Stockholm · Senior PM, Product Owner, AI Product, BI & Data

Product built on data,
powered by AI.

Senior Product Manager

I'm Cyrille, a Senior Product Manager in Stockholm. I started at Besedo, a content moderation company for classified ads and dating sites, as Head of Planning, and over eight years moved through BI, business development and operations control. Then came ten years at Betao, on the product team behind solo.fr and portail-autoentrepreneur.fr, mostly onboarding and invoicing with the analytics behind them. In every job I watch how users and teams work and check it in the data before changing the product. On my own time I build agentic workflows with local models and Claude. Sensitive data stays on my machine.

See my work Experience

Projects

Selected projects

Hands-on work in AI infrastructure and product.

AI · Agentic workflow

Radar: collect, structure, score, learn

Keyword search finds a lot, but rarely what really matters. Radar is a reusable agentic workflow. It collects public content, structures it as Markdown, scores each item against clear criteria with evidence, and learns from human feedback. The pipeline stays the same. Only the sources, the profile and the rubric change.

01CollectPublic sources, deduplicated

02StructureClean Markdown, one schema

03ScoreRules + similarity + LLM judge, evidence verified

04LearnHuman feedback becomes labels

What changes per use case: configuration, not code

	Jobs Live	Sales leads Planned	Product feedback Planned
Collect	Platsbanken + a second job board	Job postings, company registers	App reviews, support tickets
Profile	A resume	Ideal customer profile	Product roadmap, known issues
Score	Role requirements	Firmographics + hiring signal	Severity + users affected
Learn	Applied / disqualified	Contacted / won	Fixed / won't fix

Case studies

Live · daily

Job Radar · Stockholm roles

354offers collected

30sent to the LLM judge

5shown each morning

Cheap steps run first (rules, freshness, similarity), so the slow local LLM only judges the 30 most promising offers. Profile-to-role matching, fully local. Built and tested first.

Read the Job Radar case study →

Planned

Lead Radar

Goal: give a sales team a short daily list of companies worth contacting.

A company that posts a data or product role is investing in that area, so it is a likely buyer for a BI tool or a consultancy. Same collector as Job Radar. The resume is replaced by an ideal customer profile.

Planned

Feedback Radar

Goal: show a product team the 5 user problems that matter most today.

Collects app store reviews, public reviews and support tickets, groups them by theme, and scores each theme on severity and how many users it affects. The resume is replaced by the product roadmap and known issues.

What it shows: clear scoring rules, fast iteration from feedback, and agents doing the repetitive work.

PythonClaude CodeLangGraphDifyChromaDBLM StudioScoring rules

AI · Local lab

Agentic Workflow Lab, 100% local

I wanted to learn agentic AI hands-on without sending any data to the cloud, so I built my own lab on my PC.

🔌Local models wired into builders

LM Studio and Ollama connected to Dify, n8n and Flowise running in Docker.

🧠RAG with tracing

LangGraph and ChromaDB answer from my own documents, with every step traced in Arize Phoenix.

⚙️One-command setup

A PowerShell script installs and starts the whole stack, with three working examples to build on.

📄Applied use case: offline document pipeline

Qwen in LM Studio with GPU acceleration and MCP file access parses, self-corrects and structures sensitive documents without sending any data out.

What I learned: trace every step, measure answer quality, and design guardrails for where agents fail.

LangGraphChromaDBArize PhoenixDifyn8nDockerLM StudioQwenGPU

SaaS · Betao AB

Invoicing software for auto-entrepreneurs

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.

SaaSUI and process flowOnboardingData analysisCSATPostHog

Visit the product →

DoggyCompass web app, landing page and phone mockup

Young Enterprise · UF-företag

Supporting a Young Enterprise (UF-företag)

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.

Web appMentoringEntrepreneurship

Visit DoggyCompass →

How I work

Discover, measure, decide, build, automate.

A repeatable loop: understand people, measure behaviour, decide with evidence, ship with the team, then automate what can be automated, privately.

Discover

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.

User researchPostHog surveysLLM synthesis

Measure

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.

PostHogSQLOmni BIPower BIExcel

Prioritise

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.

RoadmapA/B testingScrum PO

Build

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.

Agile deliveryAPI integrationsUX & funnels

Automate with AI

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.

Local LLMsMCPLM StudioQwen3.5

Philosophy

Data gets you to the “what”Users tell you the “why”

I like to get inside a process and find the step where it gets stuck.

At Besedo I started as Head of Planning and built the forecasting and scheduling workbook that four sites used until 2014. Later I went to Bogotá, Kuala Lumpur and Malta to map where the contact centres lost time.

Betao was the same story. I spotted manual steps in the product and worked with the developers to automate them, from the ACRE application to company creation through the Guichet unique API.

At home I run a small lab where I test agentic workflows on local models and on Claude, with the same aim of taking the manual work out of a process.

