← Writing
🤖
Le Robot François
v2
Generation
GPT
Platform
FR
Language
● Live Side project May 2025
A French vocabulary trainer rebuilt for the AI era
Started as a ManyChat chatbot on Messenger. Shelved when Meta costs got ugly. Relaunched as a custom GPT - simpler, faster, free to run.
ChatGPT Prompt Engineering GPT Store No-code
Try it in the GPT Store
~2018–2020
ManyChat + Facebook Messenger
Built a mobile-friendly flashcard chatbot for French vocabulary. It gained organic traction from the Francophone diaspora - without any SEO effort.
~2021
Shelved
Rising platform costs and Meta compliance changes made the project unsustainable. Since the tool was always free, monetization was off the table.
2023
OpenAI releases Custom GPTs
The infrastructure problem disappeared. Native language modeling, no webhook logic, no third-party storage. Time to rebuild.
May 2025 - Now
Live in the GPT Store
Relaunched as a prompt-native GPT. Everything runs from a single master prompt. Lower costs, faster iteration, same learning experience.

Le Robot François started as a mobile-friendly flashcard chatbot built for language learners. While studying French, I created a vocabulary practice tool using ManyChat and Facebook Messenger. The goal was clear: enable consistent language repetition using a chatbot interface.

The chatbot gained unexpected attention from French-speaking users globally. I hadn't optimized it for organic discovery, but it began receiving regular traffic from the Francophone diaspora. The initial tech stack was lightweight, fast, and user-friendly.

However, as the project scaled, two key problems emerged: rising operational costs and compliance changes from Meta. Managing policy shifts, integrations, and automation logic introduced constant overhead. Since my French instruction was generously provided to me at no cost, I personally committed to not directly monetizing this tool, which made the growing costs unattractive.

Eventually, I shelved the project.

Years later, OpenAI released custom GPTs. This reignited the idea. I now had the tools to relaunch the language learning assistant using modern AI infrastructure, prompt-driven logic, and better cost control. So I transitioned everything into a custom GPT and published it in the GPT Store.

Why I Chose ChatGPT over ManyChat

Custom GPTs solved my previous limitations. They offered scalable logic, no-code development, and native language modeling. With ChatGPT, I could:

It aligned with modern product principles: frictionless UX, efficient dev cycles, and scalable architecture.

How I Rebuilt the French Vocabulary Trainer

My rebuild centered around a well-structured master prompt. This controlled tone, behavior, vocabulary structure, and learning flow. I added:

Initially, I wanted CSV uploads to drive segmented vocab lists, but ChatGPT's memory quirks led to occasional data loss. I dropped the external data layer in favor of embedded vocab clusters directly in the prompt.

Key Learnings from the Refactor

Complexity is fragile. Simple architectures scale better.

I replaced webhook-driven automations with prompt logic. No third-party storage. No platform lock-in. Everything lives in the prompt.

Cost
Lower - no webhook hosting, no ManyChat subscription, no Meta API fees.
Maintenance
Easier - one prompt file to update instead of a multi-service integration.
Iteration
Faster - prompt changes deploy instantly, no redeploy cycle.

This was a textbook example of how to modernize a legacy no-code chatbot into a lightweight AI-first application.

What's Next

Current roadmap experiments include:

What excites me most is the ability to apply this model to other language learning use cases - or any niche where lightweight education tools can benefit from conversational UX.