Context and assignment
Scaling a GenAI chatbot for client advisors.
After an MVP phase, LCL calls on Visian to put into production an AI model for advisors. The chatbot uses OpenAI APIs to generate answers based on internal documents. Industrialisation, LLM optimisation.
The challenge
What was at stake
For LCL, the assignment covered: “Scaling a GenAI chatbot for client advisors”. This kind of programme involves business departments, IT and data teams at the same time: it has to deliver quickly without weakening existing systems, and leave behind practices that hold once the assignment ends.
The relationship
Visian at LCL
LCL is part of the Crédit Agricole group, supported by Visian since 2020 on development, data and generative AI. Crédit Agricole group: 75 assignments across 9 entities since 2020.
Expertise involved: Generative AI, LLM, industrialisation, development.
Deliverables
- Industrialised generative AI use cases
- LLM integration
- GenAI development in Python and Java across the group
Team and duration
Duration, team and scope
- Duration: multi-phase engagement.
- Team: a multidisciplinary Visian team, sized to each phase, covering generative AI, LLM, industrialisation, development.
- Scope: Industrialised generative AI use cases; LLM integration; GenAI development in Python and Java across the group.
Approach
How Visian worked
- Scope: workshops with the departments involved, assessment of the existing set-up, prioritisation and deliverables approved in steering committee.
- Build: delivery in short iterations, shared milestones and project governance with the client teams.
- Handover: adoption support, documentation, skills transfer to in-house teams and move to run.
Results
Measured results
Scope
Methods and technologies
Expertise involved