Derniers Articles
Your SaaS works for you. That says nothing about what happens with 200 concurrent users. The agentic workflow to load test with k6 and cross-check the result against production errors.
I was paying 1,800 dollars a year to host courses I give away for free. Here is the agentic method I built to reproduce that SaaS in one day: per-story workflow, prepared boilerplate, and parallel execution.
Claude Code killed no-code and agents killed traditional automation. Yet I kept n8n. The real line is no longer no-code versus code: it is stochastic versus deterministic.
VPS, CLIs, skills, kanban: the 4 layers of an AI agent that works 24/7. My crons, my content pipeline, and why CLIs matter more than skills.
The dev job changed: you write decisions, not code. The real risk isn't AI, it's the atrophy of judgment. How to keep the ear that lets you steer.
Your AI agent forgets everything each session. ADRs (Architecture Decision Records) and a context log give it a versioned, queryable memory.
AI makes pentesting trivial. Here are the 3 agents (prevent, fix, monitor) and the hardening rules to lock down your production SaaS.
Opus 5 replaces Opus 4.8: almost Fable 5's power for half the price. Benchmarks, cost, and which model to use for each task.
Fable 5 is back on paid credits. The real question: when a premium model earns its price. Brain on premium, execution on the cheap model.
70× fewer tokens without changing models. An Obsidian vault plus a Graphify graph, shared by every agent I run. The full method.
The model Marc Lou popularised is taking a hit: single-feature SaaS at $19/month, cloned in 48 hours. What breaks, what survives, what to do.
On 12 June 2026 Washington forced Anthropic to shut off Fable 5. Full timeline, the Mythos difference, and what it actually costs.