---
title: "Work"
description: "My proof dossiers: real projects, delivered directly or inside a partner’s team, with the key points in thirty seconds, then the proof and the limits."
url: "https://mc-stud.io/en/work"
lang: "en"
updated: "2026-10-12"
---

Work · 9 case studies

# Proof files

Real projects, delivered directly or inside a partner’s teams for its end clients. Each case study gives the key points in thirty seconds, then the story, the proof and the limits.

Clients

- [Santécie](https://santecie.com/)
- [Silico](https://silico.fr/)
- [Essan NFC](https://www.essannfc.com/)

Santécie 2024-2026 AI In production

## [Automating after-sales returns to manufacturers, with a trace of every request](https://mc-stud.io/en/work/robotform-after-sales-forms)

Santécie’s after-sales return files are routed to the right manufacturer forms and filled automatically, with an audit trail for every request.

**Stake**

Every after-sales return must reach the manufacturer on that manufacturer’s own form; copying files across by hand took time and invited costly mistakes.

**Impact**

Data entry becomes configuration: at least 500 hours avoided per 10,000 requests, and a failed request is replayed without redoing the batch.

Through a partner

Read the case study

Silico 2026 AI In preparation

## [Training developers in agentic engineering, in eight sessions](https://mc-stud.io/en/work/agentic-engineering-training)

I am preparing an eight-session path, designed to take developers from occasional use of an assistant to verifiable agentic engineering, including knowing when to do without it; first session on 16 October 2026.

Direct

Read the case study

2026 AI Pilot

## [Zedflow, agent flows you can read, compose and control](https://mc-stud.io/en/work/zedflow-agent-flows)

With Zedflow, an agent flow is read, validated and composed like a program, and sensitive decisions wait for a human approval.

Internal project

Read the case study

Santécie 2026 AI Demonstrator

## [Choosing a health-card reading engine on evidence, not on a demo](https://mc-stud.io/en/work/scie-ocr-health-insurance-cards)

The choice of a reading engine for supplementary health insurance cards rests on a reproducible benchmark, not on a sales demo.

Through a partner

Read the case study

Silico 2026 AI

## [A controlled development environment, ready for coding with AI](https://mc-stud.io/en/work/coder-developer-environments)

Silico’s developers have standardised environments, described as code and hosted on controlled infrastructure, the foundation of a governed use of AI.

Direct

Read the case study

Essan NFC 2025-2026 AI Paused

## [Turning a training method into a mobile app and its back office](https://mc-stud.io/en/work/nfc-training-mobile-app)

The NFC method exists as a product: a mobile app for members and a back office for the team, on a single data foundation.

Through a partner

Read the case study

2026 AI Demonstrator

## [A memory shared between agents, partitioned by role](https://mc-stud.io/en/work/agent-memory-isolation)

Several agents rely on a shared graph memory, and none of them can reach another’s scope.

Internal project

Read the case study

2024-2025

## [A paid-leave request application for CICP2R](https://mc-stud.io/en/work/cicp-leave-requests)

On the employer side, paid-leave requests and days to pay are entered in a dedicated application, then go through an explicit validation.

Through a partner

Read the case study

2026

## [Connecting LumiSafe masts to a software gateway, for railway track safety](https://mc-stud.io/en/work/lumisafe-mast-signalling)

LumiSafe masts talk to a software gateway over a serial protocol that evolves without breaking masts still running an earlier version.

Through a partner

Read the case study

Reading guide

## How to read a case study

Every case study fits in five lines, from the stake to the limits; the narrative develops each one. The limits are part of the proof.

1. ### Stake
   What was at stake for the client, in one sentence.
2. ### Mechanism
   How the system produces that change.
3. ### Proof
   What demonstrates it: measurements, usage, material available on request.
4. ### Impact
   What it brings to the business, in time, risk or quality.
5. ### Limits
   What is not demonstrated, or still needs work.

## Let’s talk about what AI could change for you

A 30-minute discovery call, by video and with no commitment, to talk about your project, your constraints and the best next step.

[Book a call](https://calendar.app.google/VQTPrCgNvQSNwdA7A)

[contact@mc-stud.io](mailto:contact@mc-stud.io)