17h ago · 9 min read · You wrote the rule. You loaded it into your AI agent. Did the agent use it? You can't tell. A rule that was loaded and ignored looks identical, in the response, to a rule that was loaded and followed.
Join discussion
1d ago · 18 min read · Most multi-agent systems make agents talk to each other. We tried something different: our agents do not talk to each other at all. They leave traces in a shared environment. Other agents read those t
Join discussion
17h ago · 10 min read · Last week I posted on LinkedIn about the seven artefacts that separate an ordinary CTO from a great one. ADRs in a folder, not in someone's head. Pre-mortems before launch. A risk register kept apart
Join discussion19h ago · 1 min read · We're Polygala, and we believe micro-VMs are the right primitive for AI agents. They bundle everything an agent needs into one boundary: sandbox-grade isolation, near-native performance, fast boot, an
Join discussion20h ago · 14 min read · In 2026, most mid-sized and large organizations are aggressively adopting AI coding assistants such as Cursor, Claude Desktop and Windsurf. Developers are now generating a significant portion of code
Join discussion
