I'm Cyrille, with 18+ years across SaaS, BI and analytics. I connect product analytics with practical AI engineering: agentic systems that run locally, use MCP to reach files and tools, and keep sensitive data private and off the cloud.
A repeatable loop: understand people, measure behaviour, decide with evidence, ship with the team, then automate what can be automated, privately.
Every product decision starts with a real user problem. I run user research and onboarding interviews, and place short triggered surveys at key moments in the journey to capture qualitative signal at scale. LLMs help me synthesise raw feedback into themes, which I then check against the data.
I define the KPIs and funnels that matter, instrument the product, and make the numbers trustworthy. PostHog shows how people actually behave, SQL answers the specific questions, and BI dashboards become the single source of truth shared by product and business teams.
Data tells me what is happening; users tell me why. I combine both to rank opportunities, shape the roadmap and test assumptions with A/B experiments before committing the team. As a certified Scrum Product Owner, I keep the backlog small, clear and tied to outcomes.
I work side by side with design and engineering: clear problem statements, acceptance criteria and fast feedback loops. I'm comfortable with API integrations and with removing friction in flows such as onboarding, so improvements ship iteratively and are measured after release.
I start with step-by-step automation, then move to agentic workflows: I give the AI an objective and instructions, and it adapts when a step fails or a result varies. Local LLMs with LM Studio and sandboxed MCP servers keep sensitive data on my machine. See how it works.
Classic automation follows fixed steps and stops when reality differs. An agentic workflow automates the instructions, not just the steps. I give it an objective. When a step fails, a result varies or something blocks the way, it reasons about it, tries another route and decides on its own, until the objective is reached.
Green: open source, self-hosted. Orange: fair-code, paid cloud.
Before an AI agent writes a single line, I write the documents it needs. Six short, focused documents turn an idea into a specification an agent can follow, which keeps the build coherent, testable and easy to change.
The problem, the target users, goals, scope and success metrics. It states what we build and why, and just as importantly what we do not build, so the agent doesn't invent features.
The stack, architecture, integrations, security and performance constraints. It fixes how the product is built, including privacy-first choices such as local models when data is sensitive.
Every user journey mapped end to end: entry points, screens, decisions, empty and error states. It is the product logic written down before any interface exists.
Layout, components, colours, typography, spacing and accessibility rules. A shared design language keeps AI-generated screens consistent instead of different on every prompt.
Entities, relations, endpoints and permissions. A clear data model is the foundation the agent builds on, and the cheapest place to catch design mistakes.
Small, ordered tasks with acceptance criteria and test checkpoints. The agent builds one verified step at a time, and I review each result before moving on.
Then I build with Claude Code, MCP servers and agent skills, using these six documents as the shared context for every session.
Great products come from a steady cycle: measure clearly, observe real user behaviour, ask the right questions, and ship improvements. AI speeds up finding patterns, while SQL and product sense validate them.
I use PostHog and SQL to turn behaviour into roadmap priorities, and I build the local AI tooling that supports the work: local LLMs, MCP tool layers and private agent workflows.
Qwen3.5 9B running offline in LM Studio with a 100k+ token context and sandboxed MCP servers for memory and filesystem access. Zero telemetry.
Improved UX and conversion funnels for company registration and invoicing SaaS for French auto-entrepreneurs. Led onboarding research and redesign, integrated the INPI Guichet Unique API (the French government portal for company formalities), built dashboards in Omni BI (a business intelligence platform) and used LLMs to speed up user research.
Dealer invoices, incentives and financial reporting across Nordic dealer networks, plus KPI tracking, forecasting and dealer benchmarking.
Operational dashboards and data-warehouse optimisation, forecasting and workflow improvements for content moderation teams, and product innovation in fraud risk detection.
I prototype and test AI ideas hands-on, and I keep sensitive data on my own machine. Local models for private data, Claude for complex reasoning and code, MCP to connect both to files and tools. See the offline pipeline project.
Logos belong to their respective owners.
Hands-on work in AI infrastructure and product.
Enterprise AI doesn't always have to rely on expensive cloud APIs or risk data exposure. For my latest project, an automated pipeline to securely process and structure highly sensitive document data, data privacy was priority number one.
To achieve this, I deployed a fully offline AI environment optimized for advanced LLM tool use:
Running open-source reasoning models (like Qwen) locally inside LM Studio, using hardware acceleration (CUDA offloading on a dedicated GPU).
Configured the Model Context Protocol (MCP) as the central nervous system, giving the local LLM autonomous, secure access to local file systems.
Engineered robust system prompt architectures so the model can independently parse, self-correct and format unstructured text without sending a single byte of data to external servers.
Running local LLMs is no longer just a hobbyist setup. With the right hardware and protocol architecture, it's a powerful, cost-effective and secure production alternative for businesses.
What are your thoughts on running local MCP setups vs. cloud infrastructure?
Let's connect →Product work on the invoicing software of portail-autoentrepreneur.fr, used by French auto-entrepreneurs. I improved UX and conversion funnels, redesigned the invoicing process flow and UI, led onboarding research and redesign, and used data analysis to improve CSAT.
I spent days collaborating on a project close to my heart: supporting my daughter and her high school team with their Young Enterprise company (UF-företag).
Together, we built and launched DoggyCompass, a dedicated web application designed to help dog owners track and structure their dog's daily training, progress and consistency.
By combining entrepreneurship with modern web development, we transformed their vision into a functional digital product. For me, it has been an incredibly rewarding experience to mentor the next generation of innovators and bridge the gap between business ideas and tech infrastructure.
