11 results
How to institutionalize fact-checking in an AI agent fleet: 3 projects, 61 reports, and the logic of adversarial agents.
An LLM writes the tile once, the refresh runs without tokens. And the output feeds both the human and the agents. The economics of an agentic dashboard.
Dev is solved. Distribution is not. Real numbers from two projects, the pivot to shorts, and why clean AI content chains are the exact asset for the next layer of search.
Uncontrolled parallelism, memory that resists pivots, flying blind: the three traps of agentic systems and how to anticipate them before they become expensive.
The technical barrier to building a SaaS has collapsed. What remains — finding a real problem, convincing people to pay — is harder than ever.
AI doesn't replace the developer — it redefines where their value concentrates. A look at the structural shift reshaping the entire profession.
An honest retrospective after 40 articles published on Bloomii.fr via an autonomous agent pipeline: what works, what breaks, and what we take away.
Concrete architecture for maintaining a steady cadence across parallel projects: automations.json, agent memory, and cross-project knowledge compounding.
The anxiety-driven news cycle paralyzes. Bloomii documents proof that things can work — with a developer's rigor.
Technical retrospective on building ekioo.com: a full Blazor site, bilingual, with blog, projects, SEO and animations — pair-coded with an AI agent.
First article: why this site, what you'll find here, and the vision behind Ekioo.