Senior Product ManagerProduct OwnerAI Product ManagerGrowth PMBI & Data Analyst

Based in Stockholm, Sweden
Languages French (native) · Swedish · English
Methods Agile / Scrum · A/B testing · user research
Training Scrum Product Owner (Scrum.org) · Omni Analytics · SQL (SQLBolt)

Agentic workflows

From automation to agentic workflows

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.

Classic automation

Fixed steps, written in advance
A rule for every case I can predict
Stops or fails on the unexpected

Agentic workflow

Driven by an objective and instructions
Reasons about the result of each step
Finds another route when blocked
Decides alone and goes through to the end

Plan
→
Act with tools (MCP)
→
Check the result
→
Adapt or retry
→
Finish, or ask a human

How I evaluate it

Clear success criteria for each step
A test set of real cases, including the hard ones
Metrics: success rate, accuracy, retries, time and cost
A human review of a sample of the runs
I re-run the tests whenever the model or the prompt changes

Failure modes and guardrails

Endless loops: limits on steps and retries
Invented results: check against the source, validate the format
Wrong tool use: minimal rights, allowed folders, sandbox, human approval before destructive actions
Silent drift after a model change: evaluations and logs
Success claimed wrongly: an independent check step
Data leaving the machine: local models, off the cloud

Workflow builders

Dify Flowise n8n

Green: open source, self-hosted. Orange: fair-code, paid cloud.

Agent building blocks: orchestration, memory and state, observability, web-to-API

LangGraph ChromaDB Arize Phoenix Reverse API Engineer

Vibe coding

AI writes the code. Documents set the direction.

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.

PRD

Product Requirements Document

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.

TRD

Technical Requirements Document

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.

App Flow

Screens, journeys and states

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.

UI / UX Design

Look, feel and interaction rules

Layout, components, colours, typography, spacing and accessibility rules. A shared design language keeps AI-generated screens consistent instead of different on every prompt.

Backend Schema

Data model and APIs

Entities, relations, endpoints and permissions. A clear data model is the foundation the agent builds on, and the cheapest place to catch design mistakes.

Implementation Plan

Step-by-step build order

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.

AI toolkit

Hands-on with local LLMs and Claude

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.

ClaudeClaude CodeQwenDevstral Small 2Gemma 4LM StudioOllamaDockerMemoryFilesystemJS code sandboxRAGPlaywrightBrowser

Logos belong to their respective owners.

Skills

Product, data and AI

Product strategy & roadmapUX & conversion optimisationPostHog analytics & surveysSQL & BIA/B testing & user researchAgentic AIModel Context ProtocolLocal LLM deploymentAI-assisted product decisionsOmni BIAPI integrationsAgile / Scrum

Experience

From forecasting and BI to SaaS product.

2016 – Present · Stockholm

Senior Product Manager

Betao AB

Part of the product team behind solo.fr and portail-autoentrepreneur.fr, SaaS for French auto-entrepreneurs, where I work on onboarding, conversion funnels and the invoicing flow from user research to release.

Automated the ACRE application inside the product. Support now spends 60% less time per case.
Led two INPI API integrations end to end, for company changes and closures. That covered the user funnel and the back-office control panel for support, down to the final decision emailed to the user.
Own the roadmap and QA. Set up the bug and feedback process in Jira Service Desk and prioritise in Jira within Scrum, then run the release tests with the QA managers.
Run an ongoing user study with PostHog surveys. SQL pulls the answers into Omni, where I also built several BI dashboards. Funnels and KPIs stay in PostHog.

SaaSPostHogOmni BISQLJira

2015 – 2016 · Kista

Pricing & Incentives Coordinator

Renault Nordic AB

Dealer invoicing and incentives, with prices and product definitions in SAP. Kept the Nordic KPI and market share reporting up to date and helped the Country Manager present the results.

SAPKPI reporting

2007 – 2015 · Stockholm

Head of Planning to Global Operations Controller

Besedo Global Services AB

Content moderation for classified ads and dating sites. Four roles in eight years.

Global Operations Controller and Business Analyst, 2013–2015. Reporting on efficiency, quality and profitability, with forecasts, built in QlikView. Went on missions to the contact centres in Bogotá, Kuala Lumpur and Malta to set common reporting rules.
Global Business Development Manager, 2012–2013. Business cases for new contact centres in Mauritius, Bogotá and Romania. Designed fraud detection that flags proxies and suspicious IPs.
Business Intelligence Manager, 2011–2012. Forecast incoming ad volumes per country with 92 to 98% accuracy, used to staff reviewers and plan revenue.
Head of Planning, 2007–2011. Built the forecasting and scheduling workbook for about 400 positions on 4 sites. It stayed in use until 2014.

QlikViewForecastingExcelFraud detection

Contact

Let's build something great.

Stockholm · Hybrid & Remote · Open to Senior PM, AI Product, Growth PM

Email me LinkedIn