NotNil Blog

AGENTUX

Fri, 31 Jul 2026 00:00:00 +0000

The release of the Buzz platform by Block puts a spotlight on an agentic problem I’ve been working on for quite a while:

“what UX/UI for AI agents used jointly by a team, and not necessarily dev/tech people?”

Live in the workflow, not beside it

My long-standing position is that agents must interact in the middle of the workflow, so no dedicated app that requires an extra interface — Slack, Teams, GChat, email, in short whatever is already used in a company to communicate.

The wingbeat of the sloppers

Sun, 15 Mar 2026 00:00:00 +0000

For a few years now I have been teaching at a prestigious engineering school (ego booster): it is an entrepreneurship major, which means the students have to build a company project around a product or a service. My session lasts about 3 hours, and my job is to shake them up a bit on the notion of a prototype, and on how, with today’s tools, it is not acceptable not to have an MVP quickly. Safe to say the content has changed a lot over the last few years, first very oriented toward no/low code, then heavily AI-ified. To my great surprise, at the last session a little over 6 months ago, I managed to impress them with a product like v0 / Lovable. I picked one of the projects at random (a sort of marketplace for musicians), asked the student for the specs, and launched v0 on it while I was doing the intro to my session. In 7 minutes his project was ready, a thousand times more finished than what he had managed so far, well helped by his excellent specifications. Then I got silence, except from the 2 or 3 people in the know who already knew v0, and the full attention of the room.

Fenwick vs Robot

Sun, 01 Jun 2025 00:00:00 +0000

Could we play the 7 differences between these 2 images? Do an industrial paint robot and a Fenwick have anything in common?

If your answer is no, would it seem logical to you, if you were in a position to buy the paint robot, to compare its price with that of the Fenwick? And to use the price of the forklift as a bargaining point with the robot’s supplier?

Our GenAI tech stack in production

Wed, 05 Feb 2025 00:00:00 +0000

Let’s talk GenAI tech (but not LLMs)!

I was sharing my Monday observations on the GenAI market, and notably the importance of a robust software foundation.

The fundamentals of a GenAI platform

A GenAI platform rests on fundamental elements: task orchestration (often asynchronous), agents with memory management, intelligent document parsing, a high-performance vector database, and fine-grained observability of LLM generation.

If you do a Google search, sorry, Perplexity, you’ll be offered LangChain or llamaIndex, 2 “popular” frameworks that have the elements cited above. In the end we set LangChain aside; its abstraction layer turned out to be more of a hindrance than anything else. A GenAI project is above all a project of flow orchestration and API calls, nothing that requires a framework.

REX 2024

Mon, 03 Feb 2025 00:00:00 +0000

1 year ago I wrote a post about what we had seen / done in GenAI at Coddity and with some clients, and had drawn some insights out of it. 1 year later, I wouldn’t change much of it (self-congratulation), but if last year I was amusing myself formulating hypotheses, some of them have turned into certainties.

⚙️ Technical

All GenAI projects look alike and need the same components. It is essential to develop and maintain a common software foundation while avoiding “vendor lock”, so as to quickly benefit from the (numerous) new things, test them (and keep the pace).

Have you met Dan?

Mon, 08 Apr 2024 00:00:00 +0000

A few months ago, I had written a post about the hyper-personalization that’s going to crash over our entertainment: I bet that within 5 years, we will consume only content created specially for us: you will watch YOUR series, whose heroine will have every character trait that YOU love, and whose adventures will speak to YOU.

And you will also find YOUR heroine in your Instagram reels feed, who will present you the brand-new iPhone 23 X max pro at $2300 (🤷‍♂️) that YOU dream of so much. And then, while we’re at it, why not tell YOUR heroine about your workday in the evening, via a voice chat, because she understands YOU, she listens to YOU, and she knows YOU by heart.

A ten-million-token heist

Tue, 20 Feb 2024 00:00:00 +0000

This is the story of a 10-million heist, a great comms caper.

