use case driven

use case driven

@tpierrain.bsky.social

VP of Tech @shodo.io . Change Agent (powered by software) now living in Lyon(France). Former VP of Eng in a booming scale-up. Organizer of #DDDFR #AntiColonialist https://medium.com/@tpierrain +100 talks: https://github.com/tpierrain/me-myself-and-i

1K followers303 following1.1K posts

use case driven
@tpierrain.bsky.social

Having AI write the code and humans review it is like putting a Formula 1 engine in a carriage. And keeping the wooden wheels. Speeding up with AI starts with rethinking verification.

use case driven
@tpierrain.bsky.social

We can keep plugging AI into tools built for humans, and be surprised when we hit the wall. Or reinvent everything for the agentic era, keeping humans where they are irreplaceable: understanding the business, deciding what to build, and framing what “done” means. That last part is pure engineering.

use case driven
@tpierrain.bsky.social

As Alberto Brandolini said once: “Software development is a learning process, working code is a side effect.” The countdown has started. And the hardest part begins when it works.

use case driven
@tpierrain.bsky.social

Git was designed for humans who work offline.Their “devs” are now agents, connected all the time. Git’s superpowers became its kryptonite. The outcome of the redesign: checkouts 100x faster (a few seconds instead of several minutes).

use case driven
@tpierrain.bsky.social

Quand les décoloniaux de @parolesdhonneur.bsky.social décryptent mediapart, ça donne une série inégale mais globalement très intéressante. Mention spéciale pour l’épisode sur Plenel 🍗 bsky.app/profile/paro...

Paroles d’Honneur@parolesdhonneur.bsky.social

Nouvelle vidéo ! DE QUOI MEDIAPART EST-IL LE NOM ? EP #5 - LE PLÉNÉLISME - KOUVELAKIS, VIEILLESCAZES, BOUAMAMA youtu.be/T7ty_LM4aAU

youtu.beDE QUOI MEDIAPART EST-IL LE NOM ? EP #5 - LE PLÉNÉLISME - KOUVELAKIS, VIEILLESCAZES, BOUAMAMAYouTube video by Paroles D'Honneur
use case driven
@tpierrain.bsky.social

« Si tu ne peux pas expliquer en 30 secondes le code que tu as généré, tu commences à empiler de la merde. » Une heure chez If This Then Dev, enregistrée en juin, sur les fondamentaux qui restent quand le code devient une commodité. ⬇️

use case driven
@tpierrain.bsky.social

Au programme : mechanical sympathy, modèles mentaux, l'importance d'expliquer pour comprendre, forcément un peu d'IA, et pourquoi les sujets humains sont bien plus durs que les sujets tech. Merci Bruno Soulez 🙏 liens vers différents formats : www.ifttd.io/episodes/arc...

ifttd.ioIFTTD #374 - Architecture : Pourquoi les sujets humains font toute la différence avec Thomas Pierrain"les sujets tech c'est de la rigolade par rapport aux sujets humains." Dans l'épisode 374 j'ai reçu Thomas Pierrain pour parler de "Architecture"
use case driven
@tpierrain.bsky.social

Over the past few days, I've mostly been experimenting with letting go. ⬇️ (thread) My Claude Code sessions have been running in loops (loop engineering), including overnight. I wasn't constantly watching them. I'd check in every morning, or after a long run, to steer them in a new direction.

View full thread
use case driven
@tpierrain.bsky.social

To be clear: I'm still digging. But so far, I haven't managed to gather the conditions that make Loop Mode reliable and efficient — too much upfront framing, and token quotas reached too soon. The cost/benefit isn't there yet (for me).

use case driven
@tpierrain.bsky.social

Loop Mode is still worth digging into — for what's coming next. But today, the best return on investment is to secure and optimize Interactive Mode. That's where the leverage is, right now. #loopEngineering #contextEngineering

use case driven
@tpierrain.bsky.social

With AI coding agents, incidents happen every day. Fixing without capitalizing means buying the diagnosis at full price — and throwing away the receipt. New article: Knowing when to capitalize instead of just fixing — the harness-maker’s craft. medium.com/@tpierrain/k...

medium.comKnowing when to capitalize instead of just fixing — the harness-maker’s craftTL;DR: with an AI coding agent, incidents happen every day. You can fix them one by one, and pay for the same diagnosis again and again. Or…
use case driven
@tpierrain.bsky.social

I feel very privileged: my job has never stopped stimulating me intellectually. Every decade, a new obsession: code design, architecture, multi-threading, latency vs. throughput, dist systems, SRE, DDD & functional architecture, management & autonomy, product, and now AI. Endless ♥️.

use case driven reposted

Nick Tune
@nick-tune.me

Replying to @tpierrain.bsky.social

Yeah I have the same approach. All my time goes into improving the harness so that I can focus on product and domain model. This approach rewards ultra standardisation of a codebase and a process I believe!

use case driven
@tpierrain.bsky.social

Over the past few days, I've mostly been experimenting with letting go. ⬇️ (thread) My Claude Code sessions have been running in loops (loop engineering), including overnight. I wasn't constantly watching them. I'd check in every morning, or after a long run, to steer them in a new direction.

