Pinned Tweet
I Built a SaaS with AdonisJS 7, and I Loved It — OKQ.ME okq.me/blog/adonisjs-7-saas or dev.to/maximeshr/i-built-a-s…
#adonis #saas #webdev
eve is generally available with v1.0.
• Build agents on your own harness
• Ship multi-tenant, multiplayer agents
• Govern & trace sessions with Agent Runs
• Render agent UIs via Next.js, Nuxt & more
Read the blog → vercel.com/blog/eve-is-now-g…
Un condensé de bonnes pratiques d’ingénierie, couplé à l’automatisation et à la puissance de nos agents. Y a plus qu’à… comme on dit !
my AIE talk is up! come hear how the grok @bot team ships so quickly without compromise on quality
youtu.be/O_zcc6Xl12g
10
Si vous n'êtes pas d'accord avec ce qu'écrivent vos agents, trouvez l'origine du problème et corrigez-la au plus vite.
Je ne vois pas pourquoi on oublierait des décennies de bonnes pratiques sous prétexte que c'est un agent qui produit le code.
1
17
My agent runs a hook after every file it writes. In Claude Code, a PostToolUse hook runs vp check --fix on that file, with type-aware Oxlint, in under a second.
Failures go straight back while the code is still in context.
#ClaudeCode #VitePlus #Oxlint
okq.me/blog/agent-feedback-i…
1
2
58
I don’t get why people treat code coverage and code quality as the same thing. They are not. Both are mandatory, and neither replaces the other… I mean 100% coverage on a messy codebase won’t fix the quality… and the cleanest code in a codebase without tests is nothing but guessing :(
15
Your coding agents need feedback in one second, not one minute.
If a third of thirty edits contain a mistake, and each one surfaces a minute late, the agent spends ten minutes waiting. Ask how early each check can run, not which tool to use.
#AI #Agents
okq.me/blog/agent-feedback-i…
4
1
47
Anything I install outside /data disappears on the next restart. That's why Vite+ lives in my home directory.
No nvm, no global installs, no "works on my laptop." An agent that clones a repo gets the versions that repo asked for.
#VitePlus
okq.me/blog/always-on-agent-…
3
2
88
Client code never goes on that box.
Client projects stay on my laptop, in the T3 desktop app. The box only gets my personal GitHub repos. If it's compromised, the worst case is my side projects, not someone else's codebase.
#T3Code #GitHub
okq.me/blog/always-on-agent-…
20
I wanted to start an agent from my phone, walk away, and come back to a pull request.
My laptop sleeps. So I set up a small always-on box on Railway, with the T3 Code template, Claude Code, and Codex.
#Railway #T3Code #ClaudeCode #Codex
okq.me/blog/always-on-agent-…
Des dirigeants ignares dans un système dirigé par l’incompétence…
#PJL2027 Adopté par l'Assemblée nationale : la "taxe assise sur les flux de données numériques émises par les fournisseurs de contenu et acquittée par ces derniers"
Selon les députés PS, "au taux de 0,055 € par giga, un rendement de 10Md€ est attendu".
assemblee-nationale.fr/dyn/1…
17
Typing "make no mistakes" into the prompt? Yeah, that won't do it. Agents still screw up.
What does work is a quality gate before anything reaches your users: tests, evals, linters, and a blind reviewer agent grading against a fixed rubric.
16
Hacktoberfest 2026 isn’t about PRs anymore... and that’s good news! Happy #hacktoberfest 🫡😍
hacktoberfest.com/online/
okq.me/blog/hacktoberfest-20…
3
72
A few weeks ago, I put a rower in my living room. Target: 2000 m under 8 minutes. 🚣 So... I built the tool I needed for my own training — OKQ.ME okq.me/blog/ergy-built-for-m…
ergy.coach
#rowing #indiehacking #builtinpublic
26








