Making the loop act without losing control in AI agents

Making the loop act without losing control

Second article in the series on building Bloom in a week: how to give an agent real freedom to act in the world — writing real events into Google Calendar via MCP — without giving up control over when and how it acts.

July 13, 2026 · 12 min · Cairo Cananea
Who decides: the code or the model, in multi-agent systems

Who decides: the code or the model?

First article in a series on building Bloom-for-Learning in one week: why the most important decision in any agentic system is deliberately defining what belongs to deterministic code and what belongs to the model’s judgment.

July 12, 2026 · 18 min · Cairo Cananea