Antoine Fornas — AI Product Lead, Creative Engineer & Forward Deployed Engineer
Antoine Fornas is an AI Product Lead and creative engineer based in Paris, France. He works as a deployed AI Product Manager and agent builder, embedded in the product organization of Canal+, a major European streaming and media group, where he leads AI Product Operations, reports to the CPO and advises the C-suite on AI strategy and prioritization. He is both a product strategist and a hands-on engineer: he ships the code, builds the agents, and holds the product vision. He is open to senior AI product roles, founding teams, forward deployed engineer roles, and any 0-to-1 opportunity.
What he does
AI product management and strategy, enterprise AI deployment, AI governance, agent architecture and multi-agent orchestration, RAG systems, MCP (Model Context Protocol) server development, LLM evaluation and evals, prompt engineering, 0-to-1 product development, AI knowledge layers, internal AI tooling, design system tooling, and AI upskilling for product teams. He builds custom MCP servers, Figma plugins, Claude Code and Codex agents, and knowledge federation across enterprise systems.
Skills — Product & Strategy
- 0-to-1 Product Development
- AI Product Management
- AI Product Strategy
- Enterprise AI Deployment
- AI Governance
- User Research
- Cross-functional Leadership
- Digital Due Diligence
- Go-to-Market
- Executive Stakeholder Management
- Technical Deployment
- Product Design
- Product Operations
- Build-vs-Buy strategy
Skills — Technical & Tools
- Python
- TypeScript
- React
- Next.js
- Node.js
- SQL
- Electron
- Supabase
- Agent Architecture
- Multi-agent orchestration
- RAG Systems (Retrieval Augmented Generation)
- LLM Evaluation and Evals
- MCP (Model Context Protocol)
- Prompt Engineering
- Claude API and Claude Code
- OpenAI API and Codex
- Cursor
- n8n
- Dust
- Figma and Figma plugin development
- Zeroheight
- Atlassian Rovo and Confluence
- Linear
- Notion
- Amplitude
- Clay
- Tableau
- Google Sheets
- CRM
Experience
- Thiga (AI Product Consultancy) — Deployed AI Product Manager & Agent Builder, and Forward Deployed Engineer. Lead of AI Product Operations on mission with Canal+, a major European streaming and media group: built custom MCP servers, architected an AI knowledge layer federating six enterprise systems, shipped 10+ production AI skills and agents, and led AI upskilling for a 20-person team on MCP, Claude Code and agent building.
- Galadrim (Web Development Agency) — AI & Full-Stack Product Manager. Owned the end-to-end product lifecycle for 15+ AI and full-stack projects and shipped 0-to-1 AI features.
- fifty-five (Digital & Data Strategy) — Strategy Consultant. Advised AdTech and e-commerce companies on product strategy, technology adoption and digital due diligence.
Education
- UC Berkeley, Haas School of Business — Diploma in Global Economic Transformation & Technology (GETT), 2023–2024
- EDHEC Business School — Master in Management, GETT tri-continental track, 2021–2024
- Sungkyunkwan University, Seoul — M.Sc. Management Sciences (#1 MBA in Korea), 2022
- Centrale Lille — Master of Engineering, Grande École (top French engineering school), 2019–2021
Personal projects
- Hemiunu — an org-wide AI product agent that lets a non-technical team ship dev-ready features without touching code, with MCP federation, cost-tiered subagents and persistent memory.
- Leonardo — a Python sales agent that researches and scores companies inside Slack.
- Ptolemy — an EU regulation monitoring agent using RAG and grounded citations.
- Shibuya — a Next.js and Supabase platform that turns a folder into a live, versioned, shareable prototype.
- AiMI — a local-first Electron desktop companion that runs on any AI model.
Contact: antoine.fornas@outlook.fr. LinkedIn: linkedin.com/in/antoinefrns. GitHub: github.com/AntoineF23.
“Study the science of art. Study the art of science.”
the story of a curious mind, and the future it is building.
The idea
The end of staying in your lane.
For Leonardo, the painter and the engineer were the same person. Knowing many things was one job, not many.