View full thread
use case driven
@tpierrain.bsky.social

So, in Loop Mode, I don't watch the agent continuously. In Interactive Mode, I want to see everything. That's not contradictory. It's complementary. I'm still digesting these experiments. If you'd like a proper write-up, let me know.

use case driven
@tpierrain.bsky.social

Over the past few days, I've mostly been experimenting with letting go. ⬇️ (thread) My Claude Code sessions have been running in loops (loop engineering), including overnight. I wasn't constantly watching them. I'd check in every morning, or after a long run, to steer them in a new direction.

View full thread
use case driven
@tpierrain.bsky.social

In Interactive Mode, you take back control. Finalize before a release. Make trade-offs. Verify results. Redirect the work. Here, you're working interactively — and two resources matter: context window and token quota. #contextEngineering #harnessEngineering

use case driven
@tpierrain.bsky.social

Over the past few days, I've mostly been experimenting with letting go. ⬇️ (thread) My Claude Code sessions have been running in loops (loop engineering), including overnight. I wasn't constantly watching them. I'd check in every morning, or after a long run, to steer them in a new direction.

View full thread
use case driven
@tpierrain.bsky.social

In Loop Mode, you define the harness, the verification criteria, and let the loop run. The agent is still being piloted — but most of the piloting happens upfront. Constantly watching the loop makes no sense. It's an anti-pattern.

use case driven
@tpierrain.bsky.social

Over the past few days, I've mostly been experimenting with letting go. ⬇️ (thread) My Claude Code sessions have been running in loops (loop engineering), including overnight. I wasn't constantly watching them. I'd check in every morning, or after a long run, to steer them in a new direction.

use case driven
@tpierrain.bsky.social

Most of the time, though, they were working without me. And that's exactly what I was aiming for. So yes, it's a bit counterintuitive to share a screenshot taken while I'm sitting in front of the screen, watching a session.

use case driven
@tpierrain.bsky.social

Given how much time I spend on harness engineering, I'm this close to updating my LinkedIn title: harness maker (bourrelier in French) for AI agents. The job hasn't changed: build the harness so the beast pulls straight without kicking over the traces. The job of the future, established 1850. 🍴

use case driven
@tpierrain.bsky.social

Loop engineering. Graph engineering. Haven't had time to dig in yet? My final episode cuts through the buzzwords: both just draw a context boundary — in time, and in space. And a surprise guest: a twenty-year-old concept, dear to my heart 😉 medium.com/@tpierrain/w... #graphEngineeering

medium.comWhat if /clear was no longer our job?Final episode of the “Work smaller, ship fewer bugs with AI” series. The first one laid out the diagnosis: long sessions produce defects…
use case driven
@tpierrain.bsky.social

C’est complètement dingue. Ce soir à Lyon on entends les cigales. Pas à la campagne ni même très fort hein, mais des cigales ici ou là dans le centre 🤯 (et il fait chaud samere 🥵)

use case driven
@tpierrain.bsky.social

I /clear my coding agent all the time. Mid-task, even. It costs me nothing: the state of my work lives in the repo, not in the conversation. "If I clear right now, what do I lose?" If the answer isn't "nothing", episode 2 is for you 👇 medium.com/@tpierrain/a... #HarnessEngineering

medium.comA good harness makes /clear freeSecond episode of “Work smaller, ship fewer bugs with AI”. The first one (Same model — so why do some devs ship more bugs?) laid out the…
use case driven
@tpierrain.bsky.social

Quick question: how do you monitor your AI coding sessions? Not the output. The session itself. How long it's been running, how much your agent is carrying in its context right now. Same model —so why do some devs ship more bugs? medium.com/@tpierrain/s... #ContextEngineering #harnessEngineering

medium.comSame model — so why do some devs ship more bugs?TL;DR: your AI never tells you when it stops paying attention. As a session grows longer, your rules get buried, your context still holds…

use case driven reposted

Christophe Michel
@christopheml.fr

Pour vous donner une idée de la taille gigantesque du panache de fumée dégagé par les incendies en Gironde et dans les Landes. (concentrations en PM2.5, Ventusky)