Freelancer profile translated to English.

Description

I manage fleets of AI agents in production.Applied to sales, this means: finding the right prospects, enriching them, qualifying them, feeding them into the CRM, and analyzing sales calls. Once set up, it runs, and your teams maintain control.

What I've already implemented:

- At an AI firm in MedTech, I operate outreach agents on several thousand leads. For one campaign: 9,000 sourced prospects, 4,789 retained after qualification, 64.7% open rate, and 19% response rate.
- A workflow that enriches, qualifies, and fills the CRM automatically, from a business card photo to a complete record, with no re-entry.
- An agent that listens to every sales call and extracts decisions, objections, and next steps.
- Auguste: a knowledge base that agents query. It answers company-wide questions about the CRM, calls, and campaigns, citing its sources.
- Two SaaS products I built and launched alone, from back-end to interface.

I am obsessed with clarity and organization in my systems,whatever they may be: I document everything. You see what the system does, how much each action costs, and you can take over whenever you want.

Regarding tools, I use n8n, Make, or Clay when it makes sense. The core runs in TypeScript on Trigger.dev, with Langfuse for all tracing. I spent 1,230 hours on Claude Code managing fleets of agents on highly varied workflows. The Anthropic stack is my foundation, but I now couple Claude with Codex, and my outreach agents also ran on DeepSeek and Mistral. I switch models based on the task or budget.

Sales is where I deliver the most, but these systems work on pretty much any process that is still done manually. If something is eating up your time, tell me where the bottleneck is, and we'll see what's worth automating.

Industry field of expertise

Languages

French
Native or bilingual
English
Native or bilingual

Workplace preferences

Can work on-site

Paris (up to 50km), Lyon (up to 50km)

Agify
GTM Engineer
TECH
October 2025 - Today (10 months)
France
Design and optimization of AI agents delivered in production for clients in the medical sector.

I am involved in agent and task development, prompt engineering, monitoring, and observability (Langfuse). Working in TypeScript within a large-scale orchestrated agent architecture.

Concrete deliverables:

End-to-end outreach agents: cross-sourcing from multiple sources (academic research, company data, buying window signals, contact details), writing personalized messages, and managing sending campaigns to thousands of leads.
A competitive intelligence agent operating autonomously on WhatsApp, performing OCR, adding leads to the CRM, searching for information, etc.
Sales call analysis agent: each call evaluated according to best social engineering practices, with actionable summaries produced at the end of the call for continuous improvement of the sales team's performance.
AI Agents Typescript LangFuse RAG Business Process Automation
Carots.fr
CTO
SOFTWARE PUBLISHING
April 2026 - Today (4 months)
Paris, France
CTO/Technical Lead at Carots — Pre-revenue SaaS
I lead the entire technical side of our SaaS, starting from scratch and launching into production in two months: a codebase of over 150,000 lines (Dart and SQL), now used daily by three stables, approximately 90 daily active users. The product is intentionally in private beta while we refine it before public launch.

The challenge isn't just writing code, it's making the codebase operable by a team. I implemented a complete production workflow on Linear connected to Claude Code and a suite of skills I developed, structuring the transition from idea to code. I created an agent that translates requests from my two non-technical co-founders into well-defined, ready-to-implement tickets: they fully contribute to the product without touching a line of code. I even trained them to manage their own projects on Linear using this system.

Stack Flutter Supabase
Flutter AI Engineer Project Management AI Orchestration Claude Code
Prestance.io
RAG Engineer
SOFTWARE PUBLISHING
January 2026 - March 2026 (2 months)
Paris, France
Design and solo production of an AI-powered CV analysis SaaS, from architecture to interface, with its own acquisition channel.
The analysis pipeline combines several models based on their roles. An initial pass with Claude Haiku identifies missing angles in a CV and selects the relevant reference article; user responses are then fed to Claude Sonnet for in-depth analysis. CVs are read by extracting data from valid PDFs, with an OCR fallback for non-standard formats, ensuring no document is rejected.
RAG relies on vector search (pgvector, embeddings) which injects the most relevant editorial content into the model: each analysis is thus fueled by a knowledge base that I maintain myself.
This base comes from the acquisition channel I built: a daily SEO publication, driven by a workflow I optimize weekly based on Google Search Console data and user behavior via the analytics tool. The content that attracts visitors is the same that refines the quality of the analyses. Closed loop.

Reliability treated as a priority: safeguards against fabricated responses, injection security for inputs, cost control (caching, injection limits).
RAG AI Engineer LLM Vector Embeddings Context Engineering