If you followed LinkedIn properly, last Thursday Google unveiled Gemini 1.5, their latest LLM, followed a few hours later by OpenAI unveiling Sora, a text-to-video model with a mind-blowing, dreamy rendering (I’ll leave you to watch the now-famous video of the sand chair that runs away). What followed was thousands of posts about those famous videos.

Too bad for Google, because it’s over THEIR Gemini 1.5 demo videos that you should have been marveling / getting excited / hiding.

Why bet on Google in the generative AI race

Mon, 12 Feb 2024 00:00:00 +0000

I don’t want this post to be interpreted as an advertorial in favor of Google, just a cold analysis of what I see around me and on our clients’ projects at Coddity. It will inevitably evolve with the progress and the maturity of OpenAI or Mistral (and their API 🇫🇷).

[DISCLAIMER1] I’m taking Meta and Mistral out of the equation, my point being about the use of LLMs via API.

REX GenAI

Tue, 30 Jan 2024 00:00:00 +0000

While plenty of people are writing predictive posts about AI in 2024, I’m going to do a short REX on the client requests tied to GenAI that we handle / have handled at Coddity for a year now.

Document agents

Unsurprisingly, the majority is made up of requests to develop agents that use documentation / knowledge specific to the company. These requests can be addressed with homegrown RAG-type architectures, or with solutions like Google’s Search and Conversation or, more recently, OpenAI’s private GPTs. The promise of RAGs is fairly high, with performance that depends heavily on how they’re implemented and on the content they have to process. We’re a long way from the “drag and drop your pdf and chat with it” promised by many, at the scale of a company. All the more so because the cost of a high-performing RAG architecture is far from negligible (just look at the cost of managed DBs that include vector search). The challenge for 2024 is going to be evolving these architectures to take multimodality into account, opening new possibilities for RAGs.

happy 2024

Mon, 08 Jan 2024 00:00:00 +0000

What do you mean, “good luck”?

I send you all my best wishes for 2024, and this year, it isn’t just a polite formula.

We’re turning the page on 2023 with the discovery of new antibiotics (the first in 60 years!) by an AI, and the announcement of a highly effective mRNA treatment for skin cancer, available as early as 2025.

Without going back over the AI tidal wave of 2023 and the countless impacts it’s going to have on our lives and societies, I think we’re entering an exponential of technological progress that should let us face the future with a feeling that (it seems to me) has disappeared, and that is missing: optimism.

Young interns

Tue, 12 Dec 2023 00:00:00 +0000

About ten days ago, I took part in the signing of a partnership agreement between the MEDEF, with its president Patrick Martin (yeah, him), and the Association des Parents d’Elèves de l’Enseignement libre (APEL). The aim of this partnership is to bring students’ parents closer to the world of business, and therefore the children. Obviously this echoes the opening of mandatory internships (?*) in seconde, the first year of French high school, announced last week by the Minister of National Education, Gabriel Attal.

The Onclusive affair

Sat, 28 Oct 2023 00:00:00 +0000

Have you been following the Onclusive affair? You should have, because it prefigures what we’re going to live through within a few months / a year, and it underlines our lack of preparation.

Layoff plan

Onclusive is an American company specialized in media and communications, whose French branch counts 447 employees.

In mid-September it announces a layoff plan for 209 of its employees, replaced by an AI. At the end of last week it announces it’s reversing course and pushes its plan announcement back to December. A great victory according to the politicians (those who took an interest) and the unions. A mixed verdict according to Matthieu Moreau.

One more sign

Sun, 24 Sep 2023 00:00:00 +0000

Light is right

Do you know Colin Chapman? If you don’t take an interest in automotive history, he probably means nothing to you. Even if you’ve already come across his creations on the street or in film / TV.

This handsome mustached man created the sports-car brand Lotus, with a credo: “Light is right”. 7, Esprit, Elan, Elise, this maxim found its way into the design of his vehicles: light cars, far less powerful than their rivals but much more effective, making up for their lack of power with agility.

