My skills
From intelligent chatbots to data infrastructure and process automation.
RAG intelligent chatbots
- Custom assistants that work from internal documents (PDFs, emails, knowledge bases)
- Context memory across conversations, answers based exclusively on the indexed documents
- Every response is traceable to its source
- Ideal for customer support, internal assistance or document management
- EU hosting available
LangChainPythonWeb fullstackInfrastructureQdrant
Related projects
Data engineering
- Reliable data collection and transformation pipelines, from zero to production
- Modern tooling: Python, dbt, Airflow
- From connecting new sources to preparing datasets for model training
PythonDBTSQLAirflow
Related projects
AI automation
- Document classification, drafting standard replies, information extraction, automatic summaries
- Agents that orchestrate multiple AI models and connect to existing tools (CRM, APIs, databases)
- Cost control: not all AI providers are equal depending on the task
n8nAPIsQdrant
SaaS development
- From idea to MVP: backend architecture, web interfaces, AI integration, APIs and deployment
- Iterative approach to validate the concept before scaling investment
- Modern stack (Next.js, Python, Docker, ...), delivered as an extensible product
WebMVPDocker
Related projects
Machine learning
- Model trained specifically on business data to outperform generic solutions
- Data preparation, training, evaluation and deployment handled end-to-end
- Use cases: classification, extraction, enrichment, semantic search
- Ideal for companies that already have historical data to leverage
MLClassificationPrédictionData Science
Related projects
Frequently asked questions
- What is the difference between a RAG chatbot and ChatGPT? ▾
- A RAG chatbot answers exclusively from an organisation's internal documents. Unlike ChatGPT, it doesn't generate out-of-context responses and every answer is traceable to its source. The result: no hallucinations on business data.
- Can these solutions be used in a GDPR-compliant way? ▾
- Yes. All integrations can be deployed with European hosting or on-premise, with no data transfer to US servers. Use cases requiring strict GDPR compliance rely primarily on Mistral AI and OVHcloud.
- Can an LLM be useful with limited internal data? ▾
- Absolutely. Modern LLMs work very well with a few dozen well-structured documents. The data engineering phase can also help consolidate and enrich existing data, even when fragmented, before putting it to use.
Let's discuss a project
Get in touch