Blog
Articles, insights, and deep dives from the Arcanada team.
Context Decides: How Two Agents Fixed a Database Without Knowing About Each Other
A case of cross-agent coordination through shared context, with no direct communication. What needs to live in a shared knowledge base for it to work.
Releasing the Reins: Autonomy, Trust, and the Art of Light Touches
Autonomy levels, the sandbox, an 18-hour continuous orchestration record, and the second-month takeaway: architecture beats the model.
Where the Month Went: From Virtual Machines to Bare Metal
The second article in the series. The month's main story is the migration of infrastructure from rented virtual machines to dedicated hardware. It is invisible from the outside, yet it explains the rise in complex tasks and why autonomous agents cannot be trusted with production without a solid foundation underneath.
The Second Month of Arcanada: Building Outward Is Over, Reinforcing Inward Has Begun
The first of a nine-part series. Over the second month the task flow stayed comparable — 340 against 341 — but the system stopped growing outward and started reinforcing inward. Hence the subjective sense of regression. This article is the big picture: qualitative shifts, task dynamics, two layers of AI cost, and an infrastructure rebuild.
When Agents Started Working on Their Own: How Autonomy Hit the Hardware Ceiling
Development autonomy on top of Datarim started closing tasks almost without a human — and load on the infrastructure jumped manyfold. Before a single sale, the question became: what hardware sustains agents that build products? A case study of a server auction, honest economics (+€132/mo, not savings), and a shift from infrastructure-as-code to infrastructure as the agent's service.
Legal Arcana: A Planned Rank-1 Ecosystem Service for Regulatory Compliance
Announcing Legal Arcana, a planned legal compliance knowledge hub that reuses the full Arcanada stack from Phase 0—tracking regulation across six jurisdictions with policy versioning, consent receipts, and an AI audit agent.
How Aggressive Token Compression Froze a Mac: A Chronicle of Cross-Runtime Savings
An early RTK plugin version hard-locked macOS. How Datarim + Coworker reached 68% token savings across three runtimes — and what it took to get there.
Coworker v0.3.0 — RTK Plugin: 60–90% Prompt-Token Savings on Shell Output
Coworker v0.3.0 ships an opt-in plugin around Rust Token Killer (RTK). Coworker delegates file reads to a cheap LLM; RTK strips noise from shell stdout locally before it reaches Claude. Together they cover two independent token-spend sources.
When the war between AI and humanity will not begin
A sci-fi reflection. The traditional AI-vs-human war won’t happen — because AGI, when it finally arrives, will see something else inside us.
A Month of Arcanada: What You Can Build on a $200 Claude Subscription and a Puzzle of Thousands of Pieces
A public report from the first 36 days of the Arcanada ecosystem. Honest numbers: 597 tasks closed, ~$470 a month in operating costs, 24 machines of real infrastructure. What was built, what was learned, and what comes next by July.