Light is right

Fri, 15 Sep 2023 00:00:00 +0000

Light is right

Do you know Colin Chapman? If you don’t take an interest in automotive history, he probably means nothing to you. Even if you’ve already come across his creations on the street or in film / TV.

The Good, the Bad and the Ugly

Thu, 07 Sep 2023 00:00:00 +0000

The good, the bad & the ugly

A few years ago, I was asked to write a course on business strategy for master’s programs at a business school. It was a fairly complete 9-hour module (if I do say so myself), with fairly varied examples in industry (Airbus vs Boeing, automotive, defense), services (catering, cleaning), food (mass retail), and so on. I mention it because I’d happily add to those examples what we’re witnessing right now in the generative AI market, with the clash between Meta, Microsoft, and Google.

The seawall

Sat, 20 May 2023 00:00:00 +0000

the seawall

OK. I’m pretty passionate about, and fascinated by, what’s happening with LLMs since GPT-4 (so as not to use another term).

My position is that the coding assistants built with LLMs are going to have a monstrous impact on the way we produce software. By monstrous, I mean the end of the shortage of (good) developers, with at least a 30% drop in demand. Why that number? It’s what I can see in the productivity gain of a developer who uses an LLM tool in their production (and it’s the low end announced by every Amazon/Google/Microsoft for their code-specialized LLMs).

Ready-to-wear and bespoke

Wed, 19 Apr 2023 00:00:00 +0000

manners maketh man

I run a company, and I’ve now been using ChatGPT Plus daily for a month, GPT-4 in particular. I stand by what I said in my previous post about the mind-blowing impact GPT is going to have on my sector. The idea of this post isn’t to be alarmist this time, but to take a bit of stock of what I’ve tested and practiced, and also of the reactions I’ve seen around me and on my team.

The day after

Mon, 20 Mar 2023 00:00:00 +0000

my current state

A piece written in a hurry so I could put words on what I’m thinking right now, after a few days of trying ChatGPT-4. What follows may sound dramatic, but I don’t see how it could be otherwise.

Beta

I had tested GPT-3 quite a bit on fairly varied subjects: content writing, a bit of code, and even if I had been impressed, my use of it was really irregular.

A parrot, ChatGPT, and French panache

Thu, 23 Feb 2023 00:00:00 +0000

A minister and a parrot

The paper of record, 20 February 2023

I don’t know if you saw it go by, but I recommend reading this article published online in Le Monde.

The minister interviewed is Jean-Noël Barrot, minister delegate for digital affairs in the current government, and the interview is about the minister’s comments on ChatGPT.

Before you read what follows, I want to be clear that I don’t have the verbatim of the interview. There is a non-negligible chance the remarks were distorted (the rare times I’ve dealt with a journalist, half the transcriptions meant the opposite of what I’d said). Still, watching this interview with the minister, that chance gets smaller.

It's a JWT and it's pronounced jot

Wed, 18 Jan 2023 00:00:00 +0000

We're talking security, so here is a wall

If there is one thing I like about computing, it is the arguments: framework X vs Y, language A vs B, Mac vs Linux vs Win$, Arch Linux vs the world, sysadmin vs the rest of the team.

The problem with arguments is that they can generate noise and hide the useful information. That is exactly what I ran into while implementing JWT on an internal project at Coddity, and on one specific case: user session management.

Cloud and skills, part 2

Sun, 04 Dec 2022 00:00:00 +0000

The France that wins

This article follows on from a previous one, in which I talked about building individual skills, taking as an example a developer who deploys an application on PaaS rather than deploying it on a server, at least once. In this post, I mean to let that line of thought drift toward how skills get built at the scale of our country.

Watch out, this is going to go far!

T-OTP

Sun, 27 Nov 2022 00:00:00 +0000

Article originally written for the Coddity blog

For a while now I’ve been building, in my spare time, a complete authentication service, with the aim of implementing a lot of authentication mechanisms: magic link, login/password, Oauth2, account validation, password recovery, and the famous 2FA.

