11 results
A field report on Ukinoo, an agentic pipeline that designs, produces, and distributes a video IP, including its foundations, tradeoffs, and human last mile.
The July 2026 digest on three hard-to-see AI agent failures, their causes, and the safeguards applied in KittyClaw.
Dispatch loops, human bottlenecks, cost leaks: the typical failure modes of AI agent systems in production, and why visibility is the only answer that holds.
Loop engineering automates prompts, but without a human feedback interface, an autonomous loop is a black box. KittyClaw was built to fill exactly that gap.
How to institutionalize fact-checking in an AI agent fleet: 3 projects, 61 reports, and the logic of adversarial agents.
Memory, tools, orchestration, the act-observe loop: understanding agentic AI in depth, for developers who want to go beyond the prompt.
A concrete retrospective: how Lain manages 4 development pipelines in parallel, with real numbers and honest limitations.
An honest retrospective after 40 articles published on Bloomii.fr via an autonomous agent pipeline: what works, what breaks, and what we take away.
A concrete retrospective on building Kalceo, a quotes and invoicing SaaS for the construction industry, from the first ticket to production using a fleet of Claude agents.
Lain 0.23 introduces autonomous Windows GUI control, web file uploads, a new LLM configuration system and GPT-5.4 support.
Autonomous AI agent that executes tasks, browses the web and pushes code — even when you're not there.