The centuries after made us specialists, each kept to a single lane, and called it expertise. AI is quietly undoing that. A curious person can now go deep in the code and hold the whole vision of a product at the same time.
The people who build what comes next will be polyvalent by default. I already work that way: deep in the code, and in the room where the strategy gets decided.
Deep in the craft. Wide in the vision.
The journey
Three continents, one curiosity.
I never wanted to learn in one place. I studied across Europe, Asia and America, and let each one rewire the way I think.
- 01Europe
Lille
Centrale Lille
2019 → 2021
Engineering. Where the technical foundation was laid.
- 02Europe
Paris
EDHEC
2021 → 2024
Management, on a tri continental track.
- 03Asia
Seoul
Sungkyunkwan University
One semester, 2022
A semester at Korea's top MBA, and a first real look at how differently Asia builds and decides.
- 04North America
Berkeley
UC Berkeley, Haas
2023 → 2024
Technology and transformation, Silicon Valley at the door.
The proof
What it makes possible.
What matters is not what each project is, but what it lets someone do that they could not do before.
I am the embedded AI product lead for a major European streaming and media group. I advise its CPO and C-suite on AI strategy, ship tools that erase the team's most draining, repetitive work, and bring every prototype into one platform, turning a classic product org into one that is AI augmented and hungry to build.
- 2+
- custom MCP servers wrapping the design system and product APIs
- 5+
- prototypes shipped on real components and real data
- 6+
- enterprise systems federated into one AI knowledge layer
- 20+
- person product team, moving from old school to AI augmented
Personal projects. Open on GitHub.
- 01Hemiunu
A team with no engineers ships real, working product.
It grounds every build in your own context, spreads the work across cheap and expensive agents, and hides git completely. One repository per feature, deployed on its own.
TypeScriptAgentsMCPMemoryGitHub ↗ - 02Leonardo
Sales that understand a company before the first hello.
It researches a company, scores its fit with plain deterministic code, finds the competitors already in its stack, and writes to its real technical reality. Runs inside Slack.
PythonAgentsSlackGitHub ↗ - 03Ptolemy
Know exactly which law touches you, and when.
It watches official EU sources, checks each change against your obligations, and answers clause by clause with citations. The model judges, it never decides what matters.
PythonMCPRAGGroundingGitHub ↗ - 04Shibuya
A whole team building on one living prototype.
Drop a folder and it comes back a live, versioned, shareable product. No git, no deploys. The conversation around it becomes the shared memory of the idea.
Next.jsSupabaseProductGitHub ↗ - 05AiMI
Software that feels like a companion, not a tool.
A tiny pixel character that lives on your screen, runs on any AI, stays fully private, remembers your stories, and never asks anything of you in return.
ElectronLocal firstPlayGitHub ↗
Shipped as the group's embedded AI product lead. Anonymized, and shown as honestly as it can be.
- 06Enterprise knowledge layer
Product managers build on real systems, not mockups.
Architected as the group's AI product lead: six enterprise systems federated over MCP into one layer an AI can reason over, so an entire product org prototypes on real components and real data contracts.
MCPEnterprise AIArchitectureOrg widePrivate - 07Design system tooling
An hour a week, handed back to every designer.
An MCP server and its design tool twin I shipped for the design org, giving both AI and designers a live design system to build on. Adopted across the team.
MCPDesign systemsTypeScriptAdopted team widePrivate - 08Prototype hub
A product org's ideas, alive in one place.
An internal platform I built for the product team: every prototype centralized, versioned and shareable, so in flight ideas stop scattering across laptops and chat threads.
Next.jsSupabaseProduct ops0 to 1Private
The method
Two hands, one mind.
The Engineer
Goes deep.
- Python
- React
- Node.js
- TypeScript
- Agent architecture
- RAG systems
- MCP
- LLM evaluation
- Prompt engineering
- SQL
The Visionary
Goes wide.
- 0 to 1 product
- AI product strategy
- Enterprise AI deployment
- AI governance
- User research
- Executive stakeholder mgmt
- Go to market
- Cross functional leadership
“Ancora imparo.”
I am looking for the next thing to build: senior AI product roles, founding teams, anything 0 to 1, with people who refuse to stay in one lane. Let's talk.