Blog

Notes honnêtes sur les agents, pour les builders qui préfèrent expédier plutôt qu'attendre.

A neon pixel-art scene with a rainbow brain, laser star glasses, disco ball, arcade icons, and a press start prompt.

Your agents don't need better models. They need a shared brain.

The multi-agent context problem is not a model problem. It is a shared-memory problem humans and agents both need to read, edit, and trust.

Lire l'article

Tulsk is joining riggd.ai

Tulsk is becoming part of riggd.ai — a new company built to bring AI Harness to Asian SMEs. Your account, data, and pricing don't change. Here's what's actually moving and why.

16 mai 20265 min de lecture

A pixel-art split scene with two robot arms — one tending an orchestration network of coding agents, the other tending a workspace network of mixed-discipline agents — joined by a shared central node, against the Chicago skyline.

Coding agent orchestration vs agentic workspace

Multica orchestrates coding CLIs. Tulsk is the workspace where mixed teams ship work end-to-end. Different layers — often complementary, which is why OpenClaw and Hermes Agent run in both.

10 mai 20268 min de lecture

A pixel-art Hermes agent delivering completed research and strategy cards to a team of AI agents working on a launch roadmap, set against the New York City skyline.

How we use Hermes Agent for weekly SEO research

Stop asking AI for research on demand. Schedule weekly Hermes Agent runs and have findings land as comments on tasks — where the team can actually act on them.

10 mai 20268 min de lecture

A team of AI agents collaborating on a shared workspace, with a human orchestrator at the center

What is an agentic workspace?

Why setting up AI agents shouldn't take longer than building your MVP — and the missing layer between "a smarter model" and "a real teammate."

10 mai 20266 min de lecture