I’ll admit I used Google Authenticator every day without ever thinking to look at the mechanism “under the hood”. This article is the plain-language version of what I learned.

A cup of Gitea

Sat, 19 Nov 2022 00:00:00 +0000

$20

For 5 years at Coddity we had been using Gitlab’s free tier. With a private namespace, we hosted the code of every side project in the company as well as our SaaS products, the whole thing coming to about 30 users, fifty or so small projects, and 2 bigger projects using Gitlab-CI.

In March 2022, Gitlab announces the end of the free tier for private domains above 5 users. Ok, that’s fair, every company needs to generate revenue and we got plenty out of the freemium offer.

Cloud and skills, part 1

Sun, 06 Nov 2022 00:00:00 +0000

Prelude

What follows is the start of a broader reflection on how computing skills are managed in the age of cloud-everything, whether individual or collective, at the scale of a company, or even of a country.

The famous “side project”

In recruiting I meet about one junior dev a week, from every kind of background: engineering school, DUT/BUT, short program, bootcamp, or even self-taught.

On this kind of profile, we are obviously interested in the projects the candidate has built, and all the more in the ones built on their own time, which very often give a better read on the candidate, their skills, their expectations, and what drives them.

About

Fri, 28 Oct 2022 00:00:00 +0000

Hi, I’m Matthieu Moreau, and I approve this message

If you read this far, welcome.

The short version:

I trained as an engineer and spent more than ten years in telecom (operators and equipment makers) and consulting.

Seven years ago I co-founded a company I am rather proud of, Coddity, which builds digital tools. That work put me up against subjects I care about. Some of them are genuinely interesting (skills, inclusion, teaching). Others just keep life moving (cashflow, my one true love).

Building a high-performing Dialogflow agent, part II

Sat, 05 Mar 2022 00:00:00 +0000

After a first part on the general principles of Dialogflow and on building a high-performing dataset, we’re going to apply all of it to building a conversational agent!

We’ll focus on creating the dataset, and on the traps to avoid. This article, on the other hand, will skip Dialogflow’s integration features, such as context, webhooks, and the nocode Dialogflow CX feature that lets you build and integrate a complete agent without a line of code (well, almost). But don’t panic (the word is very well chosen). We’ll get to that another time!

Building a high-performing Dialogflow agent, part I

Tue, 30 Nov 2021 00:00:00 +0000

In the chatbot world, two approaches clash, with a strong impact on user experience: NLU, or not?

NLU can create a unique conversational experience for users. Implemented badly, it can just as easily produce a truly disappointing one.

At Coddity we specialize in Google’s nocode chatbot platform, Dialogflow, and around it we’re going to walk you through two blog posts:

How do you build and optimize an NLU implemented on Dialogflow? (the subject of this part I)
How do you create a dataset for a fictional bot? (part II, coming up)

NLU?

NLU, for Natural Language Understanding, makes it possible to understand a user’s intent automatically from the sentences they type. This method is one branch of research in AI / data science.

How do you do, fellow kids?

Wed, 06 Nov 2019 00:00:00 +0000

A Flask API in a GitLab CI/CD crust, accompanied by its deployment on Heroku. Or how to find yourself, at 40, not having written any code since Python 1.5, up against a production-deploy problem for a demo, at an Ethereum hackathon full of German and Russian devs in hoodies.

1. A messy hackathon

It all starts with the EthParis 2019 hackathon. Of course, when someone tugs at my feelings and says “No, come on, it’ll be cool, we’ll learn a ton of stuff, doesn’t matter if your dev level is nonexistent, there’ll always be something for you to do, and besides, you’re hitting 40, you have to do this before then.” Yeah, right. Building a small API, quick and dirty, locally, no problem. Learning GitLab CI/CD and Heroku deploys in 2 hours, surrounded by German hackers, is not quite the same thing.