLM-powered chatbot assistant, at the en…

Industry

E-commerce

classification · high
…ike this one, in your inbox every Tuesday and Thursday. Email address Subscribe Industry E-commerce Technologies · 41 chatbot question_answering summarization document_processing…

Problem

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.

quote · high
…ighted the risks of using public GenAI platforms with sensitive corporate data. For Leboncoin’s data science and machine learning teams, this created both a challenge and an opportunity: how to explore LLM capabilities safely while maintaining strict data controls. The Ada project served multiple strategic purposes beyond just providing an int…

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.

quote · high
…al workflows to access a standalone web interface created unnecessary friction. They integrated Ada’s multiple assistants directly into Slack through custom Slack Apps, meeting users where they already worked. Beyond basic question-answering, they…

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.

quote · high
…ch index. This preprocessing step significantly improved retrieval performance, raising context relevance from 0.63 to 0.73 and returning the correct source link in 70% of cases. With the final setup combining OpenSearch, query rephraser, and reranker, they…

AI capabilities

Generative AI, Conversational AI

classification · high
…xity about this page Summary Leboncoin, a French e-commerce platform, built Ada—an internal LLM-powered chatbot assistant—to provide employees with secure access to GenAI capabilities while protecting…

Technology

Claude, Amazon Bedrock

classification · high
…val complexity entirely while ensuring complete coverage of the knowledge base. All assistants were built on Anthropic Claude models accessed via AWS Bedrock, but the diversity of architectural approaches demonstrates sophisticated think…

Deployment options

cloud

classification · medium
…val complexity entirely while ensuring complete coverage of the knowledge base. All assistants were built on Anthropic Claude models accessed via AWS Bedrock, but the diversity of architectural approaches demonstrates sophisticated think…

Headline outcome

derived · high
…challenges of building custom LLM infrastructure in a rapidly evolving market. The approximately 18-month journey from inception to sunset provided the team with valuable hands-on experience in LLM infrastructure, RAG…

Use case type

Conversational assistant

classification · high
…xity about this page Summary Leboncoin, a French e-commerce platform, built Ada—an internal LLM-powered chatbot assistant—to provide employees with secure access to GenAI capabilities while protecting…
Capture details
Captured
20 Nov 2026, 05:17 UTC
Extractor
fetch-strip@1
Snapshot hash
8afd8915a72a670b456a97e988b0aa80a1b94887efe659213c8da26128ca2337